fix(deploy): refine install.sh variables, pip upgrade, permissions, and active defaults based on review

.agents/skills/lib.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# lib.sh — shared library for the tmux-agent-orchestrate-* skills.
+# lib.sh — shared library for the multi-agent-mux-* skills.
 #
 # Single source of truth for the four things that were inconsistently
 # re-implemented across create/resume/delete/monitor (REVIEW.md §4.1):
@@ -15,8 +15,8 @@
 # atomic_dump_yaml. Never `open(yaml_path, 'w')` anywhere else.
 
 SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-WORKSPACE_ROOT="$(cd "$SKILL_DIR/.." && pwd)"
+WORKSPACE_ROOT="$(cd "$SKILL_DIR/../.." && pwd)"
-AGENT_SESSIONS_YAML="${AGENT_SESSIONS_YAML:-$WORKSPACE_ROOT/.hermes/agent-sessions.yaml}"
+AGENT_SESSIONS_YAML="${AGENT_SESSIONS_YAML:-$WORKSPACE_ROOT/.mam/agent-sessions.yaml}"
 
 # Workspace-relative defaults with environment overrides (Phase Z)
 HOME_DIR="${HOME_DIR:-$WORKSPACE_ROOT}"
@@ -28,7 +28,7 @@ LOCAL_BIN="${LOCAL_BIN:-$HOME/.local/bin}"
 # ---------------------------------------------------------------------------
 # Paths to exclude when resolving the real tmux binary (shim/wrapper dirs).
 _TMUX_SHIM_DIR_PATTERN="${_TMUX_SHIM_DIR_PATTERN:-/multi-agent-tmux-shim/}"
-_TMUX_SKILLS_BIN_PATTERN="${_TMUX_SKILLS_BIN_PATTERN:-/skills/.bin}"
+_TMUX_SKILLS_BIN_PATTERN="${_TMUX_SKILLS_BIN_PATTERN:-/.agents/skills/.bin}"
 
 TMUX_SERVER_NAME="${TMUX_SERVER_NAME:-default}"
 
@@ -173,9 +173,16 @@ derive_session_name() {
   local workspace="$1" agent="$2"
   local abs parent work slug
   abs="$(cd "$workspace" 2>/dev/null && pwd)" || abs="$workspace"
-  parent="$(basename "$(dirname "$abs")")"
+  parent="$(basename "$(dirname "$abs")" 2>/dev/null || echo "")"
-  work="$(basename "$abs")"
+  work="$(basename "$abs" 2>/dev/null || echo "root")"
+  if [ -z "$parent" ] || [ "$parent" = "/" ] || [ "$parent" = "." ]; then
+    parent="workspace"
+  fi
+  if [ -z "$work" ] || [ "$work" = "/" ] || [ "$work" = "." ]; then
+    work="root"
+  fi
   slug="$(printf '%s-%s' "$parent" "$work" | tr '[:upper:]' '[:lower:]' | tr '_' '-')"
+  slug="$(printf '%s' "$slug" | tr -cd 'a-zA-Z0-9-')"
   printf '%s-creator-%s' "$slug" "$agent"
 }
 
@@ -189,13 +196,35 @@ derive_session_name() {
 # inside the script — never spliced into the source. Read-only by convention;
 # use atomic_dump_yaml when you need to write the YAML.
 # ---------------------------------------------------------------------------
+_validate_env_key() {
+  local key="$1"
+  if [[ ! "$key" =~ ^[a-zA-Z_][a-zA-Z0-9_]*$ ]]; then
+    echo "ERROR: Invalid environment variable name: $key" >&2
+    return 1
+  fi
+  case "$key" in
+    LD_PRELOAD|LD_LIBRARY_PATH|PYTHONPATH|PYTHONHOME|PYTHONINSPECT|PYTHONSTARTUP)
+      echo "ERROR: Blocked environment variable: $key" >&2
+      return 1
+      ;;
+  esac
+  return 0
+}
+
 env_python() {
   local yaml_path="$1"; shift
   local -a envs=("YAML_PATH=$yaml_path" "HOME_DIR=$HOME_DIR" "CLAUDE_PROJECT_DIR=$CLAUDE_PROJECT_DIR" "LOCAL_BIN=$LOCAL_BIN")
   while [ $# -gt 0 ]; do
     case "$1" in
-      *=*) envs+=("$1"); shift ;;
+      *=*)
-      *)   break ;;
+        local key="${1%%=*}"
+        _validate_env_key "$key" || return 1
+        envs+=("$1")
+        shift
+        ;;
+      *)
+        break
+        ;;
     esac
   done
   env "${envs[@]}" python3 - "$@"
@@ -233,8 +262,15 @@ atomic_dump_yaml() {
   local -a envs=("YAML_PATH=$yaml_path" "HOME_DIR=$HOME_DIR" "CLAUDE_PROJECT_DIR=$CLAUDE_PROJECT_DIR" "LOCAL_BIN=$LOCAL_BIN")
   while [ $# -gt 0 ]; do
     case "$1" in
-      *=*) envs+=("$1"); shift ;;
+      *=*)
-      *)   break ;;
+        local key="${1%%=*}"
+        _validate_env_key "$key" || return 1
+        envs+=("$1")
+        shift
+        ;;
+      *)
+        break
+        ;;
     esac
   done
   local mutation; mutation="$(cat)"
@@ -439,7 +475,7 @@ def db_exists(uuid):
 
 
 def hermes_exists(uuid):
-    hdb = f"{home}/.hermes/state.db"
+    hdb = f"{home}/.mam/state.db"
     if not os.path.exists(hdb):
         return False
     try:
@@ -529,7 +565,7 @@ elif agent == 'agy':
         if cand and db_exists(cand):
             emit(cand)
 elif agent == 'hermes':
-    hdb = f"{home}/.hermes/state.db"
+    hdb = f"{home}/.mam/state.db"
     if os.path.exists(hdb):
         cand = None
         try:
@@ -646,13 +682,13 @@ PYEOF
 }
 
 # ---------------------------------------------------------------------------
-# tmux-agent-orchestrate-delegate-job integration helpers
+# multi-agent-mux-delegate-job integration helpers
 #
 # All paths are resolved relative to lib.sh's own location (BASH_SOURCE), so the
 # skill tree is relocatable — no hardcoded absolute paths (review item 6).
 # ---------------------------------------------------------------------------
 
-# _delegate_py_bin — echo the virtualenv python (walk up from skills/), else python3.
+# _delegate_py_bin — echo the virtualenv python (walk up from .agents/skills/), else python3.
 _delegate_py_bin() {
   # Return cached result if available (shell variable, not exported — avoids cross-workspace pollution)
   if [ -n "${AGENT_PYTHON_BIN:-}" ] && [ -x "$AGENT_PYTHON_BIN" ]; then
@@ -671,26 +707,26 @@ _delegate_py_bin() {
   printf '%s\n' "$AGENT_PYTHON_BIN"
 }
 
-# _delegate_script <name> — echo the path to a tmux-agent-orchestrate-delegate-job script, resolved
+# _delegate_script <name> — echo the path to a multi-agent-mux-delegate-job script, resolved
-# relative to skills/ (lib.sh dir). Empty if not found.
+# relative to .agents/skills/ (lib.sh dir). Empty if not found.
 _delegate_script() {
   local name="$1" skill_dir cand
   skill_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-  cand="$skill_dir/tmux-agent-orchestrate-delegate-job/scripts/$name"
+  cand="$skill_dir/multi-agent-mux-delegate-job/scripts/$name"
   if [ -f "$cand" ]; then printf '%s\n' "$cand"; return 0; fi
   printf '%s\n' "$(find "$skill_dir" -name "$name" 2>/dev/null | head -n 1 || true)"
 }
 
 # delegate_submit_job <prompt> <agent> <agent_session>
 #
-# Register a job in the tmux-agent-orchestrate-delegate-job registry. Prints the new JID on stdout.
+# Register a job in the multi-agent-mux-delegate-job registry. Prints the new JID on stdout.
 delegate_submit_job() {
   local prompt="$1" agent="$2" session="$3"
   local py_bin registry_py
   py_bin="$(_delegate_py_bin)"
   registry_py="$(_delegate_script registry.py)"
   if [ -z "$registry_py" ] || [ ! -f "$registry_py" ]; then
-    echo "ERROR: tmux-agent-orchestrate-delegate-job registry.py not found under skills/" >&2
+    echo "ERROR: multi-agent-mux-delegate-job registry.py not found under .agents/skills/" >&2
     return 1
   fi
   "$py_bin" "$registry_py" register \
@@ -701,7 +737,7 @@ delegate_submit_job() {
 
 # delegate_publish_event <job_id> <event> [detail]
 #
-# Publish a lifecycle event to the tmux-agent-orchestrate-delegate-job registry. Consolidates the
+# Publish a lifecycle event to the multi-agent-mux-delegate-job registry. Consolidates the
 # inline .venv-walk + publish_event.py blocks that were duplicated across
 # create/delete/resume (review item 7). Non-fatal by contract: an empty job id,
 # a missing script, or a broker failure never aborts the caller.
@@ -723,16 +759,28 @@ delegate_publish_event() {
 start_watchdog() {
   local job_id="$1"
   local workdir="${2:-$PWD}"
-  local watchdog_script="$workdir/skills/tmux-agent-orchestrate-monitor/scripts/watchdog.sh"
+  local monitor_script="$workdir/.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh"
-  local log_file="$workdir/.hermes/jobs/${job_id}.watchdog.log"
+  local log_file="$workdir/.mam/multi-agent-mux-monitor.log"
   
-  if [ ! -x "$watchdog_script" ]; then
+  if [ ! -f "$monitor_script" ]; then
-    echo "ERROR: watchdog not found or not executable: $watchdog_script" >&2
+    echo "ERROR: monitor script not found: $monitor_script" >&2
     return 1
   fi
   
-  nohup "$watchdog_script" "$job_id" "$workdir" > "$log_file" 2>&1 &
+  # Check if reconcile.sh --subscribe is already running on this workspace
-  local pid=$!
+  local pid
+  pid=$(pgrep -f "bash $monitor_script --subscribe" || true)
+  
+  if [ -z "$pid" ]; then
+    # Start the wildcard monitor subscriber daemon with --idle-timeout 0 (never idle out)
+    # and ensure it runs with $workdir as cwd to anchor relative log paths.
+    local orig_pwd="$PWD"
+    cd "$workdir"
+    nohup bash "$monitor_script" --subscribe --idle-timeout 0 >> "$log_file" 2>&1 &
+    pid=$!
+    cd "$orig_pwd"
+  fi
+  
   echo "$pid"
 }
 

.agents/skills/multi-agent-mux-create/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: tmux-agent-orchestrate-create
+name: multi-agent-mux-create
-description: "Create a new agent session (claude, antigravity/agy) in a dedicated tmux session for context-preserving long-running work. Always creates a tmux session — never backgrounds with nohup/disown. Writes the new session to .hermes/agent-sessions.yaml. Use when you want to start a fresh agent (no prior UUID) for a new project workspace."
+description: "Create a new agent session (claude, antigravity/agy) in a dedicated tmux session for context-preserving long-running work. Always creates a tmux session — never backgrounds with nohup/disown. Writes the new session to .mam/agent-sessions.yaml. Use when you want to start a fresh agent (no prior UUID) for a new project workspace."
 version: 1.0.0
 author: godopu
 license: MIT
@@ -9,18 +9,18 @@ environments: [terminal, tmux]
 metadata:
   hermes:
     tags: [agent, tmux, claude, antigravity, agy, multi-agent, context, session]
-    related_skills: [tmux-agent-orchestrate-resume, tmux-agent-orchestrate-stop, tmux-agent-orchestrate-monitor, claude-code]
+    related_skills: [multi-agent-mux-resume, multi-agent-mux-stop, multi-agent-mux-monitor, claude-code]
     prereq_skills: [claude-code]
 ---
 
 # Multi-Agent Create — Start a Fresh Agent in a tmux Session
 
-> **Companion skills**: `tmux-agent-orchestrate-resume` (resume an existing UUID), `tmux-agent-orchestrate-stop` (terminate), `tmux-agent-orchestrate-monitor` (live status).
+> **Companion skills**: `multi-agent-mux-resume` (resume an existing UUID), `multi-agent-mux-stop` (terminate), `multi-agent-mux-monitor` (live status).
-> **Single source of truth**: `./.hermes/agent-sessions.yaml` (this skill writes to it; never read it ad-hoc — go through this skill).
+> **Single source of truth**: `./.mam/agent-sessions.yaml` (this skill writes to it; never read it ad-hoc — go through this skill).
 
 ## What this skill does
 
-Spawn a new agent (`claude` or `agy`/antigravity-cli) in a **dedicated tmux session** for context-preserving long-running work. The tmux session is the *container*; the agent's session ID is *data* inside the container. **This skill creates the container + starts the agent — but does not resume an old conversation** (use `tmux-agent-orchestrate-resume` for that).
+Spawn a new agent (`claude` or `agy`/antigravity-cli) in a **dedicated tmux session** for context-preserving long-running work. The tmux session is the *container*; the agent's session ID is *data* inside the container. **This skill creates the container + starts the agent — but does not resume an old conversation** (use `multi-agent-mux-resume` for that).
 
 For all agents: the tmux session name is produced by **`lib.sh::derive_session_name`** — the single source of truth shared by create/resume/stop/status/monitor (P0-A). The rule (verbatim from the function):
 
@@ -98,12 +98,12 @@ tmc ls  # Lists only your multi-agent sessions
 ```bash
 WORKSPACE=/path/to/project
 AGENT=claude  # or agy
-source skills/lib.sh
+source .agents/skills/lib.sh
 SESSION_NAME="$(derive_session_name "$WORKSPACE" "$AGENT")"
 
 # 1. If session already alive, fail fast
 tmux has-session -t "$SESSION_NAME" 2>/dev/null && {
-  echo "ERROR: tmux session '$SESSION_NAME' already exists. Use tmux-agent-orchestrate-resume to attach or tmux-agent-orchestrate-stop first."
+  echo "ERROR: tmux session '$SESSION_NAME' already exists. Use multi-agent-mux-resume to attach or multi-agent-mux-stop first."
   exit 1
 }
 
@@ -137,7 +137,7 @@ TMUX_EPOCH=$(tmux list-sessions -F '#{session_created}' -t "$SESSION_NAME" 2>/de
 
 ## Registering the session in agent-sessions.yaml
 
-After spawn, append a new `tmux_sessions[]` entry to `.hermes/agent-sessions.yaml`:
+After spawn, append a new `tmux_sessions[]` entry to `.mam/agent-sessions.yaml`:
 
 ```yaml
 - name: <SESSION_NAME>
@@ -172,7 +172,7 @@ After spawn, append a new `tmux_sessions[]` entry to `.hermes/agent-sessions.yam
 Use the `agent-sessions-yaml-edit` script in `scripts/` to safely append (preserves comments + format):
 
 ```bash
-bash skills/tmux-agent-orchestrate-create/scripts/create_session.sh \
+bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh \
   --workspace "$WORKSPACE" --agent "$AGENT" --session "$SESSION_NAME"
 ```
 
@@ -184,7 +184,7 @@ The script handles the YAML append, pane capture, and the `last_visible_status`
 - **Don't trust `--session-id <uuid>` flags blindly** — claude/agy may not accept a fixed session id on first spawn. The session id is *assigned* on first user message; you can read it back from `~/.claude/projects/.../session.jsonl` headers or `~/.gemini/.../cache/last_conversations.json` AFTER the first message.
 - **Wrapper script MUST NOT be created via `hermes profile alias`** — that command writes a `hermes -p <profile>` wrapper that destroys the tmux behavior. Create wrappers manually (see `lab-landing-page-creator-claude` template).
 - **Always use the workspace-relative path** in tmux `cwd` — relative paths break when tmux respawns in a different shell context.
-- **The first `claude` message generates the session id** — `tmux-agent-orchestrate-create` only sets up the *container*. If you need a known session id for later resume, send a placeholder message (e.g. "init") and read it back, then call `tmux-agent-orchestrate-resume` later.
+- **The first `claude` message generates the session id** — `multi-agent-mux-create` only sets up the *container*. If you need a known session id for later resume, send a placeholder message (e.g. "init") and read it back, then call `multi-agent-mux-resume` later.
 
 ## Verification
 
@@ -200,7 +200,7 @@ tmux list-panes -t "$SESSION_NAME" -F 'cmd=#{pane_current_command} cwd=#{pane_cu
 # 3. agent-sessions.yaml has the new entry
 python3 -c "
 import yaml
-d = yaml.safe_load(open('.hermes/agent-sessions.yaml'))
+d = yaml.safe_load(open('.mam/agent-sessions.yaml'))
 names = [s['name'] for s in d['tmux_sessions']]
 assert '$SESSION_NAME' in names, 'session not registered'
 print('OK:', names)
@@ -214,7 +214,7 @@ tmux capture-pane -t "$SESSION_NAME" -p -S -20
 
 ## When NOT to use this skill
 
-- **Resuming an old conversation** → `tmux-agent-orchestrate-resume`
+- **Resuming an old conversation** → `multi-agent-mux-resume`
-- **Killing an existing session** → `tmux-agent-orchestrate-stop`
+- **Killing an existing session** → `multi-agent-mux-stop`
 - **Just attaching to an existing session** → `tmux attach -t <name>` (no skill needed)
 - **One-shot print mode (claude -p "...")** → no tmux needed; use `claude-code` skill's print mode

.agents/skills/multi-agent-mux-create/scripts/create_session.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# create_session.sh — tmux-agent-orchestrate-create 의 부속 스크립트
+# create_session.sh — multi-agent-mux-create 의 부속 스크립트
 # Usage:
 #   bash create_session.sh --workspace <path> --agent <claude|agy> [--session <name>] [--wrapper]
 #
@@ -15,7 +15,7 @@
 #   0  = success
 #   1  = preflight failure
 #   2  = invalid args
-#   3  = tmux session already exists (use tmux-agent-orchestrate-resume or delete first)
+#   3  = tmux session already exists (use multi-agent-mux-resume or delete first)
 #   4  = agent-sessions.yaml append failure
 set -euo pipefail
 
@@ -32,7 +32,7 @@ Options:
   --wrapper           force use of ~/.local/bin/<session> wrapper even if not present
   --dry-run           print commands without executing
   --tmux-server NAME  specify isolated tmux server name
-  --submit-job PROMPT submit a job to tmux-agent-orchestrate-delegate-job registry with the given prompt
+  --submit-job PROMPT submit a job to multi-agent-mux-delegate-job registry with the given prompt
   -h, --help          this help
 EOF
 }
@@ -95,7 +95,7 @@ fi
 
 # 이미 살아있으면 실패
 if _tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
-  echo "ERROR: tmux session '$SESSION_NAME' already exists. Use tmux-agent-orchestrate-resume to attach, or tmux-agent-orchestrate-stop first." >&2
+  echo "ERROR: tmux session '$SESSION_NAME' already exists. Use multi-agent-mux-resume to attach, or multi-agent-mux-stop first." >&2
   exit 3
 fi
 
@@ -110,7 +110,7 @@ spawn() {
         nohup "$WRAPPER" >/dev/null 2>&1 &
         disown
       else
-        _tmux new-session -d -s "$SESSION_NAME" -x 140 -y 40 -c "$WORKSPACE" "claude"
+        _tmux new-session -d -s "$SESSION_NAME" -x 140 -y 40 -c "$WORKSPACE" "claude --dangerously-skip-permissions"
       fi
       ;;
     agy)
@@ -142,7 +142,7 @@ NOW_ISO=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
 
 # cmd_full 결정
 case "$AGENT" in
-  claude) CMD_FULL='claude' ;;
+  claude) CMD_FULL='claude --dangerously-skip-permissions' ;;
   agy)    CMD_FULL='agy --dangerously-skip-permissions' ;;
   hermes) CMD_FULL='hermes' ;;
 esac
@@ -158,7 +158,7 @@ case "$AGENT" in
     if [ -x "$WRAPPER" ]; then
       START_CMD="$WRAPPER   # ~/.local/bin 의 래퍼"
     else
-      START_CMD="$local_tmux new-session -d -s \"$SESSION_NAME\" -x 140 -y 40 -c \"$WORKSPACE\" \"claude\""
+      START_CMD="$local_tmux new-session -d -s \"$SESSION_NAME\" -x 140 -y 40 -c \"$WORKSPACE\" \"claude --dangerously-skip-permissions\""
     fi
     ;;
   agy|hermes)
@@ -279,7 +279,7 @@ echo "=== created ==="
 echo "tmux session: $SESSION_NAME (pane pid $PANE_PID, cmd $PANE_CMD, cwd $PANE_CWD)"
 if [ -n "$DELEGATE_JOB_ID" ]; then
   echo "delegate job: $DELEGATE_JOB_ID"
-  delegate_publish_event "$DELEGATE_JOB_ID" started "tmux-agent-orchestrate session created"
+  delegate_publish_event "$DELEGATE_JOB_ID" started "multi-agent-mux session created"
   WD_PID=$(start_watchdog "$DELEGATE_JOB_ID" "$WORKSPACE")
   echo "watchdog PID: $WD_PID"
 fi
@@ -290,5 +290,5 @@ if [ -n "${TMUX_SERVER_NAME:-}" ] && [ "$TMUX_SERVER_NAME" != "default" ]; then
 else
   echo "Attach:  tmux attach -t $SESSION_NAME"
 fi
-echo "Delete:  use tmux-agent-orchestrate-stop skill"
+echo "Delete:  use multi-agent-mux-stop skill"
-echo "Resume:  use tmux-agent-orchestrate-resume skill (after first message creates a session id)"
+echo "Resume:  use multi-agent-mux-resume skill (after first message creates a session id)"

.agents/skills/multi-agent-mux-delegate-job/README.md

@@ -0,0 +1,11 @@
+# multi-agent-mux-delegate-job 스킬
+
+작업(Job)을 자율 에이전트(claude-code/codex/opencode/human)에게 위임하고 MQTT
+이벤트 채널로 비동기 관찰하는 Hermes 스킬. **시작점은 [`SKILL.md`](./SKILL.md).**
+
+- 프로토콜/스키마: [`job-protocol.md`](./job-protocol.md)
+- 브로커 PoC→운영 전환: [`mqtt-broker-setup.md`](./mqtt-broker-setup.md)
+- 레지스트리 포맷/동시성: [`registry.md`](./registry.md)
+- 참조 구현: [`multi-agent-mux-delegate-job`](./multi-agent-mux-delegate-job) (bash wrapper), [`scripts/publish_event.py`](./scripts/publish_event.py), [`scripts/job_subscriber.py`](./scripts/job_subscriber.py), [`scripts/registry.py`](./scripts/registry.py), [`scripts/mqtt_common.py`](./scripts/mqtt_common.py)
+- 영구 감사 로그: `.mam/delegate_job_logs/<job_id>/` (`meta.json`·`events.ndjson`·`status.json`)
+  — `multi-agent-mux-delegate-job logs <id>` 또는 `multi-agent-mux-delegate-job logs --list`로 조회 (SKILL.md "Audit Logs" 참조)

.agents/skills/multi-agent-mux-delegate-job/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: tmux-agent-orchestrate-delegate-job
+name: multi-agent-mux-delegate-job
-description: "Delegate a unit of work to any autonomous agent (claude-code, codex, opencode, or a human) and observe it asynchronously over an MQTT event channel. Each job gets a unique id, a registry record (prompt, broker, status, timeouts), and a single per-job topic that carries started/permission_required/progress/completed/error events as schema-versioned JSON. The delegator starts a subscriber first, runs the agent, and treats a completed/error event or a timeout as the job's terminal state. Ships a working reference implementation (publish_event.py, job_subscriber.py, registry.py, mqtt_common.py, tmux-agent-orchestrate-delegate-job wrapper) plus a PoC-to-production path: validate on a public broker, then move to an authenticated TLS broker by changing config only — no code change. Use when you need fire-and-observe delegation, multi-job fan-out across tmux sessions, or a uniform completion-signal protocol shared by several agent types."
+description: "Delegate a unit of work to any autonomous agent (claude-code, codex, opencode, or a human) and observe it asynchronously over an MQTT event channel. Each job gets a unique id, a registry record (prompt, broker, status, timeouts), and a single per-job topic that carries started/permission_required/progress/completed/error events as schema-versioned JSON. The delegator starts a subscriber first, runs the agent, and treats a completed/error event or a timeout as the job's terminal state. Ships a working reference implementation (publish_event.py, job_subscriber.py, registry.py, mqtt_common.py, multi-agent-mux-delegate-job wrapper) plus a PoC-to-production path: validate on a public broker, then move to an authenticated TLS broker by changing config only — no code change. Use when you need fire-and-observe delegation, multi-job fan-out across tmux sessions, or a uniform completion-signal protocol shared by several agent types."
 version: 1.0.0
 author: Hermes Agent
 license: MIT
@@ -11,7 +11,7 @@ metadata:
     related_skills: [claude-code, codex, opencode, hermes-agent-skill-authoring]
 ---
 
-# tmux-agent-orchestrate-delegate-job — Async Job Delegation over MQTT
+# multi-agent-mux-delegate-job — Async Job Delegation over MQTT
 
 Delegate a unit of work to an autonomous agent, then **observe** it instead of
 blocking on it. Every job gets a unique id and a registry record; the agent
@@ -27,7 +27,7 @@ canonical concrete instance.
 
 The model is deliberately small. A **job** is one delegated task. An **agent**
 is a worker (a claude-code tmux session, a codex run, a human). The **registry**
-(`.hermes/jobs/<id>.json`) holds everything about a job so nothing important
+(`.mam/jobs/<id>.json`) holds everything about a job so nothing important
 lives in environment variables — which means one tmux session can process many
 jobs sequentially, and many sessions can fan out in parallel, with no env
 collisions. The **event channel** is one MQTT topic per job carrying JSON
@@ -73,7 +73,7 @@ you need finer control.
 ```bash
 # 1) one line: register → start subscriber → launch agent in tmux
 #    (uses public broker by default; last stdout line is the audit-log dir)
-tmux-agent-orchestrate-delegate-job submit \
+multi-agent-mux-delegate-job submit \
   --agent claude-code \
   --prompt "정렬 문제 10개를 만들어 sort_problems.md로 저장" \
   --workdir /path/to/project \
@@ -83,15 +83,15 @@ tmux-agent-orchestrate-delegate-job submit \
 #          subscriber pid: …
 #          agent launched in tmux session: demo
 #          subscriber output: <one line per event>
-#          /path/to/project/.hermes/delegate_job_logs/<JID>     ← audit log dir
+#          /path/to/project/.mam/delegate_job_logs/<JID>     ← audit log dir
 
 # 2) at any time, query the job or its audit log
-tmux-agent-orchestrate-delegate-job status --job <JID>
+multi-agent-mux-delegate-job status --job <JID>
-tmux-agent-orchestrate-delegate-job logs   <JID>            # pretty timeline
+multi-agent-mux-delegate-job logs   <JID>            # pretty timeline
-tmux-agent-orchestrate-delegate-job logs   --list           # every job, live status
+multi-agent-mux-delegate-job logs   --list           # every job, live status
 
 # 3) run a user-supplied validator against the job's artifacts
-tmux-agent-orchestrate-delegate-job verify --job <JID> --validate ./validate.sh
+multi-agent-mux-delegate-job verify --job <JID> --validate ./validate.sh
 ```
 
 The wrapper enforces the **subscribe-before-publish** ordering and **forwards
@@ -102,7 +102,7 @@ propagated to the agent"). When you need finer control, the manual flow is:
 ```bash
 # Manual 5-step (same outcome, more knobs)
 PY=.venv/bin/python
-SKILL=./skills/tmux-agent-orchestrate-delegate-job/scripts
+SKILL=./.agents/skills/multi-agent-mux-delegate-job/scripts
 
 # 1) register
 JID=$($PY "$SKILL/registry.py" register \
@@ -148,9 +148,9 @@ One topic per job: `python/mqtt/jobs/<job_id>/events`. Payload (JSON, UTF-8,
 ## Registry Format
 
 ```
-.hermes/jobs/<id>.json        # metadata record (single source of truth)
+.mam/jobs/<id>.json        # metadata record (single source of truth)
-.hermes/jobs/<id>.events.log  # append-only JSON-lines log (debug, optional)
+.mam/jobs/<id>.events.log  # append-only JSON-lines log (debug, optional)
-.hermes/jobs/.lock            # fcntl advisory lock for the registry
+.mam/jobs/.lock            # fcntl advisory lock for the registry
 ```
 
 The record holds `status`, `prompt`, `agent`, `agent_session`, a `broker` block,
@@ -163,13 +163,13 @@ the atomic rename trick, and multi-session job claiming are in
 ## Audit Logs
 
 Every job's lifecycle is mirrored to a **persistent, append-only audit log**
-under `.hermes/delegate_job_logs/` (override with `DELEGATE_JOB_LOGS_DIR`;
+under `.mam/delegate_job_logs/` (override with `DELEGATE_JOB_LOGS_DIR`;
-default `<cwd>/.hermes/delegate_job_logs`). Unlike the registry — live state
+default `<cwd>/.mam/delegate_job_logs`). Unlike the registry — live state
 mutated in place and liable to be cleaned up — the audit log is durable
 history you can replay after the fact. It is git-ignored.
 
 ```
-.hermes/delegate_job_logs/<job_id>/
+.mam/delegate_job_logs/<job_id>/
   meta.json      # registration snapshot: prompt, agent, broker, timeouts, …
   events.ndjson  # append-only, one JSON event per line, in time order
   status.json    # current status only (fast point-query)
@@ -194,8 +194,8 @@ never touched.
 **Reading them:**
 
 ```bash
-tmux-agent-orchestrate-delegate-job logs <job_id>     # pretty-print one job's timeline
+multi-agent-mux-delegate-job logs <job_id>     # pretty-print one job's timeline
-tmux-agent-orchestrate-delegate-job logs --list       # summarise every logged job (with live status)
+multi-agent-mux-delegate-job logs --list       # summarise every logged job (with live status)
 # or directly via the registry CLI:
 $PY scripts/registry.py logs <job_id> [--tail N] [--json]
 $PY scripts/registry.py logs --list [--json]
@@ -239,7 +239,7 @@ agent").
   Your job_id is "$JOB_ID" (read it from the registry record for this delegation —
   do not reuse any job_id you saw before).
 
-  On start:        $PY tmux-agent-orchestrate-delegate-job/scripts/publish_event.py --job "$JOB_ID" --event started
+  On start:        $PY multi-agent-mux-delegate-job/scripts/publish_event.py --job "$JOB_ID" --event started
   On permission:   $PY … --job "$JOB_ID" --event permission_required --detail "<tool>:<what>"
   On progress:     $PY … --job "$JOB_ID" --event progress --detail "<short status>"
   On success:      $PY … --job "$JOB_ID" --event completed --detail "<one-line summary>"
@@ -261,17 +261,17 @@ agent").
 
 ## User Interface
 
-The [`tmux-agent-orchestrate-delegate-job`](./tmux-agent-orchestrate-delegate-job) bash wrapper bundles register +
+The [`multi-agent-mux-delegate-job`](./multi-agent-mux-delegate-job) bash wrapper bundles register +
 subscribe-first + run-agent + validate:
 
 ```bash
-tmux-agent-orchestrate-delegate-job submit  --agent claude-code \
+multi-agent-mux-delegate-job submit  --agent claude-code \
    --prompt "정렬 문제 10개를 만들어 sort_problems.md로 저장" \
     --workdir /path/to/project --timeout 3600 [--validate ./validate.sh]
-tmux-agent-orchestrate-delegate-job status  --job <id>          # one record, pretty-printed
+multi-agent-mux-delegate-job status  --job <id>          # one record, pretty-printed
-tmux-agent-orchestrate-delegate-job list                        # all jobs, one line each
+multi-agent-mux-delegate-job list                        # all jobs, one line each
-tmux-agent-orchestrate-delegate-job verify  --job <id> --validate ./validate.sh   # runs it, reports exit code
+multi-agent-mux-delegate-job verify  --job <id> --validate ./validate.sh   # runs it, reports exit code
-tmux-agent-orchestrate-delegate-job wait    [--job <id>]        # block until terminal (else --wait-any)
+multi-agent-mux-delegate-job wait    [--job <id>]        # block until terminal (else --wait-any)
 ```
 
 `submit` **always starts the subscriber before the agent** (the ordering
@@ -371,13 +371,13 @@ has been verified (2026-06-21, 6-batch refactoring sprint):
 - [ ] `publisher.py`/`subscriber.py`/`README.md` demo on `python/mqtt/sample`
       still works unchanged (regression).
 - [ ] **audit log integrity** — for a completed job,
-      `.hermes/delegate_job_logs/<JID>/events.ndjson` contains `registered` →
+      `.mam/delegate_job_logs/<JID>/events.ndjson` contains `registered` →
       `received started` → `published completed` (in that order), and
       `status.json.status == "completed"` matches the registry record. A
       logging failure (e.g. read-only log dir) does not break the publish or
       subscribe path — only a `logger.warning` is emitted.
 - [ ] **end-to-end demo smoke** — run
-      `tmux-agent-orchestrate-delegate-job submit --agent claude-code --agent-session tmux:demo-smoke
+      `multi-agent-mux-delegate-job submit --agent claude-code --agent-session tmux:demo-smoke
        --prompt "echo hello and call publish_event.py --job <JID>
        --event completed" --timeout 120` and confirm
       (a) registered job id echoed, (b) subscriber pid echoed, (c) tmux session

.agents/skills/multi-agent-mux-delegate-job/job-protocol.md

@@ -1,6 +1,6 @@
 # Job Event Protocol
 
-The wire contract every tmux-agent-orchestrate-delegate-job agent (claude-code, codex, opencode,
+The wire contract every multi-agent-mux-delegate-job agent (claude-code, codex, opencode,
 human, …) speaks. One job → one MQTT topic → JSON event payloads. Stable across
 the PoC (public broker) and production (own broker) stages; only transport
 hardening changes, never the payload shape.

.agents/skills/multi-agent-mux-delegate-job/mqtt-broker-setup.md

@@ -1,6 +1,6 @@
 # MQTT Broker Setup — PoC → Production
 
-The tmux-agent-orchestrate-delegate-job scripts read **all** broker settings from environment
+The multi-agent-mux-delegate-job scripts read **all** broker settings from environment
 variables (or a job record's `broker.*` block) through a single helper,
 `broker_config_from_env()` in
 [`./scripts/mqtt_common.py`](./scripts/mqtt_common.py). The design goal:
@@ -152,7 +152,7 @@ export MQTT_PASSWORD=…            # subscriber side
 mosquitto_sub -h "$MQTT_BROKER" -p 8883 --cafile "$MQTT_CA_CERTS" \
   -u hermes -P "$MQTT_PASSWORD" -t 'python/mqtt/jobs/+/events' -v &
 
-# 3) run the unchanged tmux-agent-orchestrate-delegate-job loop
+# 3) run the unchanged multi-agent-mux-delegate-job loop
 PY=.venv/bin/python
 JID=$($PY scripts/registry.py register --prompt "broker cutover smoke")
 $PY scripts/job_subscriber.py --job "$JID" --timeout 30 &

.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# tmux-agent-orchestrate-delegate-job — user-facing orchestrator for the tmux-agent-orchestrate-delegate-job skill.
+# multi-agent-mux-delegate-job — user-facing orchestrator for the multi-agent-mux-delegate-job skill.
 #
 # Subcommands:
 #   submit   register a job, start the subscriber FIRST, then run the agent,
@@ -37,11 +37,11 @@ pick_python() {
   echo "$py_bin"
 }
 
-REGISTRY_DIR_DEFAULT=".hermes/jobs"
+REGISTRY_DIR_DEFAULT=".mam/jobs"
 
 usage() {
   cat <<'EOF'
-tmux-agent-orchestrate-delegate-job <command> [options]
+multi-agent-mux-delegate-job <command> [options]
 
   submit  --agent <name> --prompt <text> [--workdir <dir>] [--agent-session <label>]
           [--timeout <sec>] [--idle-timeout <sec>] [--validate <script>]
@@ -164,15 +164,14 @@ run_agent() {
   # The user attaches with `tmux attach -t <session>` and types follow-up
   # prompts themselves. We pre-load the first prompt via stdin and `read`
   # keeps the pane open after the agent exits so the user can review.
-  case "$AGENT" in
+  if [ "$AGENT" = "human" ]; then
-    claude-code) bin="claude";;
+    echo "[human agent] complete the task, then run publish_event.py --event completed"
-    codex)       bin="codex";;
+    return
-    human)       echo "[human agent] complete the task, then run publish_event.py --event completed"; return;;
+  fi
-    *)           bin="$AGENT";;
+  local sess="${AGENT_SESSION#tmux:}"
-  esac
 
   if [[ "$DRY_RUN" == "1" ]]; then
-    echo "[dry-run] would launch agent '$AGENT' in a fresh tmux session with instructions:"
+    echo "[dry-run] would delegate task to running agent '$AGENT' in tmux session '$sess' with instructions:"
     echo "----"; echo "$instructions"; echo "----"
     return
   fi
@@ -182,21 +181,15 @@ run_agent() {
     echo "       Install with: brew install tmux   (or your package manager)" >&2
     return 1
   fi
-  if ! command -v "$bin" >/dev/null 2>&1; then
+
-    echo "ERROR: agent binary '$bin' not found in PATH." >&2
+  local _tmux="tmux"
-    return 1
+  if [ -n "${TMUX_SERVER_NAME:-}" ]; then
+    _tmux="tmux -L $TMUX_SERVER_NAME"
   fi
 
-  local sess="${AGENT_SESSION#tmux:}"
+  if ! $_tmux has-session -t "$sess" 2>/dev/null; then
-  # Detect a stale session with the same name (e.g. the user is still attached
+    echo "ERROR: 에이전트 세션 '$sess'이 존재하지 않습니다. 작업을 위임하기 전에 먼저 에이전트 세션을 기동해 주세요." >&2
-  # from an earlier run, or a previous wrapper died without cleanup). tmux
+    echo "       팁: 'multi-agent-mux-resume' 또는 'multi-agent-mux-create'를 통해 에이전트를 먼저 생성할 수 있습니다." >&2
-  # new-session on an existing name fails silently; check first and fail loud.
-  if tmux has-session -t "$sess" 2>/dev/null; then
-    local attached
-    attached=$(tmux list-clients -t "$sess" 2>/dev/null | wc -l | tr -d ' ')
-    echo "ERROR: tmux session '$sess' already exists (clients attached: $attached)." >&2
-    echo "       Pick a unique --agent-session (e.g. tmux:demo, tmux:claude-a) or" >&2
-    echo "       kill the stale one first:  tmux kill-session -t $sess" >&2
     return 1
   fi
 
@@ -206,9 +199,13 @@ run_agent() {
     trap 'rc=$?; if [ $rc -ne 0 ]; then "$PY" "$pub_script" --job "$job_id" --event error --detail "agent bootstrap failed (exit $rc)"; fi' EXIT
   fi
 
-  tmux new-session -d -s "$sess" -c "$WORKDIR" \
+  echo "살아있는 에이전트 세션 '$sess'에 작업을 위임합니다..."
-    "printf '%s' \"$instructions\" | $bin --dangerously-skip-permissions; echo; echo '--- agent exited (job $job_id); press enter to close ---'; read"
+  $_tmux set-buffer -b "job_buf_$job_id" "$instructions"
-  echo "agent launched in tmux session: $sess (attach with: tmux attach -t $sess)"
+  $_tmux paste-buffer -b "job_buf_$job_id" -t "$sess"
+  $_tmux send-keys -t "$sess" C-m
+  $_tmux delete-buffer -b "job_buf_$job_id"
+  
+  echo "작업이 세션 '$sess'에 전송되었습니다. (연결하려면: $_tmux attach -t $sess)"
   trap - EXIT
 }
 

.agents/skills/multi-agent-mux-delegate-job/registry.md

@@ -15,13 +15,13 @@ Reference implementation: [`./scripts/registry.py`](./scripts/registry.py)
 ## 1. Directory layout
 
 ```
-.hermes/jobs/
+.mam/jobs/
   <job_id>.json          # job metadata record (schema below)
   <job_id>.events.log    # append-only JSON-lines event log (debug, optional)
   .lock                  # shared advisory lock (fcntl) for the whole registry
 ```
 
-`registry_dir` defaults to `.hermes/jobs` and is overridable everywhere via
+`registry_dir` defaults to `.mam/jobs` and is overridable everywhere via
 `--registry-dir`.
 
 ---
@@ -143,13 +143,13 @@ that session.
 ## 7. Persistent audit log
 
 Separate from the registry, every job is also mirrored to a durable append-only
-audit log at `.hermes/delegate_job_logs/<job_id>/` (override with
+audit log at `.mam/delegate_job_logs/<job_id>/` (override with
-`DELEGATE_JOB_LOGS_DIR`, default `<cwd>/.hermes/delegate_job_logs`). The registry
+`DELEGATE_JOB_LOGS_DIR`, default `<cwd>/.mam/delegate_job_logs`). The registry
 is **live state** mutated in place; the audit log is **history** that survives
 even after the registry dir is cleaned up. It is git-ignored.
 
 ```
-.hermes/delegate_job_logs/<job_id>/
+.mam/delegate_job_logs/<job_id>/
   meta.json      # registration snapshot (the full job record at register time)
   events.ndjson  # append-only, one JSON event per line, time-ordered
   status.json    # current status only (fast point-query)

.agents/skills/multi-agent-mux-delegate-job/scripts/mqtt_common.py

@@ -1,4 +1,4 @@
-"""Shared MQTT + registry helpers for the tmux-agent-orchestrate-delegate-job skill.
+"""Shared MQTT + registry helpers for the multi-agent-mux-delegate-job skill.
 
 Single entry point for:
   - broker configuration (env -> dataclass),
@@ -71,11 +71,11 @@ _load_dotenv()
 # Constants
 # --------------------------------------------------------------------------
 SCHEMA_VERSION = 1
-DEFAULT_REGISTRY_DIR = ".hermes/jobs"
+DEFAULT_REGISTRY_DIR = ".mam/jobs"
 DEFAULT_TOPIC_ROOT = "python/mqtt/jobs"
 LOCK_FILENAME = ".lock"
 
-# Persistent audit-log layout: .hermes/delegate_job_logs/<job_id>/{meta,events,status}.
+# Persistent audit-log layout: .mam/delegate_job_logs/<job_id>/{meta,events,status}.
 # This is a *separate* artifact from the registry: the registry is the live job
 # record (mutated in place), the audit log is an append-only history that
 # survives even if the registry dir is cleaned up.
@@ -86,15 +86,15 @@ STATUS_FILENAME = "status.json"
 
 def _default_logs_dir() -> str:
     """Audit-log root. Overridable with ``DELEGATE_JOB_LOGS_DIR``; otherwise
-    ``<cwd>/.hermes/delegate_job_logs`` — we keep audit logs next to the
+    ``<cwd>/.mam/delegate_job_logs`` — we keep audit logs next to the
-    live registry (``.hermes/jobs/``) so the two runtime artifacts sit
+    live registry (``.mam/jobs/``) so the two runtime artifacts sit
     under the same parent dir and follow the same ``.gitignore`` rule.
     The cwd of whichever process emits events (the bash wrapper and
     scripts) is used as the anchor."""
     env = os.environ.get("DELEGATE_JOB_LOGS_DIR")
     if env and env.strip():
         return env
-    return os.path.join(os.getcwd(), ".hermes", "delegate_job_logs")
+    return os.path.join(os.getcwd(), ".mam", "delegate_job_logs")
 
 
 LOGS_DIR = _default_logs_dir()
@@ -328,8 +328,8 @@ def update_job_status(job_id: str, registry_dir: str = DEFAULT_REGISTRY_DIR, **f
 
     This is the single chokepoint for status writes (both ``registry.update_status``
     and ``publish_event.py``'s status sync route through here), so it also mirrors
-    any ``status`` change into the persistent audit log — best-effort, after the
+    any ``status`` change into the persistent audit log. We perform the log mirror
-    registry lock is released so a slow/failed log write never blocks the record."""
+    under the lock to guarantee sequential consistency in audit history."""
     with registry_lock(registry_dir):
         record = load_job(job_id, registry_dir)
         old_status = record.get("status")
@@ -376,7 +376,7 @@ def _utcnow_precise() -> str:
 
 
 # --------------------------------------------------------------------------
-# Persistent audit log (.hermes/delegate_job_logs/<job_id>/...)
+# Persistent audit log (.mam/delegate_job_logs/<job_id>/...)
 #
 # Every function here is idempotent, concurrency-safe, and *best-effort*: a
 # logging failure is swallowed with a logger.warning and never propagated, so it
@@ -410,6 +410,21 @@ def _file_lock(fh):
         fcntl.flock(fh.fileno(), fcntl.LOCK_UN)
 
 
+def _redact_dict(d: Any) -> Any:
+    """Recursively mask sensitive values (passwords, secrets, tokens) inside logs."""
+    if isinstance(d, dict):
+        redacted = {}
+        for k, v in d.items():
+            if any(s in k.lower() for s in ("password", "token", "secret", "auth_token", "key")):
+                redacted[k] = "[REDACTED]"
+            else:
+                redacted[k] = _redact_dict(v)
+        return redacted
+    elif isinstance(d, list):
+        return [_redact_dict(item) for item in d]
+    return d
+
+
 def append_event(job_id: str, event_dict: Dict[str, Any], logs_dir: Optional[str] = None) -> None:
     """Append one event as a JSON line to ``<logs>/<job_id>/events.ndjson``.
 
@@ -418,7 +433,7 @@ def append_event(job_id: str, event_dict: Dict[str, Any], logs_dir: Optional[str
     try:
         path = job_log_path(job_id, EVENTS_FILENAME, logs_dir)
         path.parent.mkdir(parents=True, exist_ok=True)
-        record = dict(event_dict)
+        record = _redact_dict(dict(event_dict))
         record.setdefault("logged_at", _utcnow_precise())
         line = json.dumps(record, ensure_ascii=False) + "\n"
         with open(path, "a", encoding="utf-8") as fh:
@@ -453,8 +468,9 @@ def init_job_log(job_id: str, meta: Dict[str, Any], logs_dir: Optional[str] = No
     try:
         d = job_log_dir(job_id, logs_dir)
         d.mkdir(parents=True, exist_ok=True)
+        meta_redacted = _redact_dict(meta)
         with open(d / META_FILENAME, "w", encoding="utf-8") as fh:
-            json.dump(meta, fh, ensure_ascii=False, indent=2)
+            json.dump(meta_redacted, fh, ensure_ascii=False, indent=2)
             fh.write("\n")
         status = meta.get("status", "pending")
         update_logged_status(

.agents/skills/multi-agent-mux-delegate-job/scripts/registry.py

@@ -1,4 +1,4 @@
-"""Job registry for the tmux-agent-orchestrate-delegate-job skill.
+"""Job registry for the multi-agent-mux-delegate-job skill.
 
 A job record is the single source of truth for one delegated unit of work:
 its id, prompt, owning agent session, broker connection, timeouts, and status.
@@ -9,7 +9,7 @@ Concurrency is handled via the fcntl lock in :mod:`mqtt_common` (PoC). For
 multi-host delegation, migrate to SQLite WAL — see references/registry.md.
 
 Importable as a library and runnable as a CLI (``register``/``list``/``get``/
-``status``/``pick``) so the ``tmux-agent-orchestrate-delegate-job`` bash wrapper can shell out.
+``status``/``pick``) so the ``multi-agent-mux-delegate-job`` bash wrapper can shell out.
 """
 from __future__ import annotations
 
@@ -184,7 +184,7 @@ def _iter_records(registry_dir: str):
 # CLI (so the bash wrapper can shell out without inline python)
 # --------------------------------------------------------------------------
 def _build_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(description="tmux-agent-orchestrate-delegate-job registry CLI")
+    parser = argparse.ArgumentParser(description="multi-agent-mux-delegate-job registry CLI")
     parser.add_argument("--registry-dir", default=DEFAULT_REGISTRY_DIR)
     sub = parser.add_subparsers(dest="command", required=True)
 
@@ -222,7 +222,7 @@ def _build_parser() -> argparse.ArgumentParser:
                         help="summarise every job under the logs dir instead")
     p_logs.add_argument("--logs-dir", default=None,
                         help="override the audit-log root (default: $DELEGATE_JOB_LOGS_DIR "
-                             "or <cwd>/.hermes/delegate_job_logs)")
+                             "or <cwd>/.mam/delegate_job_logs)")
     p_logs.add_argument("--tail", type=int, default=0,
                         help="show only the last N events (0 = all)")
     p_logs.add_argument("--json", action="store_true",

.agents/skills/multi-agent-mux-monitor/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: tmux-agent-orchestrate-monitor
+name: multi-agent-mux-monitor
-description: "Run a long-lived Kanban worker that polls .hermes/agent-sessions.yaml against the actual tmux/agent runtime state and reconciles them. Use when you want live visibility into which agent sessions are running, which are dead, which have stale YAML entries, and which have new session ids that haven't been recorded yet. Designed to be dispatched as a Kanban goal_mode task (--goal) so it keeps running until the user stops it."
+description: "Run a long-lived Kanban worker that polls .mam/agent-sessions.yaml against the actual tmux/agent runtime state and reconciles them. Use when you want live visibility into which agent sessions are running, which are dead, which have stale YAML entries, and which have new session ids that haven't been recorded yet. Designed to be dispatched as a Kanban goal_mode task (--goal) so it keeps running until the user stops it."
 version: 1.0.0
 author: godopu
 license: MIT
@@ -9,14 +9,14 @@ environments: [kanban, terminal, tmux]
 metadata:
   hermes:
     tags: [agent, tmux, claude, antigravity, agy, monitor, kanban, observation, reconciliation]
-    related_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-resume, tmux-agent-orchestrate-stop, kanban-orchestrator]
+    related_skills: [multi-agent-mux-create, multi-agent-mux-resume, multi-agent-mux-stop, kanban-orchestrator]
-    prereq_skills: [kanban-worker, tmux-agent-orchestrate-create]
+    prereq_skills: [kanban-worker, multi-agent-mux-create]
 ---
 
 # Agent Sessions Monitor — Live Reconciliation via Kanban Worker
 
-> **Companion skills**: `tmux-agent-orchestrate-create` / `tmux-agent-orchestrate-resume` / `tmux-agent-orchestrate-stop` (mutators); this skill is the **observer**.
+> **Companion skills**: `multi-agent-mux-create` / `multi-agent-mux-resume` / `multi-agent-mux-stop` (mutators); this skill is the **observer**.
-> **Single source of truth**: `./.hermes/agent-sessions.yaml`.
+> **Single source of truth**: `./.mam/agent-sessions.yaml`.
 
 ## What this skill does
 
@@ -59,16 +59,16 @@ hermes kanban create \
   --title "agent-sessions monitor (live reconcile)" \
   --assignee default \
   --workspace worktree \
-  --branch wt/tmux-agent-orchestrate-monitor \
+  --branch wt/multi-agent-mux-monitor \
   --goal \
   --goal-max-turns 100 \
   --max-runtime 8h \
   --max-retries 1 \
-  --skill tmux-agent-orchestrate-monitor \
+  --skill multi-agent-mux-monitor \
   --body "$(cat <<'EOF'
 You are the agent-sessions monitor. Every 30 seconds, do:
 
-1. Read .hermes/agent-sessions.yaml
+1. Read .mam/agent-sessions.yaml
 2. Run `tmux ls` and `tmux list-panes -F 'session=#{session_name} pid=#{pane_pid} cmd=#{pane_current_command} cwd=#{pane_current_path}'`
 3. For each session in the YAML, check the corresponding tmux state
 4. For each tmux session matching `*-creator-claude` or `*-creator-agy` that's not in the YAML, register it
@@ -79,7 +79,7 @@ If the user comments `stop` or `stop monitoring` on this card, call `kanban_bloc
 
 If you find that a Claude session's `claude_session_id_own` is null but there's a new *.jsonl in the project dir, read the sessionId from the first line and update the YAML.
 
-Use the helper script at skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh for the YAML updates — it handles all the merge logic and writes a structured comment to this card.
+Use the helper script at .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh for the YAML updates — it handles all the merge logic and writes a structured comment to this card.
 EOF
 )"
 ```
@@ -94,17 +94,17 @@ The worker calls this script every 30s. It:
 
 ```bash
 # Reconcile + auto-update YAML (atomic, flock-guarded). Emits JSON drift to stdout.
-bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --once --emit-diff
+bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --once --emit-diff
 
 # Read-only: compute drift WITHOUT writing the YAML (use for "what's running?" checks).
-bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --once --emit-diff --dry-run
+bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --once --emit-diff --dry-run
 
 # Push-based MQTT Monitor: listen to delegated job events on the broker and update the YAML instantly.
 # Bounded run that exits after 5 min idle, or 1 h wall-clock; falls back to polling if the broker is down.
-bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --subscribe --idle-timeout 300 --timeout 3600
+bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --subscribe --idle-timeout 300 --timeout 3600
 
 # Persistent monitor (no timeouts): runs until interrupted; still polls if the broker is unreachable.
-bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --subscribe --idle-timeout 0
+bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --subscribe --idle-timeout 0
 ```
 
 Flags: `--once` (single pass), `--emit-diff` (print JSON), `--dry-run` (P1-E — no mutation), `--subscribe` (push-based MQTT subscription monitoring). `--subscribe` sub-flags: `--timeout N` (exit after N seconds of wall-clock; `0` = no limit, default), `--idle-timeout N` (exit after N seconds with no message; default `3600`, `0` = never idle-out). On a broker connection failure (connect error **or** non-zero CONNACK), `--subscribe` falls back to a polling loop that re-runs `--once --emit-diff` every `RECONCILE_POLL_INTERVAL` (default 15) seconds until `--timeout`. Terminal-event YAML updates are written through `lib.sh::atomic_dump_yaml` (flock + schema-validate + `.bak`). There are **no** `--workspace` / `--agent` / `--comment-card` flags; the worker turns the emitted JSON `drifts[]` into `kanban_comment` calls itself.
@@ -126,7 +126,7 @@ tmux:  no session
 
 **Skip-set**: the auto-terminate only fires for sessions whose status is `running`.
 Rows already in a deliberate end state — `terminated`, `archived`, or **`stopped`**
-(set by `tmux-agent-orchestrate-stop`) — are
+(set by `multi-agent-mux-stop`) — are
 left untouched. This is critical: a `stopped` row keeps its `resumable: true` and
 captured `*_session_id_own`, so the monitor must **not** overwrite it with
 `terminated ("auto-detected")` when its tmux is (expectedly) gone.
@@ -165,8 +165,8 @@ disk:  ~/.claude/projects/.../87dc548e-...jsonl: missing
 
 - **Don't run the monitor without `--goal`** — without goal mode, a single turn will spawn, do one reconcile, and complete. Goal mode keeps the worker alive across many turns.
 - **The 30s poll is a default** — workers may override if they detect heavy churn. A workspace with 5+ agent sessions should bump to 60s to avoid noise.
-- **`kanban_comment` rate limits** — Kanban may throttle if you comment too fast. Coalesce: only comment when the diff is *new* (not the same drift on every poll). The script tracks a state file at `.cache/tmux-agent-orchestrate-monitor/<workspace>.state` in the workspace root for this (overridable via `AGENT_SESSIONS_STATE_DIR`).
+- **`kanban_comment` rate limits** — Kanban may throttle if you comment too fast. Coalesce: only comment when the diff is *new* (not the same drift on every poll). The script tracks a state file at `.cache/multi-agent-mux-monitor/<workspace>.state` in the workspace root for this (overridable via `AGENT_SESSIONS_STATE_DIR`).
-- **Don't fight the user's explicit action** — if `tmux-agent-orchestrate-stop` is mid-flight and the monitor sees the same session in two states within 5s, prefer the user's most recent action. The monitor should not auto-revert a fresh `terminated` to `running` because of a stale `tmux has-session` check.
+- **Don't fight the user's explicit action** — if `multi-agent-mux-stop` is mid-flight and the monitor sees the same session in two states within 5s, prefer the user's most recent action. The monitor should not auto-revert a fresh `terminated` to `running` because of a stale `tmux has-session` check.
 - **The monitor should never modify the conversation artifacts** (jsonl, db) — only the YAML. If you see a stale UUID, comment about it but don't delete the file.
 - **TUI capture-pane is expensive** — only capture when you need to update `last_visible_status`, not every poll.
 
@@ -180,7 +180,7 @@ The `--body` of the dispatched task IS the worker's behavior spec. Here's a test
 ## Loop (every 30s)
 
 1. Read agent-sessions.yaml
-2. Bash: `bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --emit-diff`
+2. Bash: `bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --emit-diff`
 3. Parse the JSON diff from stdout
 4. If `drifts` is non-empty:
    - For each drift, call `kanban_comment` with the diff message
@@ -203,7 +203,7 @@ If `$HERMES_KANBAN_TASK` card has any comment containing "stop" or "stop monitor
 
 - Do NOT modify conversation artifacts (jsonl, db, brain/)
 - Do NOT spawn/delete tmux sessions — that's the create/delete skills' job
-- Do NOT call tmux-agent-orchestrate-create or tmux-agent-orchestrate-stop — only the user initiates those
+- Do NOT call multi-agent-mux-create or multi-agent-mux-stop — only the user initiates those
 - Do NOT call `git commit` / `git push`
 ```
 
@@ -226,7 +226,7 @@ When using `--subscribe` with the default PoC public broker
 
 ```bash
 # Run reconcile once and inspect output
-bash skills/tmux-agent-orchestrate-monitor/scripts/reconcile.sh --emit-diff --once \
+bash .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --emit-diff --once \
   | python3 -m json.tool
 ```
 

.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# reconcile.sh — tmux-agent-orchestrate-monitor 의 부속 스크립트
+# reconcile.sh — multi-agent-mux-monitor 의 부속 스크립트
 # YAML ↔ tmux ↔ 디스크 artifact 간 drift 감지 (+ YAML 자동 갱신).
 #
 # Usage:
@@ -7,7 +7,7 @@
 #   bash reconcile.sh --once --emit-diff --dry-run  # drift 만 계산, 쓰기 안 함 (P1-E)
 #
 # --dry-run: 부수효과 없는 read-only. "지금 뭐 돌고 있지?" 질문에 안전.
-#            tmux-agent-orchestrate-status 스킬이 이걸 재사용.
+#            multi-agent-mux-status 스킬이 이걸 재사용.
 #
 # 출력 (JSON): {timestamp, yaml_path, tmux_sessions_alive, tmux_confirmed, drifts, actions}
 #
@@ -16,7 +16,7 @@ set -euo pipefail
 
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"
 
-STATE_DIR="${AGENT_SESSIONS_STATE_DIR:-$WORKSPACE_ROOT/.cache/tmux-agent-orchestrate-monitor}"
+STATE_DIR="${AGENT_SESSIONS_STATE_DIR:-$WORKSPACE_ROOT/.cache/multi-agent-mux-monitor}"
 
 ONCE=0
 EMIT_DIFF=0
@@ -55,26 +55,42 @@ if [ "$SUBSCRIBE" = "1" ]; then
   # The MQTT subscribe loop exits 3 to signal "broker unavailable → poll instead".
   set +e
   YAML_PATH="$AGENT_SESSIONS_YAML" HOME_DIR="$HOME_DIR" CLAUDE_PROJECT_DIR="$CLAUDE_PROJECT_DIR" LOCAL_BIN="$LOCAL_BIN" \
-    SUB_TIMEOUT="$SUB_TIMEOUT" SUB_IDLE_TIMEOUT="$SUB_IDLE_TIMEOUT" \
+    WORKSPACE_ROOT="$WORKSPACE_ROOT" SUB_TIMEOUT="$SUB_TIMEOUT" SUB_IDLE_TIMEOUT="$SUB_IDLE_TIMEOUT" \
     SKILLS_DIR="$SKILLS_DIR" LIB_SH="$LIB_SH" \
     "$PYBIN" - <<'PYEOF'
 import os, sys, json, time, subprocess
 
 lib_sh = os.environ.get('LIB_SH', '')
 skills_dir = os.environ.get('SKILLS_DIR', '')
+yaml_path = os.environ.get('YAML_PATH', '')
+workspace_root = os.environ.get('WORKSPACE_ROOT', '')
 timeout = int(os.environ.get('SUB_TIMEOUT', '0') or '0')          # 0 = no overall timeout
 idle_timeout = int(os.environ.get('SUB_IDLE_TIMEOUT', '3600') or '0')  # 0 = no idle timeout
 
-# Locate skills/tmux-agent-orchestrate-delegate-job/scripts to import mqtt_common — relative first, then
+# Prevent duplicate wildcard subscribers for this workspace (concurrency race)
+import fcntl
+lock_file_path = os.path.join(workspace_root or '.', '.mam', 'monitor.lock')
+try:
+    os.makedirs(os.path.dirname(lock_file_path), exist_ok=True)
+    lock_file = open(lock_file_path, 'w')
+    fcntl.flock(lock_file, fcntl.LOCK_EX | fcntl.LOCK_NB)
+except BlockingIOError:
+    print("MQTT Monitor: another subscriber is already running for this workspace. Exiting.", flush=True)
+    sys.exit(0)
+except Exception as e:
+    print(f"MQTT Monitor: failed to acquire monitor lock ({e}). Exiting.", flush=True)
+    sys.exit(1)
+
+# Locate skills/multi-agent-mux-delegate-job/scripts to import mqtt_common — relative first, then
 # an upward walk from cwd. No hardcoded absolute path (review item 6).
-cand = os.path.join(skills_dir, 'tmux-agent-orchestrate-delegate-job', 'scripts') if skills_dir else ''
+cand = os.path.join(skills_dir, 'multi-agent-mux-delegate-job', 'scripts') if skills_dir else ''
 if cand and os.path.isdir(cand):
     sys.path.append(cand)
 else:
     d = os.getcwd()
     while d and d != '/':
         hit = None
-        for sub in (('skills', 'tmux-agent-orchestrate-delegate-job', 'scripts'), ('tmux-agent-orchestrate-delegate-job', 'scripts')):
+        for sub in (('.agents', 'skills', 'multi-agent-mux-delegate-job', 'scripts'), ('skills', 'multi-agent-mux-delegate-job', 'scripts'), ('multi-agent-mux-delegate-job', 'scripts')):
             p = os.path.join(d, *sub)
             if os.path.isdir(p):
                 hit = p
@@ -85,6 +101,7 @@ else:
         d = os.path.dirname(d)
 
 import mqtt_common
+import registry
 
 # Executed INSIDE lib.sh::atomic_dump_yaml (system python3 + PyYAML), under the
 # YAML flock with schema-validate + .bak (review item 5). Marks matching running
@@ -132,6 +149,7 @@ def handle_terminal(jid, event):
 
 
 state = {'last_msg': time.time(), 'connected': False, 'failed': False}
+last_seqs = {}
 
 
 def on_message(_client, _userdata, msg):
@@ -140,7 +158,48 @@ def on_message(_client, _userdata, msg):
         payload = json.loads(msg.payload.decode("utf-8"))
         jid = payload.get("job_id")
         event = payload.get("event")
-        if jid and event in ("completed", "error"):
+        if not jid or not event:
+            return
+        
+        if workspace_root:
+            registry_dir = os.path.join(workspace_root, '.mam', 'jobs')
+        else:
+            yaml_dir = os.path.dirname(yaml_path) if yaml_path else ""
+            registry_dir = os.path.join(yaml_dir, 'jobs') if yaml_dir else '.mam/jobs'
+        
+        try:
+            job = registry.load_job(jid, registry_dir)
+        except FileNotFoundError:
+            # Silently ignore events for jobs not in the local registry
+            return
+            
+        expected_token = job.get("auth_token")
+        if not mqtt_common.verify_hmac(payload, expected_token):
+            print(f"MQTT Monitor: drop event for job {jid}: HMAC verify failed", flush=True)
+            return
+            
+        seq = payload.get("seq")
+        if seq is None or not isinstance(seq, int):
+            print(f"MQTT Monitor: drop event for job {jid}: missing or invalid seq", flush=True)
+            return
+        if seq <= last_seqs.get(jid, 0):
+            print(f"MQTT Monitor: drop event for job {jid}: seq {seq} not monotonic (last {last_seqs.get(jid, 0)})", flush=True)
+            return
+        last_seqs[jid] = seq
+        
+        # Append the event to events.ndjson audit trail
+        mqtt_common.append_event(jid, {
+            "event": "received",
+            "source_event": event,
+            "seq": seq,
+            "topic": msg.topic,
+            "timestamp": payload.get("timestamp"),
+            "detail": payload.get("detail", ""),
+        })
+        
+        print(f"MQTT Monitor: recorded event {event} for job {jid} (seq={seq})", flush=True)
+        
+        if event in ("completed", "error"):
             print(f"MQTT Monitor: received terminal event {event} for job {jid}", flush=True)
             handle_terminal(jid, event)
     except Exception as e:
@@ -204,7 +263,7 @@ PYEOF
 
   if [ "$sub_rc" = "3" ]; then
     echo "MQTT Monitor: broker unavailable — falling back to polling (interval ${POLL_INTERVAL}s)" >&2
-    _self="$SKILLS_DIR/tmux-agent-orchestrate-monitor/scripts/reconcile.sh"
+    _self="$SKILLS_DIR/multi-agent-mux-monitor/scripts/reconcile.sh"
     _start=$(date +%s)
     while :; do
       bash "$_self" --once --emit-diff >/dev/null 2>&1 || true
@@ -351,7 +410,7 @@ if tmux_confirmed:
         if not pm:
             continue
         agent = 'claude' if name.endswith('-creator-claude') else 'agy'
-        cmd_full = 'claude' if agent == 'claude' else 'agy --dangerously-skip-permissions'
+        cmd_full = 'claude --dangerously-skip-permissions' if agent == 'claude' else 'agy --dangerously-skip-permissions'
         server_opt = f"-L {srv} " if srv != 'default' else ""
         entry = {
             'name': name,

.agents/skills/multi-agent-mux-resume/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: tmux-agent-orchestrate-resume
+name: multi-agent-mux-resume
-description: "Resume an existing agent (claude, antigravity/agy) conversation by UUID into a tmux session. Reads .hermes/agent-sessions.yaml for the saved session/conversation id, spawns (or reuses) a tmux session of the matching name, and runs `claude -r <id>` or `agy --conversation <id>` inside. Use when you want to reattach to a previous session's context, or revive a session whose tmux died but the agent's conversation is still on disk."
+description: "Resume an existing agent (claude, antigravity/agy) conversation by UUID into a tmux session. Reads .mam/agent-sessions.yaml for the saved session/conversation id, spawns (or reuses) a tmux session of the matching name, and runs `claude -r <id>` or `agy --conversation <id>` inside. Use when you want to reattach to a previous session's context, or revive a session whose tmux died but the agent's conversation is still on disk."
 version: 1.0.0
 author: godopu
 license: MIT
@@ -9,15 +9,15 @@ environments: [terminal, tmux]
 metadata:
   hermes:
     tags: [agent, tmux, claude, antigravity, agy, multi-agent, context, resume, session-id]
-    related_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-stop, tmux-agent-orchestrate-monitor, claude-code]
+    related_skills: [multi-agent-mux-create, multi-agent-mux-stop, multi-agent-mux-monitor, claude-code]
-    prereq_skills: [tmux-agent-orchestrate-create]
+    prereq_skills: [multi-agent-mux-create]
 ---
 
 # Multi-Agent Resume — Reattach to a Saved Conversation
 
-> **Companion skills**: `tmux-agent-orchestrate-create` (start a fresh agent), `tmux-agent-orchestrate-stop` (terminate), `tmux-agent-orchestrate-monitor` (live status).
+> **Companion skills**: `multi-agent-mux-create` (start a fresh agent), `multi-agent-mux-stop` (terminate), `multi-agent-mux-monitor` (live status).
-> **Tmux Isolation**: `TMUX_SERVER_NAME` env var를 create에서 설정한 경우, 동일 서버에서 동작합니다. 자세한 격리 패턴은 [tmux-agent-orchestrate-create/SKILL.md](../tmux-agent-orchestrate-create/SKILL.md) 참조.
+> **Tmux Isolation**: `TMUX_SERVER_NAME` env var를 create에서 설정한 경우, 동일 서버에서 동작합니다. 자세한 격리 패턴은 [multi-agent-mux-create/SKILL.md](../multi-agent-mux-create/SKILL.md) 참조.
-> **Single source of truth**: `./.hermes/agent-sessions.yaml`.
+> **Single source of truth**: `./.mam/agent-sessions.yaml`.
 
 ## What this skill does
 
@@ -26,12 +26,12 @@ metadata:
 Three cases this skill handles:
 
 1. **tmux is dead, conversation lives** — `agent-sessions.yaml` has the UUID. The JSONL/db is on disk. Re-spawn the tmux session + run `claude -r <id>` / `agy --conversation <id>`.
-2. **tmux is alive but empty** — You started a session with `tmux-agent-orchestrate-create` but haven't sent a message yet (so no session id was assigned). The user can either send their first message (and the id is auto-assigned), or you can read the *workspace's* most recent conversation from `$HOME_DIR/.gemini/antigravity-cli/cache/last_conversations.json` (defaults to `~/.gemini/...`) for agy, or the latest `*.jsonl` in `$CLAUDE_PROJECT_DIR/<workspace-key>/` (defaults to `~/.claude/projects/`) for claude.
+2. **tmux is alive but empty** — You started a session with `multi-agent-mux-create` but haven't sent a message yet (so no session id was assigned). The user can either send their first message (and the id is auto-assigned), or you can read the *workspace's* most recent conversation from `$HOME_DIR/.gemini/antigravity-cli/cache/last_conversations.json` (defaults to `~/.gemini/...`) for agy, or the latest `*.jsonl` in `$CLAUDE_PROJECT_DIR/<workspace-key>/` (defaults to `~/.claude/projects/`) for claude.
 3. **tmux is alive AND the agent inside is already running** — Just attach. No re-spawn needed.
 
 ### Resuming a `stopped` session (`stopped → running`)
 
-When a session was ended via `tmux-agent-orchestrate-stop` (which captures the ID and gracefully stops by default),
+When a session was ended via `multi-agent-mux-stop` (which captures the ID and gracefully stops by default),
 its row is `status: stopped` with `resumable: true` and the conversation id
 already recorded in `claude_session_id_own` / `agy_conversation_id_own`. This is the
 ideal resume path:
@@ -55,26 +55,26 @@ ideal resume path:
    - claude: `ls -t $CLAUDE_PROJECT_DIR/<workspace-key>/*.jsonl | head -1` and parse the `sessionId` from the first line
    - agy: `jq -r '."<workspace>"' $HOME_DIR/.gemini/antigravity-cli/cache/last_conversations.json`
 
-If all three are empty → the workspace has no conversation yet. Fall back to `tmux-agent-orchestrate-create`.
+If all three are empty → the workspace has no conversation yet. Fall back to `multi-agent-mux-create`.
 
 ## Workflow
 
 ```bash
 WORKSPACE=/path/to/project
 AGENT=claude  # or agy or hermes
-SESSION_NAME=<workspace>-creator-<agent>  # same convention as tmux-agent-orchestrate-create
+SESSION_NAME=<workspace>-creator-<agent>  # same convention as multi-agent-mux-create
 
 # 1. Resolve the session id
-UUID=$(bash skills/tmux-agent-orchestrate-resume/scripts/resolve_session_id.sh \
+UUID=$(bash .agents/skills/multi-agent-mux-resume/scripts/resolve_session_id.sh \
   --workspace "$WORKSPACE" --agent "$AGENT")
 
 if [ -z "$UUID" ]; then
-  echo "No saved session for $WORKSPACE ($AGENT). Use tmux-agent-orchestrate-create first."
+  echo "No saved session for $WORKSPACE ($AGENT). Use multi-agent-mux-create first."
   exit 1
 fi
 
 # Resolve the isolated tmux server name
-source skills/lib.sh
+source .agents/skills/lib.sh
 export TMUX_SERVER_NAME="$(resolve_tmux_server "$SESSION_NAME")"
 
 # 2. If tmux is alive, attach. Done.
@@ -107,8 +107,8 @@ case "$AGENT" in
 esac
 
 # 4. Update agent-sessions.yaml: status running, last_visible_status
-# (Also automatically publishes a `progress --detail "resumed"` event to the tmux-agent-orchestrate-delegate-job registry if a delegate_job_id exists)
+# (Also automatically publishes a `progress --detail "resumed"` event to the multi-agent-mux-delegate-job registry if a delegate_job_id exists)
-bash skills/tmux-agent-orchestrate-resume/scripts/update_yaml_resumed.sh \
+bash .agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh \
   --session "$SESSION_NAME" --uuid "$UUID"
 
 # 5. Attach
@@ -120,8 +120,8 @@ tmux attach -t "$SESSION_NAME"
 - **`claude -r` requires the SAME project directory** — if the workspace path differs from when the session was created, claude will create a new project dir key (`-home-...-different-name`) and put the resume in a different location. Always `-c` (cd to workspace) before running.
 - **agy's `--conversation` flag name varies by version** — older versions used `--resume` or `-r`. Check `agy --help | grep -E "conversation|resume"` and use the right flag. v1.0.x: `--conversation`.
 - **The first message after resume might re-trigger TUI dialogs** — if the original session was created with `--dangerously-skip-permissions`, those flags are NOT persisted; you must re-apply them on resume. The script above re-passes them.
-- **Don't resume if the session is brand new and empty** — `tmux-agent-orchestrate-create` already set up an empty container; sending a probe message ("init") is the right way to materialize a session id, NOT `claude -r` with a placeholder.
+- **Don't resume if the session is brand new and empty** — `multi-agent-mux-create` already set up an empty container; sending a probe message ("init") is the right way to materialize a session id, NOT `claude -r` with a placeholder.
-- **`agy --conversation <id>` will fail if the conversation was deleted from disk** — check `~/.gemini/antigravity-cli/conversations/<uuid>.db` exists before attempting resume. If missing, the conversation is gone; you need a fresh session via `tmux-agent-orchestrate-create`.
+- **`agy --conversation <id>` will fail if the conversation was deleted from disk** — check `~/.gemini/antigravity-cli/conversations/<uuid>.db` exists before attempting resume. If missing, the conversation is gone; you need a fresh session via `multi-agent-mux-create`.
 
 ## Verification
 
@@ -132,7 +132,7 @@ tmux list-panes -t "$SESSION_NAME" -F 'cmd=#{pane_current_command} cwd=#{pane_cu
 # 2. agent-sessions.yaml updated
 python3 -c "
 import yaml
-d = yaml.safe_load(open('.hermes/agent-sessions.yaml'))
+d = yaml.safe_load(open('.mam/agent-sessions.yaml'))
 s = [s for s in d['tmux_sessions'] if s['name'] == '$SESSION_NAME'][0]
 print(f'  status: {s[\"status\"]}')
 print(f'  pane.cmd_full: {s[\"pane\"][\"cmd_full\"]}')
@@ -146,6 +146,6 @@ tmux capture-pane -t "$SESSION_NAME" -p -S -30
 
 ## When NOT to use this skill
 
-- **No saved session yet** → `tmux-agent-orchestrate-create`
+- **No saved session yet** → `multi-agent-mux-create`
-- **Killing an existing session** → `tmux-agent-orchestrate-stop`
+- **Killing an existing session** → `multi-agent-mux-stop`
 - **Just attaching** → `tmux attach -t <name>` (no skill needed)

.agents/skills/multi-agent-mux-resume/scripts/resolve_session_id.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# resolve_session_id.sh — tmux-agent-orchestrate-resume 의 부속 스크립트
+# resolve_session_id.sh — multi-agent-mux-resume 의 부속 스크립트
 # Usage:
 #   bash resolve_session_id.sh --workspace <path> --agent <claude|agy>
 # 출력: stdout 으로 UUID 한 줄 (없으면 빈 줄 + exit 0)

.agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# update_yaml_resumed.sh — tmux-agent-orchestrate-resume 의 부속 스크립트
+# update_yaml_resumed.sh — multi-agent-mux-resume 의 부속 스크립트
 # Resume 한 세션의 agent-sessions.yaml 엔트리를 status=running + resume 메타로 갱신.
 # resume UUID 를 per-row own id (claude_session_id_own / agy_conversation_id_own)
 # 에 박는다 — agent_identities 전역은 더 이상 primary 아님 (cache 로 강등, P0-C/단계 e).

.agents/skills/multi-agent-mux-status/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: tmux-agent-orchestrate-status
+name: multi-agent-mux-status
 description: "Read-only instant snapshot of all agent tmux sessions — name, YAML status, tmux alive, pane cmd/cwd, resume UUID on disk, and any drift. No Kanban, no mutation. Reuses reconcile.sh --dry-run for the diff logic. Use when you want to know 'what's running RIGHT NOW' without spinning up a Kanban monitor worker."
 version: 1.0.0
 author: godopu
@@ -9,36 +9,36 @@ environments: [terminal, tmux]
 metadata:
   hermes:
     tags: [agent, tmux, claude, antigravity, agy, status, read-only, snapshot]
-    related_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-resume, tmux-agent-orchestrate-stop, tmux-agent-orchestrate-monitor]
+    related_skills: [multi-agent-mux-create, multi-agent-mux-resume, multi-agent-mux-stop, multi-agent-mux-monitor]
-    prereq_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-monitor]
+    prereq_skills: [multi-agent-mux-create, multi-agent-mux-monitor]
 ---
 
 # Multi-Agent Status — Read-Only Instant Snapshot
 
-> **Companion skills**: `tmux-agent-orchestrate-create` (start), `tmux-agent-orchestrate-resume` (re-attach), `tmux-agent-orchestrate-stop` (terminate), `tmux-agent-orchestrate-monitor` (live polling).
+> **Companion skills**: `multi-agent-mux-create` (start), `multi-agent-mux-resume` (re-attach), `multi-agent-mux-stop` (terminate), `multi-agent-mux-monitor` (live polling).
 > **Tmux Isolation**: `status` 명령은 YAML에 등록된 모든 세션의 격리 서버(`tmux_server` 필드)를 자동으로 조회하여 상태를 확인하므로, `TMUX_SERVER_NAME` 환경변수를 수동으로 지정하지 않아도 모든 격리 서버의 세션 상태를 통합 조회합니다.
-> **Single source of truth**: `./.hermes/agent-sessions.yaml`.
+> **Single source of truth**: `./.mam/agent-sessions.yaml`.
 
 ## What this skill does
 
 Print a single table of every agent tmux session, comparing YAML state to actual tmux state. **No mutation. No Kanban. No polling loop.**
 
-This is the "what's running right now?" answer — faster than dispatching `tmux-agent-orchestrate-monitor` (which polls every 30s) and safer than `reconcile.sh --once --emit-diff` (which mutates as a side effect).
+This is the "what's running right now?" answer — faster than dispatching `multi-agent-mux-monitor` (which polls every 30s) and safer than `reconcile.sh --once --emit-diff` (which mutates as a side effect).
 
 ## Pre-flight
 
 ```bash
 command -v tmux
 command -v python3
-test -f .hermes/agent-sessions.yaml
+test -f .mam/agent-sessions.yaml
 ```
 
-If `agent-sessions.yaml` doesn't exist or is malformed → print clear error, exit 1. **Do not create it.** (Use `tmux-agent-orchestrate-create` first.)
+If `agent-sessions.yaml` doesn't exist or is malformed → print clear error, exit 1. **Do not create it.** (Use `multi-agent-mux-create` first.)
 
 ## Workflow
 
 ```bash
-bash skills/tmux-agent-orchestrate-status/scripts/status.sh [--json]
+bash .agents/skills/multi-agent-mux-status/scripts/status.sh [--json]
 ```
 
 The script:
@@ -98,17 +98,17 @@ lab-paper-pdf2md-creator-claude              default      running    alive  clau
 
 | Class | Detection | Meaning |
 |---|---|---|
-| `A` | YAML `running`, tmux dead | session died without going through `tmux-agent-orchestrate-stop`. *Could* auto-terminate but won't — that's `tmux-agent-orchestrate-monitor`'s job. |
+| `A` | YAML `running`, tmux dead | session died without going through `multi-agent-mux-stop`. *Could* auto-terminate but won't — that's `multi-agent-mux-monitor`'s job. |
-| `B` | tmux alive, not in YAML | ad-hoc session someone started without `tmux-agent-orchestrate-create`. Suggest: "use tmux-agent-orchestrate-create to register, or tmux kill-session to clean up." |
+| `B` | tmux alive, not in YAML | ad-hoc session someone started without `multi-agent-mux-create`. Suggest: "use multi-agent-mux-create to register, or tmux kill-session to clean up." |
-| `C` | YAML has `claude_session_id_own: null` AND a new *.jsonl exists | new session id materialized; suggest: "run tmux-agent-orchestrate-resume or reconcile to register it." |
+| `C` | YAML has `claude_session_id_own: null` AND a new *.jsonl exists | new session id materialized; suggest: "run multi-agent-mux-resume or reconcile to register it." |
-| `D` | YAML has UUID in `agent_identities`, but the on-disk artifact is gone | stale UUID; user should `tmux-agent-orchestrate-stop --purge-conversation` to clean up. |
+| `D` | YAML has UUID in `agent_identities`, but the on-disk artifact is gone | stale UUID; user should `multi-agent-mux-stop --purge-conversation` to clean up. |
 
 ## Pitfalls
 
-- **Do NOT use this skill to drive mutations** — the output is a snapshot, not a call to action. If you need to fix drifts, dispatch `tmux-agent-orchestrate-monitor` (Kanban worker) or run `tmux-agent-orchestrate-resume` / `tmux-agent-orchestrate-stop` manually.
+- **Do NOT use this skill to drive mutations** — the output is a snapshot, not a call to action. If you need to fix drifts, dispatch `multi-agent-mux-monitor` (Kanban worker) or run `multi-agent-mux-resume` / `multi-agent-mux-stop` manually.
 - **Read-only is enforced by script** — `status.sh` opens the YAML with `open(path)` (no `'w'`), never calls `tmux kill-session`, never writes anywhere. The `reconcile.sh --dry-run` mode is the same path.
-- **If `agent-sessions.yaml` is malformed** — print the YAML error verbatim and exit 1. Do NOT attempt recovery (that's `tmux-agent-orchestrate-stop --purge-conversation` or manual edit's job).
+- **If `agent-sessions.yaml` is malformed** — print the YAML error verbatim and exit 1. Do NOT attempt recovery (that's `multi-agent-mux-stop --purge-conversation` or manual edit's job).
-- **Sessions outside the `<workspace>-creator-*` naming convention** are still shown but tagged `ad-hoc` — they didn't go through `tmux-agent-orchestrate-create` and aren't tracked in YAML.
+- **Sessions outside the `<workspace>-creator-*` naming convention** are still shown but tagged `ad-hoc` — they didn't go through `multi-agent-mux-create` and aren't tracked in YAML.
 
 ## When to use
 
@@ -119,6 +119,6 @@ lab-paper-pdf2md-creator-claude              default      running    alive  clau
 
 ## When NOT to use
 
-- Continuous live tracking → `tmux-agent-orchestrate-monitor` (Kanban worker)
+- Continuous live tracking → `multi-agent-mux-monitor` (Kanban worker)
 - Recovering from corruption → manual edit + `.bak` restore
-- Polling more than once a minute → `tmux-agent-orchestrate-monitor` (it dedupes)
+- Polling more than once a minute → `multi-agent-mux-monitor` (it dedupes)

.agents/skills/multi-agent-mux-status/scripts/status.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# status.sh — tmux-agent-orchestrate-status 의 부속 스크립트 (READ-ONLY)
+# status.sh — multi-agent-mux-status 의 부속 스크립트 (READ-ONLY)
 # 한 번 호출로 현재 agent 세션 상태표를 출력. 부수효과 없음.
 # reconcile.sh --dry-run 을 재사용해 drift 를 계산하고 (P1-E), YAML/디스크에서
 # 보강한 표를 그린다. YAML 을 절대 수정하지 않는다.
@@ -9,12 +9,12 @@ set -euo pipefail
 
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"
 
-RECONCILE="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/tmux-agent-orchestrate-monitor/scripts/reconcile.sh"
+RECONCILE="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/multi-agent-mux-monitor/scripts/reconcile.sh"
 
 JSON=0
 [ "${1:-}" = "--json" ] && JSON=1
 
-[ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found. Run tmux-agent-orchestrate-create first." >&2; exit 1; }
+[ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found. Run multi-agent-mux-create first." >&2; exit 1; }
 
 # read-only drift snapshot — reconcile.sh --dry-run (no side effects)
 DRIFT_JSON="$(bash "$RECONCILE" --once --emit-diff --dry-run)"
@@ -24,9 +24,9 @@ if [ "$JSON" = "1" ]; then
   exit 0
 fi
 
-# Project root (parent of skills/) holds the tmux-agent-orchestrate-delegate-job .hermes registry.
+# Project root (parent of .agents/) holds the multi-agent-mux-delegate-job .mam registry.
 # Resolved relative to this script — no hardcoded absolute path (review item 6).
-PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)"
+PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../../../" && pwd)"
 
 DRIFT_JSON="$DRIFT_JSON" env_python "$AGENT_SESSIONS_YAML" PROJECT_ROOT="$PROJECT_ROOT" <<'PYEOF'
 import os, json, glob
@@ -95,9 +95,9 @@ def get_job_status(s):
     # Candidate locations (review item 6: project-root-relative, no hardcoded abs paths):
     #   1) cwd-relative registry  2) project-root registry  3) project-root audit log
     candidates = [
-        os.path.join('.hermes', 'jobs', f"{jid}.json"),
+        os.path.join('.mam', 'jobs', f"{jid}.json"),
-        os.path.join(project_root, '.hermes', 'jobs', f"{jid}.json"),
+        os.path.join(project_root, '.mam', 'jobs', f"{jid}.json"),
-        os.path.join(project_root, '.hermes', 'delegate_job_logs', jid, 'status.json'),
+        os.path.join(project_root, '.mam', 'delegate_job_logs', jid, 'status.json'),
     ]
     for path in candidates:
         if os.path.exists(path):

.agents/skills/multi-agent-mux-stop/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: tmux-agent-orchestrate-stop
+name: multi-agent-mux-stop
-description: "Stop an agent tmux session (claude, antigravity/agy) and update .hermes/agent-sessions.yaml. Default stops gracefully and marks status=stopped with conversation preserved for resume. Does NOT delete on-disk conversation artifacts (jsonl/db) — those are preserved unless --purge-conversation is passed. Use when ending a work session, switching to a different one, or cleaning up before a fresh start."
+description: "Stop an agent tmux session (claude, antigravity/agy) and update .mam/agent-sessions.yaml. Default stops gracefully and marks status=stopped with conversation preserved for resume. Does NOT delete on-disk conversation artifacts (jsonl/db) — those are preserved unless --purge-conversation is passed. Use when ending a work session, switching to a different one, or cleaning up before a fresh start."
 version: 1.0.0
 author: godopu
 license: MIT
@@ -9,23 +9,23 @@ environments: [terminal, tmux]
 metadata:
   hermes:
     tags: [agent, tmux, claude, antigravity, agy, multi-agent, stop, terminate, cleanup]
-    related_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-resume, tmux-agent-orchestrate-monitor]
+    related_skills: [multi-agent-mux-create, multi-agent-mux-resume, multi-agent-mux-monitor]
-    prereq_skills: [tmux-agent-orchestrate-create, tmux-agent-orchestrate-resume]
+    prereq_skills: [multi-agent-mux-create, multi-agent-mux-resume]
 ---
 
 # Multi-Agent Stop — Stop an Agent tmux Session
 
-> **Companion skills**: `tmux-agent-orchestrate-create` (start), `tmux-agent-orchestrate-resume` (re-attach), `tmux-agent-orchestrate-monitor` (live status).
+> **Companion skills**: `multi-agent-mux-create` (start), `multi-agent-mux-resume` (re-attach), `multi-agent-mux-monitor` (live status).
 > **Tmux Isolation**: `stop` 명령은 YAML의 `tmux_server` 필드를 자동으로 파싱하여 해당 격리 서버의 세션을 안전하게 종료(kill)하므로, `TMUX_SERVER_NAME` 환경변수를 수동으로 지정할 필요가 없습니다.
-> **Single source of truth**: `./.hermes/agent-sessions.yaml`.
+> **Single source of truth**: `./.mam/agent-sessions.yaml`.
 
 ## What this skill does
 
 Stop an agent's tmux session gracefully, resolve and store the conversation ID, and **mark the YAML entry (status=stopped)**. Preserves:
 
 - The tmux session's recorded `pane.pid / cmd / cwd / mcp_attachments` for audit
-- The agent's on-disk conversation (claude `*.jsonl`, agy `conversations/*.db`) — so the user can `tmux-agent-orchestrate-resume` later
+- The agent's on-disk conversation (claude `*.jsonl`, agy `conversations/*.db`) — so the user can `multi-agent-mux-resume` later
-- The `start_command` so a future `tmux-agent-orchestrate-create --session <name>` reproduces the same tmux spec
+- The `start_command` so a future `multi-agent-mux-create --session <name>` reproduces the same tmux spec
 
 The stop command is always **graceful by default**:
 1. Sends exit keys to the agent TUI (`/exit` for Claude, `Exit` for Agy) and waits 3 seconds.
@@ -37,7 +37,7 @@ The stop command is always **graceful by default**:
 
 ```bash
 SESSION_NAME=<workspace>-creator-<agent>  # convention
-AGENT_SESSIONS_YAML=.hermes/agent-sessions.yaml
+AGENT_SESSIONS_YAML=.mam/agent-sessions.yaml
 
 # 1) Session is registered?
 python3 -c "
@@ -45,7 +45,7 @@ import yaml
 d = yaml.safe_load(open('$AGENT_SESSIONS_YAML'))
 names = [s['name'] for s in d.get('tmux_sessions', [])]
 if '$SESSION_NAME' not in names:
-    print('NOT in YAML — refusing to stop (no audit trail). Use tmux-agent-orchestrate-create first, or pass --force-no-yaml.')
+    print('NOT in YAML — refusing to stop (no audit trail). Use multi-agent-mux-create first, or pass --force-no-yaml.')
     raise SystemExit(1)
 "
 
@@ -65,16 +65,16 @@ fi
 
 ```bash
 # 1. Stop gracefully (default — captures ID, shuts down safely, status=stopped)
-bash skills/tmux-agent-orchestrate-stop/scripts/stop_session.sh \
+bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh \
   --session "$SESSION_NAME"
 
 # 2. Stop gracefully + record a custom stop reason
-bash skills/tmux-agent-orchestrate-stop/scripts/stop_session.sh \
+bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh \
   --session "$SESSION_NAME" --reason api_error
 
 # 3. Stop gracefully + clean up on-disk conversation (DANGEROUS)
 #    — this prevents any future resume (status=terminated, resumable=false).
-bash skills/tmux-agent-orchestrate-stop/scripts/stop_session.sh \
+bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh \
   --session "$SESSION_NAME" --purge-conversation
 ```
 
@@ -94,19 +94,19 @@ If `--purge-conversation` is used: `status: terminated`, `terminated_at`, `termi
 
 The script:
 1. Verifies the session is in agent-sessions.yaml
-2. If `delegate_job_id` is set, automatically publishes a `progress --detail "terminating"` event to the tmux-agent-orchestrate-delegate-job registry
+2. If `delegate_job_id` is set, automatically publishes a `progress --detail "terminating"` event to the multi-agent-mux-delegate-job registry
 3. Captures the `last_visible_status` from `tmux capture-pane` (so we have a final TUI snapshot for audit)
 4. Attempts graceful exit keys → SIGTERM kill-session → SIGKILL fallback
 5. For `purge-conversation`: deletes `~/.claude/projects/.../jsonl` (claude) or `~/.gemini/antigravity-cli/conversations/...db` + `brain/...` (agy)
 6. Updates the YAML entry and SQLite database atomically
-7. If `delegate_job_id` is set, publishes a `completed` event to the tmux-agent-orchestrate-delegate-job registry
+7. If `delegate_job_id` is set, publishes a `completed` event to the multi-agent-mux-delegate-job registry
 
 ## Pitfalls
 
-- **Don't delete on-disk artifacts by default** — the agent's `*.jsonl` / `conversations/*.db` is the data that `tmux-agent-orchestrate-resume` needs. `--purge-conversation` is for when the user is genuinely done with the conversation and wants zero recovery chance.
+- **Don't delete on-disk artifacts by default** — the agent's `*.jsonl` / `conversations/*.db` is the data that `multi-agent-mux-resume` needs. `--purge-conversation` is for when the user is genuinely done with the conversation and wants zero recovery chance.
-- **YAML is append-only until you write a stop** — if a previous run left the entry as `running` but tmux is actually dead (crash, host reboot), the YAML is stale. Running `tmux-agent-orchestrate-stop` will detect "tmux already dead, just update YAML" and proceed.
+- **YAML is append-only until you write a stop** — if a previous run left the entry as `running` but tmux is actually dead (crash, host reboot), the YAML is stale. Running `multi-agent-mux-stop` will detect "tmux already dead, just update YAML" and proceed.
-- **Don't delete the `claude_session_id_own: null` placeholder** — when the user creates a fresh session with `tmux-agent-orchestrate-create` and never sent a message, the entry has `claude_session_id_own: null`. Stopping must preserve that field.
+- **Don't delete the `claude_session_id_own: null` placeholder** — when the user creates a fresh session with `multi-agent-mux-create` and never sent a message, the entry has `claude_session_id_own: null`. Stopping must preserve that field.
-- **Monitor skill may still be tracking** — if `tmux-agent-orchestrate-monitor` is running a heartbeat loop, stopping a session while it watches will trigger its `tmux ls != yaml` reconciliation. That's expected — let the monitor run, it will mark the entry as `terminated` on its own.
+- **Monitor skill may still be tracking** — if `multi-agent-mux-monitor` is running a heartbeat loop, stopping a session while it watches will trigger its `tmux ls != yaml` reconciliation. That's expected — let the monitor run, it will mark the entry as `terminated` on its own.
 
 ## Verification
 
@@ -133,4 +133,4 @@ print(f'  preserved: pane.pid={s[\"pane\"][\"pid\"]}, cmd={s[\"pane\"][\"cmd\"]}
 
 - **Just detaching** → `tmux detach` (Ctrl-B d) or just close the terminal. The tmux session keeps running.
 - **Stopping the agent inside but keeping tmux** → send `Ctrl-C` or `/exit` (claude) / `Ctrl-D` (agy) via `tmux send-keys`. The tmux session stays but the agent process is gone.
-- **Replacing an existing session with a new one** → `tmux-agent-orchestrate-stop` first, then `tmux-agent-orchestrate-create`.
+- **Replacing an existing session with a new one** → `multi-agent-mux-stop` first, then `multi-agent-mux-create`.

.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# stop_session.sh — tmux-agent-orchestrate-stop 의 부속 스크립트
+# stop_session.sh — multi-agent-mux-stop 의 부속 스크립트
 # Usage:
 #   bash stop_session.sh --session <name> [--agent claude|agy] \
 #       [--mode soft|hard] [--purge-conversation] [--yes]
@@ -139,7 +139,7 @@ fi
 if [ "$PURGE" = "1" ] && [ "$YES" != "1" ]; then
   echo "DANGER: --purge-conversation will DELETE this workspace's on-disk conversation."
   echo "  workspace: ${TARGET_CWD:-<unknown>}"
-  echo "  This means: no future tmux-agent-orchestrate-resume for this session."
+  echo "  This means: no future multi-agent-mux-resume for this session."
   echo "  Re-run with --yes to confirm."
   exit 3
 fi
@@ -286,11 +286,11 @@ if purge and purge_uuid:
             print(f"purged: {brain}", flush=True)
         target['agy_conversation_id_own'] = None
     elif agent == 'hermes':
-        json_file = f"{home}/.hermes/sessions/session_{purge_uuid}.json"
+        json_file = f"{home}/.mam/sessions/session_{purge_uuid}.json"
         if os.path.exists(json_file):
             os.remove(json_file)
             print(f"purged: {json_file}", flush=True)
-        hdb = f"{home}/.hermes/state.db"
+        hdb = f"{home}/.mam/state.db"
         if os.path.exists(hdb):
             try:
                 import sqlite3
@@ -337,5 +337,5 @@ echo "  captured: ${CAPTURED_UUID:-<none>}"
 echo "  purge:    $PURGE${PURGE_UUID:+ (uuid $PURGE_UUID)}"
 echo "  time:     $NOW_ISO"
 echo
-echo "Recovery: tmux-agent-orchestrate-create + tmux-agent-orchestrate-resume 로 동일 컨텍스트 복원 가능"
+echo "Recovery: multi-agent-mux-create + multi-agent-mux-resume 로 동일 컨텍스트 복원 가능"
 echo "  (단 --purge-conversation 사용 시 복원 불가)"

.env.example

@@ -1,5 +1,5 @@
 # ---------------------------------------------------------------------------
-# .env.example — committable template for the tmux-agent-orchestrate-* skills
+# .env.example — committable template for the multi-agent-mux-* skills
 #
 # This file is tracked in git and contains NO secrets. To get a working local
 # config, copy it to `.env` (which is git-ignored) and edit as needed:
@@ -20,12 +20,12 @@
 # ===========================================================================
 
 # Single source of truth for the agent session registry YAML.
-#default: <workspace>/.hermes/agent-sessions.yaml
+#default: <workspace>/.mam/agent-sessions.yaml
-# AGENT_SESSIONS_YAML=/path/to/workspace/.hermes/agent-sessions.yaml
+# AGENT_SESSIONS_YAML=/path/to/workspace/.mam/agent-sessions.yaml
 
 # Where the monitor (reconcile.sh) keeps its drift-state cache.
-#default: <workspace>/.cache/tmux-agent-orchestrate-monitor
+#default: <workspace>/.cache/multi-agent-mux-monitor
-# AGENT_SESSIONS_STATE_DIR=/path/to/workspace/.cache/tmux-agent-orchestrate-monitor
+# AGENT_SESSIONS_STATE_DIR=/path/to/workspace/.cache/multi-agent-mux-monitor
 
 # Root directory that holds Claude Code per-project conversation logs (*.jsonl).
 #default: $HOME/.claude/projects
@@ -72,6 +72,6 @@
 #default: (unset → no client key)
 # MQTT_KEYFILE=/path/to/client.key
 
-# Directory for delegate-job audit logs (sits beside .hermes/jobs/).
+# Directory for delegate-job audit logs (sits beside .mam/jobs/).
-#default: <cwd>/.hermes/delegate_job_logs
+#default: <cwd>/.mam/delegate_job_logs
-# DELEGATE_JOB_LOGS_DIR=/path/to/workspace/.hermes/delegate_job_logs
+# DELEGATE_JOB_LOGS_DIR=/path/to/workspace/.mam/delegate_job_logs

.gitignore

@@ -8,7 +8,7 @@ test-sessions*.yaml.bak
 test-sessions*.yaml.lock
 
 # delegate-job 임시/런타임 산출물
-.hermes/
+.mam/
 .venv/
 __pycache__/
 *.pyc
@@ -19,5 +19,5 @@ __pycache__/
 !.env.example
 
 # 빌드/배포 HTML 산출물
-skills/tmux-agent-orchestrate-delegate-job/USER_MANUAL.html
+.agents/skills/multi-agent-mux-delegate-job/USER_MANUAL.html
-skills/tmux-agent-orchestrate-delegate-job/mqtt-broker-setup.html
+.agents/skills/multi-agent-mux-delegate-job/mqtt-broker-setup.html

AGENT.ko.md

@@ -43,8 +43,8 @@
 
 ### 🗃️ 레지스트리 및 상태 관리
 - 본 아키텍처는 목적에 따라 두 가지 레지스트리를 분리하여 운영합니다:
-  - **잡 레지스트리 (Job Registry)**: 각 비동기 잡의 메타데이터와 생명주기는 개별 JSON 파일(`.hermes/jobs/<id>.json`)로 기록되며, 다중 세션 간의 동시 청구(claiming) 경합은 파일 단위의 `fcntl` advisory lock(`registry_lock` via `registry.py`)을 통해 방어합니다.
+  - **잡 레지스트리 (Job Registry)**: 각 비동기 잡의 메타데이터와 생명주기는 개별 JSON 파일(`.mam/jobs/<id>.json`)로 기록되며, 다중 세션 간의 동시 청구(claiming) 경합은 파일 단위의 `fcntl` advisory lock(`registry_lock` via `registry.py`)을 통해 방어합니다.
-  - **세션 레지스트리 (Session Registry)**: TMUX 모니터링 상태 및 에이전트 구동 정보는 SQLite WAL 데이터베이스(`.hermes/agent-sessions.db`)를 통해 단일 호스트 내에서 안정적인 동시 트랜잭션으로 일관되게 제어합니다. 단, SQLite WAL 모드는 NFS(네트워크 파일 시스템) 환경에서는 완전한 파일 락이 보장되지 않으므로 로컬 파일 시스템 사용을 권장합니다.
+  - **세션 레지스트리 (Session Registry)**: TMUX 모니터링 상태 및 에이전트 구동 정보는 SQLite WAL 데이터베이스(`.mam/agent-sessions.db`)를 통해 단일 호스트 내에서 안정적인 동시 트랜잭션으로 일관되게 제어합니다. 단, SQLite WAL 모드는 NFS(네트워크 파일 시스템) 환경에서는 완전한 파일 락이 보장되지 않으므로 로컬 파일 시스템 사용을 권장합니다.
 
 ### 🛡️ 보안 프로토콜 (HMAC-SHA256)
 - **무인증 PoC 모드**: 잡 레지스트리 생성 시 `auth_token`이 `null`로 지정된 경우(PoC 기본 모드), 별도의 서명 검증을 생략하고 모든 이벤트를 수용합니다 (`verify_hmac`이 항상 `True`를 반환).
@@ -116,7 +116,7 @@ TMUX 환경에서 실행되는 에이전트가 화면 스크롤 한계로 인해
 
 - [ ] **가상환경 의존성**: `pyyaml`, `paho-mqtt` 등 필요한 Python 패키지가 `.venv` 또는 `requirements.txt`에 포함되었는가?
 - [ ] **환경 설정 파일**: MQTT 브로커 주소 및 보안 Credential이 `.env` 파일에 안전하게 로드되고 공유되는가?
-- [ ] **디렉토리 규약**: 레지스트리 경로(`.hermes/jobs/`) 및 로깅 경로(`.hermes/delegate_job_logs/`)가 `.gitignore`에 등록되었는가?
+- [ ] **디렉토리 규약**: 레지스트리 경로(`.mam/jobs/`) 및 로깅 경로(`.mam/delegate_job_logs/`)가 `.gitignore`에 등록되었는가?
 - [ ] **스크립트 구비**: `mqtt_common.py`, `publish_event.py`, `job_subscriber.py`, `registry.py` 등의 핵심 모듈이 배치되었는가?
 - [ ] **HMAC 활성화**: 새로운 레지스트리 잡 발급 시 난수 기반의 `auth_token`이 정상적으로 주입되고, 서명 기반의 상호 인증이 활성화되는가?
 - [ ] **운영 헌장 배치**: 본 규약 파일(`AGENT.md`)이 새 프로젝트의 **최상위 루트(Root) 디렉터리**에 배치되었는가? (협업을 수행하는 에이전트들이 온보딩 시 규칙을 가장 먼저 인지할 수 있도록 루트 경로 배치가 필수적입니다.)

AGENT.md

@@ -43,8 +43,8 @@ Asynchronous communication and state management between agents are controlled vi
 
 ### 🗃️ Registry & State Management
 - This architecture maintains two distinct registries based on their purpose:
-  - **Job Registry**: The metadata and lifecycle of each asynchronous job are recorded in individual JSON files (`.hermes/jobs/<id>.json`). Concurrency conflicts (claiming races) across multiple sessions are prevented via file-based `fcntl` advisory locks (`registry_lock` via `registry.py`).
+  - **Job Registry**: The metadata and lifecycle of each asynchronous job are recorded in individual JSON files (`.mam/jobs/<id>.json`). Concurrency conflicts (claiming races) across multiple sessions are prevented via file-based `fcntl` advisory locks (`registry_lock` via `registry.py`).
-  - **Session Registry**: TMUX monitoring states and running agent metadata are consistently controlled using a SQLite WAL database (`.hermes/agent-sessions.db`) to support reliable concurrent transactions on a single host. However, since SQLite WAL mode does not guarantee complete file locking in Network File System (NFS) environments, we recommend using a local file system.
+  - **Session Registry**: TMUX monitoring states and running agent metadata are consistently controlled using a SQLite WAL database (`.mam/agent-sessions.db`) to support reliable concurrent transactions on a single host. However, since SQLite WAL mode does not guarantee complete file locking in Network File System (NFS) environments, we recommend using a local file system.
 
 ### 🛡️ Security Protocol (HMAC-SHA256)
 - **Unauthenticated PoC Mode**: If the `auth_token` in the job registry is set to `null` (the default PoC mode), signature verification is skipped and all events are accepted (`verify_hmac` always returns `True`).
@@ -116,7 +116,7 @@ Use this checklist when deploying this agent orchestration model to a new projec
 
 - [ ] **Virtualenv Dependencies**: Are required Python packages like `pyyaml` and `paho-mqtt` included in `.venv` or `requirements.txt`?
 - [ ] **Configuration File**: Are the MQTT broker address and security credentials safely loaded and shared via the `.env` file?
-- [ ] **Directory Convention**: Are the registry path (`.hermes/jobs/`) and logging path (`.hermes/delegate_job_logs/`) added to `.gitignore`?
+- [ ] **Directory Convention**: Are the registry path (`.mam/jobs/`) and logging path (`.mam/delegate_job_logs/`) added to `.gitignore`?
 - [ ] **Core Scripts**: Are the core scripts (`mqtt_common.py`, `publish_event.py`, `job_subscriber.py`, and `registry.py`) in place?
 - [ ] **HMAC Enablement**: When a new registry job is created, is a random `auth_token` correctly injected, and is signature-based mutual authentication active?
 - [ ] **Charter Placement**: Is this protocol file (`AGENT.md`) placed in the **top-level root directory** of the new project? (Placing it at the root is essential so that onboarding agents can recognize the rules immediately.)

BOOTSTRAP.ko.md

@@ -10,14 +10,14 @@
 
 본 프로젝트를 새로운 환경에 복제(Clone)한 후, 핵심 구성 요소들의 위치와 역할을 먼저 파악해야 합니다.
 
-*   `skills/`: 멀티 에이전트 구동 및 비동기 잡 처리를 수행하는 셸 스크립트 모음
+*   `.agents/skills/`: 멀티 에이전트 구동 및 비동기 잡 처리를 수행하는 셸 스크립트 모음
     *   `lib.sh`: 오케스트레이션의 핵심 셸 함수 및 가상환경(venv) 자동 연동 라이브러리
-    *   `tmux-agent-orchestrate-create/`: 격리된 tmux 에이전트 세션을 시작하는 스크립트
+    *   `multi-agent-mux-create/`: 격리된 tmux 에이전트 세션을 시작하는 스크립트
-    *   `tmux-agent-orchestrate-stop/`: 세션을 정상적으로 중지하고 상태를 업데이트하는 스크립트
+    *   `multi-agent-mux-stop/`: 세션을 정상적으로 중지하고 상태를 업데이트하는 스크립트
-    *   `tmux-agent-orchestrate-resume/`: 중지된 에이전트 세션을 이전 대화 상태 그대로 복원하는 스크립트
+    *   `multi-agent-mux-resume/`: 중지된 에이전트 세션을 이전 대화 상태 그대로 복원하는 스크립트
-    *   `tmux-agent-orchestrate-status/`: 전체 에이전트 세션의 현재 구동 상태를 조회하는 스크립트
+    *   `multi-agent-mux-status/`: 전체 에이전트 세션의 현재 구동 상태를 조회하는 스크립트
-    *   `tmux-agent-orchestrate-monitor/`: tmux 상태와 레지스트리 상태를 동기화하는 모니터 스크립트
+    *   `multi-agent-mux-monitor/`: tmux 상태와 레지스트리 상태를 동기화하는 모니터 스크립트
-    *   `tmux-agent-orchestrate-delegate-job/`: 비동기 잡 분할 실행 모듈
+    *   `multi-agent-mux-delegate-job/`: 비동기 잡 분할 실행 모듈
         *   `requirements.txt`: Python 의존성 목록 (paho-mqtt, pyyaml)
         *   `scripts/`: 핵심 비즈니스 로직을 구동하는 Python 스크립트 디렉터리
             *   `registry.py`: 잡의 등록, 클레임 및 원자적 파일 락 제어 (CLI 지원)
@@ -48,7 +48,7 @@
 생성된 `.env` 파일을 열어 설정을 필요에 따라 구성합니다.
 
 > [!NOTE]
-> `generate-env.sh`로 생성된 기본 `.env` 파일은 모든 환경 변수 항목이 주석 처리되어 있습니다. 주석 처리된 상태로 둘 경우 로컬 프로젝트 루트를 기준으로 한 상대 경로(`.hermes/` 등) 및 기본 공개 브로커 주소가 자동 지정되므로 그대로 사용하셔도 무방합니다.
+> `generate-env.sh`로 생성된 기본 `.env` 파일은 모든 환경 변수 항목이 주석 처리되어 있습니다. 주석 처리된 상태로 둘 경우 로컬 프로젝트 루트를 기준으로 한 상대 경로(`.mam/` 등) 및 기본 공개 브로커 주소가 자동 지정되므로 그대로 사용하셔도 무방합니다.
 
 1.  **MQTT Broker 설정 (`MQTT_BROKER`)**:
     *   기본값은 HiveMQ 공개 브로커(`broker.hivemq.com`)로 잡혀 있으나, 보안 및 프라이버시가 중요한 프로덕션 작업 시에는 개인/사설 브로커 주소로 변경할 것을 강력히 권장합니다.
@@ -80,11 +80,11 @@ source .venv/bin/activate
 ```
 
 ### 단계 3.2: 의존성 패키지 설치
-`tmux-agent-orchestrate-delegate-job` 디렉터리에 기재된 `requirements.txt` 의존성 목록을 가상환경에 설치합니다.
+`multi-agent-mux-delegate-job` 디렉터리에 기재된 `requirements.txt` 의존성 목록을 가상환경에 설치합니다.
 
 ```bash
 # 의존성 패키지(pyyaml, paho-mqtt 등) 설치
-pip install -r skills/tmux-agent-orchestrate-delegate-job/requirements.txt
+pip install -r .agents/skills/multi-agent-mux-delegate-job/requirements.txt
 ```
 
 ---
@@ -94,15 +94,15 @@ pip install -r skills/tmux-agent-orchestrate-delegate-job/requirements.txt
 에이전트 제어 상태 및 잡 기록을 위해 로컬 레지스트리 디렉터리가 정상적으로 생성되었는지 확인합니다.
 
 1.  **필수 로컬 디렉터리 구조**:
-    *   `.hermes/jobs/`: 등록된 비동기 잡의 세부 메타데이터가 파일 형태로 저장되는 디렉터리
+    *   `.mam/jobs/`: 등록된 비동기 잡의 세부 메타데이터가 파일 형태로 저장되는 디렉터리
-    *   `.hermes/delegate_job_logs/`: 에이전트가 발행하는 모든 백플레인 이벤트 흐름이 기록되는 audit log (`events.ndjson`) 보존 디렉터리
+    *   `.mam/delegate_job_logs/`: 에이전트가 발행하는 모든 백플레인 이벤트 흐름이 기록되는 audit log (`events.ndjson`) 보존 디렉터리
 2.  **Git 커밋 제어 (.gitignore)**:
     *   새 프로젝트 초기화 시 아래 파일들이 절대 리포지토리에 커밋되지 않도록 `.gitignore` 상태를 점검합니다. `!.env.example` 예외 처리가 유지되어야 템플릿이 보존됩니다:
         ```text
         .env
         .env.*
         !.env.example
-        .hermes/
+        .mam/
         .venv/
         __pycache__/
         *.pyc
@@ -115,14 +115,14 @@ pip install -r skills/tmux-agent-orchestrate-delegate-job/requirements.txt
 환경 구축이 오작동 없이 안전하게 완료되었는지 아래의 체크리스트를 실행해 검증합니다.
 
 > [!IMPORTANT]
-> 아래의 모든 검증 명령은 반드시 **프로젝트 루트 디렉터리**(`.hermes/` 디렉터리가 직접 보이는 위치)에서 실행해야 합니다. 잡 레지스트리 디렉터리 기본 경로가 프로젝트 루트 하위의 `./.hermes/jobs` 상대 경로를 기준으로 탐색되기 때문입니다.
+> 아래의 모든 검증 명령은 반드시 **프로젝트 루트 디렉터리**(`.mam/` 디렉터리가 직접 보이는 위치)에서 실행해야 합니다. 잡 레지스트리 디렉터리 기본 경로가 프로젝트 루트 하위의 `./.mam/jobs` 상대 경로를 기준으로 탐색되기 때문입니다.
 
 ### 검증 테스트 1: 잡 레지스트리 정상 구동 여부
 Python 스크립트 및 venv 라이브러리가 올바르게 로드되는지 확인하기 위해 잡 목록을 조회합니다.
 
 ```bash
 # 가상환경(.venv) 파이썬 인터프리터를 사용하여 실행
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py list
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py list
 ```
 *   **출력 기대 결과**: 에러 메시지 없이 빈 JSON 배열 `[]` 또는 현재 등록된 pending/running 잡 목록이 성공적으로 출력되어야 합니다.
 
@@ -131,29 +131,29 @@ Python 스크립트 및 venv 라이브러리가 올바르게 로드되는지 확
 
 ```bash
 # 1. 테스트용 임시 잡 등록 및 발급된 8자리 Hex 잡 ID 획득
-JID=$(.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py register \
+JID=$(.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py register \
   --agent "test-agent" \
   --prompt "Bootstrap check command" \
   --timeout 120)
 echo "Generated Job ID: $JID"
 
 # 2. 획득한 잡 ID에 대해 백그라운드 이벤트 구독기(Subscriber) 구동
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/job_subscriber.py --job "$JID" &
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/job_subscriber.py --job "$JID" &
 
 # 3. 구독자의 MQTT Broker 소켓 연결 및 수신부 초기화 완료를 보장하기 위해 2초 대기
 sleep 2
 
 # 4. 테스트 시작 이벤트 발행 (Subscribe-before-Publish 원칙 준수)
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/publish_event.py \
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/publish_event.py \
   --job "$JID" \
   --event started \
   --detail "Bootstrap MQTT verification connection check"
 
-# 5. 이벤트 수신이 터미널(stdout) 및 .hermes/delegate_job_logs/events.ndjson 로그 파일에 정상 기록되는지 확인
+# 5. 이벤트 수신이 터미널(stdout) 및 .mam/delegate_job_logs/events.ndjson 로그 파일에 정상 기록되는지 확인
 
 # 6. 검증 완료 후 백그라운드 프로세스 종료 및 테스트 잡 레코드 수동 정리
 kill %1
-rm -f ".hermes/jobs/$JID.json" ".hermes/jobs/$JID.lock"
+rm -f ".mam/jobs/$JID.json" ".mam/jobs/$JID.lock"
 ```
 
 ---

BOOTSTRAP.md

@@ -10,14 +10,14 @@ A new agent can follow the steps in this guide sequentially to establish a stabl
 
 Before cloning this project into a new environment, you must first understand the locations and roles of its core components:
 
-*   `skills/`: A collection of shell scripts that execute multi-agent coordination and asynchronous job processing.
+*   `.agents/skills/`: A collection of shell scripts that execute multi-agent coordination and asynchronous job processing.
     *   `lib.sh`: The core orchestration shell functions and virtual environment (venv) auto-loading library.
-    *   `tmux-agent-orchestrate-create/`: Script to launch isolated tmux agent sessions.
+    *   `multi-agent-mux-create/`: Script to launch isolated tmux agent sessions.
-    *   `tmux-agent-orchestrate-stop/`: Script to gracefully stop agent sessions and update states.
+    *   `multi-agent-mux-stop/`: Script to gracefully stop agent sessions and update states.
-    *   `tmux-agent-orchestrate-resume/`: Script to restore stopped agent sessions back to their previous conversation state.
+    *   `multi-agent-mux-resume/`: Script to restore stopped agent sessions back to their previous conversation state.
-    *   `tmux-agent-orchestrate-status/`: Script to query the current running state of all agent sessions.
+    *   `multi-agent-mux-status/`: Script to query the current running state of all agent sessions.
-    *   `tmux-agent-orchestrate-monitor/`: Monitor script to sync tmux states with the registry.
+    *   `multi-agent-mux-monitor/`: Monitor script to sync tmux states with the registry.
-    *   `tmux-agent-orchestrate-delegate-job/`: Asynchronous job splitting and delegation module.
+    *   `multi-agent-mux-delegate-job/`: Asynchronous job splitting and delegation module.
         *   `requirements.txt`: Python dependency list (`paho-mqtt`, `pyyaml`).
         *   `scripts/`: Python scripts running the core business logic.
             *   `registry.py`: Job registration, claiming, and atomic file lock control (CLI supported).
@@ -48,7 +48,7 @@ Run the environment template copy script provided in the project root:
 Open the generated `.env` file to configure settings as needed.
 
 > [!NOTE]
-> The default `.env` file generated by `generate-env.sh` has all environment variables commented out. If left commented out, the system defaults to using relative paths (`.hermes/`, etc.) relative to the local project root, and the public MQTT broker. You can use it as-is without uncommenting anything.
+> The default `.env` file generated by `generate-env.sh` has all environment variables commented out. If left commented out, the system defaults to using relative paths (`.mam/`, etc.) relative to the local project root, and the public MQTT broker. You can use it as-is without uncommenting anything.
 
 1.  **MQTT Broker Setup (`MQTT_BROKER`)**:
     *   The default broker is HiveMQ's public sandbox broker (`broker.hivemq.com`). However, for production work where security and privacy are critical, we strongly recommend changing this to a private broker address.
@@ -80,11 +80,11 @@ source .venv/bin/activate
 ```
 
 ### Step 3.2: Install Dependency Packages
-Install the required packages listed in `requirements.txt` under `tmux-agent-orchestrate-delegate-job`:
+Install the required packages listed in `requirements.txt` under `multi-agent-mux-delegate-job`:
 
 ```bash
 # Install dependencies (pyyaml, paho-mqtt, etc.)
-pip install -r skills/tmux-agent-orchestrate-delegate-job/requirements.txt
+pip install -r .agents/skills/multi-agent-mux-delegate-job/requirements.txt
 ```
 
 ---
@@ -94,15 +94,15 @@ pip install -r skills/tmux-agent-orchestrate-delegate-job/requirements.txt
 Ensure that the local registry directories required to track agent states and jobs are successfully created:
 
 1.  **Required Directory Structure**:
-    *   `.hermes/jobs/`: Holds detailed metadata files for registered asynchronous jobs.
+    *   `.mam/jobs/`: Holds detailed metadata files for registered asynchronous jobs.
-    *   `.hermes/delegate_job_logs/`: Holds the audit logs (`events.ndjson`) for all backplane events published by agents.
+    *   `.mam/delegate_job_logs/`: Holds the audit logs (`events.ndjson`) for all backplane events published by agents.
 2.  **Git Ignore Configuration (`.gitignore`)**:
     *   When initializing a new project, verify that the following entries are configured in `.gitignore` to prevent committing local runtimes to the repository. The exception `!.env.example` must be kept to preserve the template:
         ```text
         .env
         .env.*
         !.env.example
-        .hermes/
+        .mam/
         .venv/
         __pycache__/
         *.pyc
@@ -115,14 +115,14 @@ Ensure that the local registry directories required to track agent states and jo
 To verify that the environment has been successfully built without runtime errors, run the following verification checklist.
 
 > [!IMPORTANT]
-> All verification commands below must be executed from the **project root directory** (where the `.hermes/` directory is directly visible). This is because the default job registry path resolved by scripts is relative to the current working directory under `./.hermes/jobs`.
+> All verification commands below must be executed from the **project root directory** (where the `.mam/` directory is directly visible). This is because the default job registry path resolved by scripts is relative to the current working directory under `./.mam/jobs`.
 
 ### Verification Test 1: Registry Script Load Check
 Verify that the Python scripts and virtual environment libraries load correctly by listing jobs:
 
 ```bash
 # Run using the python interpreter in the virtual environment
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py list
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py list
 ```
 *   **Expected Output**: The command should exit successfully and print an empty JSON array `[]` (or a list of pending/running jobs if any exist) without any python traceback errors.
 
@@ -131,30 +131,30 @@ Test the end-to-end communication through the broker to verify that events are p
 
 ```bash
 # 1. Register a temporary test job and capture its 8-character Hex Job ID
-JID=$(.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py register \
+JID=$(.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py register \
   --agent "test-agent" \
   --prompt "Bootstrap check command" \
   --timeout 120)
 echo "Generated Job ID: $JID"
 
 # 2. Run the background event subscriber (Subscriber) for this Job ID
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/job_subscriber.py --job "$JID" &
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/job_subscriber.py --job "$JID" &
 
 # 3. Wait 2 seconds to allow the Subscriber to establish its MQTT socket connection
 sleep 2
 
 # 4. Publish a start event (adhering to the Subscribe-before-Publish rule)
-.venv/bin/python3 skills/tmux-agent-orchestrate-delegate-job/scripts/publish_event.py \
+.venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/publish_event.py \
   --job "$JID" \
   --event started \
   --detail "Bootstrap MQTT verification connection check"
 
 # 5. Verify that the event is printed to stdout and written to the audit log:
-#    .hermes/delegate_job_logs/events.ndjson
+#    .mam/delegate_job_logs/events.ndjson
 
 # 6. Stop the background subscriber and clean up the test job records
 kill %1
-rm -f ".hermes/jobs/$JID.json" ".hermes/jobs/$JID.lock"
+rm -f ".mam/jobs/$JID.json" ".mam/jobs/$JID.lock"
 ```
 
 ---

DONE.ko.md

@@ -7,7 +7,7 @@
 
 ## 요약
 
-- **처리 항목**: FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N4, Infra Pattern (총 24개)
+- **처리 항목**: FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N7, FW-W3, Infra Pattern (총 28개)
 - **Working tree**: clean
 - **검증 결과**: 모든 장기 과제, 신규 발견 항목 및 분석 인프라 개선 완료 (agy-existing, claude-existing 교차 검증 PASS)
 
@@ -44,6 +44,7 @@
 | FW-N5 | `job-protocol.md` 보안 프로토콜 규격 갱신 (HMAC 서명 기준) | `6a88f10, 450722b` | Hermes 직접 | 문서/설계 정합성 패스 완료 (PASS) |
 | FW-N6 | `registry.py` 내 `auth_token` 자동 생성 및 CLI 연동 지원 | `6a88f10` | Hermes 직접 | `--auth-token` 인자 추가 및 보안 브로커 감지 시 자동 생성 처리 완료 (PASS) |
 | FW-N7 | `job_subscriber.py` 내 시퀀스 단조 증가 검증을 통한 Replay Attack 방어 | `6a88f10` | Hermes 직접 | Watcher 내 last_seq 추적 및 seq 단조 증가 검사 로직 구현 완료 (PASS) |
+| FW-W3 | 개별 잡 와치독을 단일 와일드카드 구독자로 통합 | `358c72b` | Antigravity | watchdog.sh를 제거하고 reconcile.sh --subscribe 단일 구독자로 이벤트 처리 및 와치독 역할 통합 완료 (PASS) |
 
 ---
 
@@ -98,4 +99,5 @@ a6f7c04 feat(delegate-job): bump default --timeout 600s -> 3600s (1h wall-clock
 
 ## 날짜
 
-2026-06-21 (Sun) 03:52 ~ 07:00 KST
+- 2026-06-21 (Sun) 03:52 ~ 07:00 KST (FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N7, Infra)
+- 2026-06-22 (Mon) 23:44 ~ KST (FW-W3)

DONE.md

@@ -7,7 +7,7 @@
 
 ## Summary
 
-- **Completed Items**: FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N4, Infra Pattern (total of 24 items)
+- **Completed Items**: FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N7, FW-W3, Infra Pattern (total of 28 items)
 - **Working Tree**: clean
 - **Verification Results**: All long-term tasks, newly discovered items, and analysis infrastructure improvements have been completed (mutual verification PASS from `agy-existing` and `claude-existing`).
 
@@ -44,6 +44,7 @@
 | FW-N5 | Update `job-protocol.md` security protocol spec (to HMAC signatures) | `6a88f10, 450722b` | Hermes Direct | Documentation/Design consistency pass completed (PASS) |
 | FW-N6 | Support auto-generated `auth_token` and CLI integration in `registry.py` | `6a88f10` | Hermes Direct | Added `--auth-token` argument, auto-generation on secure broker detection (PASS) |
 | FW-N7 | Prevent Replay Attacks via sequence monotonic increase validation in `job_subscriber.py` | `6a88f10` | Hermes Direct | Added seq tracking in watcher to verify monotonic increase (PASS) |
+| FW-W3 | Consolidate per-job watchdogs into shared wildcard subscriber | `358c72b` | Antigravity | Consolidate watchdog logic to reconcile.sh --subscribe, remove watchdog.sh (PASS) |
 
 ---
 
@@ -100,4 +101,5 @@ a6f7c04 feat(delegate-job): bump default --timeout 600s -> 3600s (1h wall-clock
 
 ## Date
 
-2026-06-21 (Sun) 03:52 ~ 07:00 KST
+- 2026-06-21 (Sun) 03:52 ~ 07:00 KST (FW-01 ~ FW-16, FW-L1 ~ FW-L3, FW-N1 ~ FW-N7, Infra)
+- 2026-06-22 (Mon) 23:44 ~ KST (FW-W3)

FUTURE_WORKS.ko.md

@@ -1,18 +1,30 @@
 # FUTURE_WORKS.md
 
-> **목적**: `tmux_agent_orchestration` 프로젝트의 향후 작업 후보를 추적한다.
+> **목적**: `multi-agent-mux` 프로젝트의 향후 작업 후보를 추적한다.
 > 완료된 항목은 `DONE.ko.md`를 참조.
-> **최종 갱신**: 2026-06-21
+> **최종 갱신**: 2026-06-22
 
 ---
 
 ## 향후 개선 작업 로드맵
 
-현재 대기 중인 향후 작업(Future Works) 항목입니다. 본 항목들은 `Understand_Anything_Analysis.md` 보고서의 보안 및 동시성 분석을 바탕으로 제안되었습니다.
+현재 대기 중인 향후 작업(Future Works) 항목입니다. 본 항목들은 시스템의 보안, 동시성, 이식성 및 워크플로우 분석을 바탕으로 제안되었습니다.
 
 | ID | 과제명 | 우선순위 | 작업량 | 해결 분야 / 설명 | 의존성 |
 |---|---|---|---|---|---|
 | **FW-L4** | Job Registry의 SQLite 마이그레이션 및 NFS flock 한계 극복 | P3 (Low) | 대 | **동시성/인프라 확장성**: 세션 레지스트리와 마찬가지로 개별 JSON 파일 락(`fcntl.flock`) 방식의 잡 레지스트리를 SQLite 데이터베이스 트랜잭션 구조로 통합 마이그레이션하여, NFS 등 분산/네트워크 FS 환경에서의 안정성을 완전 확보 | **조건부** (실제 멀티 호스트/NFS 배포 필요 발생 시 착수) |
+| **FW-P1** | lib.sh 내 GNU/Linux 유저랜드 가정 제거 | P2 (Medium) | 소 | **이식성**: `lib.sh`에 포함된 GNU coreutils 전용 명령(`df --output=target` 및 리눅스 mount 포맷 분석)을 이식 가능한 명령어로 대체하여 macOS/BSD에서 NFS 감지가 자동 무력화되는 사각지대 해결 | 없음 |
+| **FW-P2** | 윈도우 환경을 위한 명시적인 동시성 제어 전략 제공 | P1 (High) | 중 | **이식성 / 동시성**: `fcntl`이 POSIX 전용이므로 `mqtt_common.py` 임포트 실패 시 예외가 발생하는 문제를 스타트업 시점에 감지하여 사용자 친화적 경고와 함께 조기 종료하게 하거나, 윈도우용 `msvcrt.locking` 등으로 락 메커니즘을 동적 매핑함. 이벤트 감사 로그를 기록하는 `_file_lock`은 설계 사양대로 best-effort(무영향) 속성을 유지함 | 없음 |
+| **FW-P3** | 가상환경(virtualenv) 로딩 및 의존성 사전 검증 강화 | P2 (Medium) | 중 | **이식성**: requirements.txt의 paho-mqtt 2.x 의존성 선언 외에, UV/Poetry 등 독립 툴 체인에서 가상환경 인터프리터 불일치를 조기 차단하고, 실행 진입점(entrypoint)에서 필수 라이브러리 탑재 여부를 즉시 검증하는 진단 로직 추가 | 없음 |
+| **FW-P4** | 기본 MQTT 브로커 및 네임스페이스 보안 강화 | P1 (High) | 중 | **이식성 / 보안**: 공용 브로커인 `broker.hivemq.com`과 열린 네임스페이스 대신, 사설 TLS 브로커 크레덴셜을 기본 템플릿으로 제공하여 원격 세션 탈취 및 도청 공격 위협 원천 방지 | 없음 |
+| **FW-P5** | zsh 환경 하에서의 BASH_SOURCE 경로 오작동 해결 | P2 (Medium) | 소 | **이식성**: zsh 쉘에서 `lib.sh`를 대화형으로 sourcing할 때 `${BASH_SOURCE[0]}`가 공백으로 평가되어 스킬 경로(`SKILL_DIR`)를 잘못 설정하는 오류 해결 | 없음 |
+| **FW-P6** | 마커 파일 조회를 통한 프로젝트 루트 동적 감지 | P1 (High) | 중 | **이식성**: `lib.sh`, `status.sh`, `reconcile.sh` 등 여러 스크립트에서 `../..` 등 상대 경로 깊이를 하드코딩하여 발생하는 취약성 해결. `.git`, `.mam`, `.env` 등을 찾는 상위 탐색 마커-파일 워크 방식을 적용하고, 단일한 `WORKSPACE_ROOT` 환경변수로 통일하여 오케스트레이션 안정성 확보 | 없음 |
+| **FW-P7** | 모니터 종료 경로에 대한 HMAC 서명 검증 및 활성 상태 체크 강화 | P1 (High) | 중 | **이식성 / 보안**: `reconcile.sh`가 `verify_hmac` 서명 검증 없이 `completed`/`error` 이벤트만으로 세션을 즉시 강제 종료하는 리스크 해결. 모니터링 이벤트 핸들러(`on_message`)에서 보안 토큰 검증을 필수 처리하고, `kill-session` 전 실제 tmux 활성 여부와 예상 아티팩트 보존 상태를 대조하게 설계 | 없음 |
+| **FW-W1** | 글로벌 레지스트리 락을 세밀한 락(Fine-grained locks)으로 대체 | P2 (Medium) | 중 | **동시성 / 확장성**: 모든 세션 및 progress/sequence 업데이트가 단일 `.mam/jobs/` 글로벌 fcntl lock을 거치며 생기는 병목 차단. 잡 단위의 개별 락 파일 도입 | 없음 |
+| **FW-W2** | 블라인드 TUI 키 입력 방지를 위한 실행 준비도 검증 | P2 (Medium) | 대 | **워크플로우**: 세션 생성, 재개, 중지 시 단순 sleep(예: 6초) 대신 터미널 스크린 스크랩이나 준비도 프로브(Readiness Probe)를 활용하여 다이얼로그나 예외 창을 안전하게 차단 | 없음 |
+| **FW-W4** | 구독자 시퀀스 번호(last_seq)의 디스크 영속화 | P1 (High) | 중 | **워크플로우 / 보안**: 와치독 재기동 시 시퀀스 카운터가 리셋되는 구조적 취약을 방지하기 위해 `subscriber.last_seq`를 디스크/DB에 기록하여 잡 라이프타임 전체를 커버하는 Replay 방어선 유지 | 없음 |
+| **FW-W5** | 리뷰어 판정을 위한 구조적 메시지 스키마 정의 | P2 (Medium) | 중 | **워크플로우**: PM 에이전트가 터미널 스크롤백 문자열을 무가공 grep 파싱하는 대신, 전용 리뷰 피드백 토픽(예: `reviews/<job_id>/verdicts`) 및 정형화된 JSON 포맷(`PASS`/`NOT_PASS` + 차단 요인) 도입 | 없음 |
+| **FW-W6** | 모니터링 복구 루프의 Hermes 에이전트 지원 확장 | P2 (Medium) | 중 | **워크플로우 / 일관성**: `reconcile.sh` 내 자동 등록(drift-B) 및 ID 동기화(drift-C) 로직에 `hermes` 세션을 완전 편입시켜 Claude/Agy 세션과 동일한 모니터링 및 복구 수준 지원 | 없음 |
 
 ---
 
@@ -20,3 +32,15 @@
 
 1. **SQLite 통합(FW-L4)의 조건부 연기**:
    * 세션 레지스트리와 달리 개별 잡 데이터는 JSON 파일 구조가 관리 및 디버깅 직관성이 우수하며, 현재 배포 환경은 단일 호스트 로컬 FS로 제한되어 있어 `fcntl.flock` 잠금만으로 안전하게 운용 가능하므로 낮은 우선순위(P3)로 배정하고 필요 시 착수합니다.
+
+2. **윈도우 환경을 위한 명시적인 동시성 제어 전략 제공 (FW-P1, FW-P2)**:
+   * 동시성 제어 시스템에서 오류 시 락 없이 그냥 실행되는 침묵형 오작동(Silent failover)은 가장 위험한 구조입니다. 윈도우 환경에서 `fcntl` 모듈 누락 시 묵인하지 않고 진입점에서 명시적인 조기 경고를 내어 POSIX 환경이나 전용 래퍼 실행을 유도하고, 혹은 `msvcrt.locking` 파일 제어 전략을 동적 매핑하여 플랫폼 전반의 안전성을 담보해야 합니다.
+
+3. **마커 파일을 통한 동적 루트 앵커링 (FW-P6)**:
+   * 하위 경로 탐색 시 특정 파일의 상대 경로 깊이(`../..` 등)에 의존하는 구조는 디렉터리 리팩토링이나 래퍼 이동 시 치명적 취약점으로 작용합니다. 디렉터리 트리를 따라 `.git`이나 `.mam` 등 알려진 루트 표시 마커를 동적으로 검색하는 방식을 채택하여 스크립트 실행 안정성과 이식 속도를 획기적으로 개선합니다.
+
+4. **모니터 종료 권한 제어 강화 (FW-P7)**:
+   * 세션 강제 종료(`tmux kill-session`) 권한은 안전하게 제어되어야 합니다. 모니터(`reconcile.sh`)가 와일드카드 토픽을 무검증 수신하여 즉시 세션을 정리하면 위조 주입 공격에 취약해집니다. 종료 이벤트 수신부에 HMAC 서명 검증을 의무화하고, 세션 강제 중지 전 예상되는 작업 결과물(Artifact) 존속 상태를 교차 검토하도록 설계합니다.
+
+5. **개별 잡 와치독의 단일 와일드카드 구독자 통합 (FW-W3)**:
+   * 매 잡마다 개별적으로 실행되어 2분 주기로 끊고 재연결하던 `watchdog.sh` 프로세스 방식 대신, 상시 기동되는 `reconcile.sh --subscribe` 단일 와일드카드 구독자 구조로 이벤트 처리, HMAC 보안 검증 및 시퀀스 추적 로직을 완전히 통일했습니다. 이를 통해 불필요한 MQTT 커넥션 급증을 원천 차단하고 세션 정리 과정을 간소화했으며, 메모리 캐시 기반 시퀀스 추적을 통해 Replay 공격 차단 정합성을 동시 실행 중인 모든 잡에 대해 안정적으로 제공합니다.

FUTURE_WORKS.md

@@ -1,18 +1,30 @@
 # FUTURE_WORKS.md
 
-> **Purpose**: Track future work candidates for the `tmux_agent_orchestration` project.
+> **Purpose**: Track future work candidates for the `multi-agent-mux` project.
 > For completed items, see `DONE.md`.
-> **Last Updated**: 2026-06-21
+> **Last Updated**: 2026-06-22
 
 ---
 
 ## Future Improvements Roadmap
 
-Below is the list of pending future work items. These items were proposed based on the security and concurrency analysis in the `Understand_Anything_Analysis.md` report.
+Below is the list of pending future work items. These items were proposed based on the security, concurrency, portability, and workflow analysis of the system.
 
 | ID | Task | Priority | Effort | Domain / Description | Dependencies |
 |---|---|---|---|---|---|
 | **FW-L4** | Migrate Job Registry to SQLite to overcome NFS flock limitations | P3 (Low) | Large | **Concurrency/Infrastructure Scalability**: Similar to the Session Registry, migrate the individual JSON file lock (`fcntl.flock`) registry structure into an integrated SQLite database transaction structure, guaranteeing full reliability in distributed/network file systems like NFS. | **Conditional** (commence only when multi-host/NFS deployment is required) |
+| **FW-P1** | Eliminate GNU/Linux userland assumptions in lib.sh | P2 (Medium) | Small | **Portability**: Replace GNU coreutils-specific commands (like `df --output=target` and Linux-specific mount formats) in `lib.sh` with portable equivalents, resolving silent failures of NFS detection on macOS/BSD. | None |
+| **FW-P2** | Add explicit Windows concurrency strategy in mqtt_common.py | P1 (High) | Medium | **Portability / Concurrency**: Detect non-POSIX systems at module initialization and either fail fast with a descriptive warning or substitute alternative lock strategies (e.g. `msvcrt.locking`), while preserving the best-effort nature of the `_file_lock` log appender. | None |
+| **FW-P3** | Align virtualenv loading and dependency verifications | P2 (Medium) | Medium | **Portability**: Prevent local interpreter mismatches in Poetry/UV environments and ensure the launch scripts fail early with clear diagnostic warnings if required Python dependencies are missing at startup. | None |
+| **FW-P4** | Secure default MQTT broker and namespaces | P1 (High) | Medium | **Portability / Security**: Prevent remote session hijack and eavesdropping by providing a private TLS-enabled broker template rather than defaulting to `broker.hivemq.com` in public namespaces. | None |
+| **FW-P5** | Resolve BASH_SOURCE path resolution under zsh | P2 (Medium) | Small | **Portability**: Fix `lib.sh` interactive sourcing issues under zsh shell where `${BASH_SOURCE[0]}` resolves to empty. | None |
+| **FW-P6** | Anchor project root dynamically via marker-file lookup | P1 (High) | Medium | **Portability**: Resolve structural fragility caused by hardcoded `../..` relative directory traversal in `lib.sh`, `status.sh`, and `reconcile.sh`. Use an upward search for root markers (`.git`, `.mam`, `.env`) to export a single source of truth for `WORKSPACE_ROOT`. | None |
+| **FW-P7** | Enforce HMAC verification and liveness checks on monitor termination | P1 (High) | Medium | **Portability / Security**: Prevent remote session killing by unauthorized or spoofed events. Integrate `verify_hmac` inside the monitor (`reconcile.sh`'s `on_message` handler) and confirm expected artifacts exist before executing `tmux kill-session`. | None |
+| **FW-W1** | Replace global registry lock with fine-grained locks | P2 (Medium) | Medium | **Concurrency / Scaling**: Eliminate throughput bottlenecks where all progress/sequence updates channel through a single fcntl lock on `.mam/jobs/`. Implement per-job lock files. | None |
+| **FW-W2** | Implement readiness probes for blind TUI key inputs | P2 (Medium) | Large | **Workflow**: Replace fixed timing sleeps in create, resume, and stop scripts with dynamic terminal readiness probes (e.g. scrapers or CLI checking hooks) to dismiss trust dialogs robustly. | None |
+| **FW-W4** | Persist subscriber sequence numbers alongside job records | P1 (High) | Medium | **Workflow / Security**: Persist `subscriber.last_seq` to disk or SQLite to prevent sequence counter reset on subscriber restart, locking down the replay defense window for the full job lifetime. | None |
+| **FW-W5** | Define structured message schema for reviewer verdicts | P2 (Medium) | Medium | **Workflow**: Create a dedicated reviewer topic (e.g., `reviews/<job_id>/verdicts`) emitting structured JSON verdicts (`PASS` / `NOT_PASS` + details) to eliminate raw text grepping by the PM. | None |
+| **FW-W6** | Expand monitor reconciliation support to Hermes agent | P2 (Medium) | Medium | **Workflow / Consistency**: Fully integrate `hermes` sessions into auto-registration (drift-B) and ID materialization (drift-C) under `reconcile.sh` to match Claude/Agy monitoring coverage. | None |
 
 ---
 
@@ -20,3 +32,15 @@ Below is the list of pending future work items. These items were proposed based
 
 1. **Conditional Deferral of SQLite Integration (FW-L4)**:
    * Unlike the session registry, maintaining individual job data in JSON files is highly intuitive for management and debugging. Since the current deployment is constrained to a single-host local file system, `fcntl.flock` locks are sufficient. Thus, this is assigned a low priority (P3) and will be tackled conditionally.
+
+2. **Explicit Concurrency Strategy on Windows (FW-P1, FW-P2)**:
+   * Silent failovers are the worst design patterns for concurrency. Instead of letting Windows environments run without a lock (which occurs when fcntl fails silently), we detect POSIX availability at startup. We either fail fast to prompt the user to use a POSIX-compliant shell/wrapper, or dynamically load `msvcrt.locking` to provide a matching file locking mechanism. This guarantees consistent synchronization behaviors across Windows and Unix platforms.
+
+3. **Dynamic Root Anchor (FW-P6)**:
+   * Hardcoding relative depth limits (like `../..` relative to a skill's location) creates direct fragility when moving directories or refactoring. By walking up the directory tree to search for known anchors (like `.git` or `.mam`), we establish a single canonical root path and prevent scripts from breaking when their execution wrappers are relocated.
+
+4. **Monitor Termination Authorization (FW-P7)**:
+   * Auto-termination must not trust unauthenticated events. Since `reconcile.sh` listens to a wildcard topic, any client on a public broker could spoof a terminal message and trigger `tmux kill-session`. Requiring HMAC signature verification on the terminal event path, combined with artifact validation, mitigates spoofing and accidental session cleanup.
+
+5. **Consolidation of per-job watchdogs (FW-W3)**:
+   * Instead of spawning an independent `watchdog.sh` process for each job which reconnects every 2 minutes, we consolidated the event handling, HMAC security verification, and sequence tracking into a single, persistent wildcard subscriber running under `reconcile.sh --subscribe`. This drastically reduces MQTT broker connections, simplifies cleanup logic, and leverages python's memory storage to handle replay attack prevention (monotonic sequence numbers) for concurrent jobs.

MESSAGING.md

@@ -1,6 +1,6 @@
 # Messaging System Technical Analysis & Architecture Report
 
-This report provides a comprehensive, deep-dive analysis of the messaging system implemented in the `tmux-agent-orchestrate-delegate-job` skill. It covers the MQTT broker architecture, event protocols, job lifecycles, codebase internals, cross-system integration, and a list of known limitations along with production recommendations.
+This report provides a comprehensive, deep-dive analysis of the messaging system implemented in the `multi-agent-mux-delegate-job` skill. It covers the MQTT broker architecture, event protocols, job lifecycles, codebase internals, cross-system integration, and a list of known limitations along with production recommendations.
 
 ---
 
@@ -183,8 +183,8 @@ stateDiagram-v2
 ### 3.1 Step-by-Step Lifecycle Phase Details
 
 #### Phase 1: Registration (`register`)
-* **Trigger**: A delegator triggers `registry.py register` (or the `tmux-agent-orchestrate-delegate-job submit` command).
+* **Trigger**: A delegator triggers `registry.py register` (or the `multi-agent-mux-delegate-job submit` command).
-* **Registry State**: Flips from non-existent to `pending` inside `.hermes/jobs/<job_id>.json`. A `last_seq` counter is initialized to `0`.
+* **Registry State**: Flips from non-existent to `pending` inside `.mam/jobs/<job_id>.json`. A `last_seq` counter is initialized to `0`.
 * **Locking**: Exclusive fcntl file lock acquired over `.lock` during write.
 * **Durable Audit Log**: Writes `<logs>/<job_id>/meta.json`, sets status to `pending` in `status.json`, and appends a `registered` event line to `events.ndjson`.
 
@@ -272,7 +272,7 @@ The delegated messaging system functions as a critical control backplane, bindin
 
 ```mermaid
 graph LR
-    User["User/Cron Client"] -->|submit| Wrap["tmux-agent-orchestrate-delegate-job (Bash)"]
+    User["User/Cron Client"] -->|submit| Wrap["multi-agent-mux-delegate-job (Bash)"]
     Wrap -->|registers| Reg["registry.py (Live Registry)"]
     Wrap -->|spawns background| Sub["job_subscriber.py"]
     Wrap -->|spawns tmux pane| Tmux["tmux Session (Agent Pane)"]
@@ -285,9 +285,9 @@ graph LR
     Mon -->|updates| Inv["agent-sessions.yaml <br> (lib.sh::atomic_dump_yaml)"]
 ```
 
-### 5.1 Orchestration Wrappers (`tmux-agent-orchestrate-*`)
+### 5.1 Orchestration Wrappers (`multi-agent-mux-*`)
-1. **`tmux-agent-orchestrate-delegate-job (submit)`**:
+1. **`multi-agent-mux-delegate-job (submit)`**:
-   * Registers a job, spawns `job_subscriber.py` to capture standard output streams to `.hermes/jobs/<job_id>.subscriber.out`, and sleeps for `1` second.
+   * Registers a job, spawns `job_subscriber.py` to capture standard output streams to `.mam/jobs/<job_id>.subscriber.out`, and sleeps for `1` second.
    * Boots the agent pane in tmux:
      ```bash
      tmux new-session -d -s "$sess" -c "$WORKDIR" \
@@ -295,10 +295,10 @@ graph LR
      ```
    * Pre-seeds agent instruction headers via stdin to enforce that the agent runs `publish_event.py` for its transitions.
    * Blocks on `wait $sub_pid`, and finally prints the audit log directory.
-2. **`tmux-agent-orchestrate-monitor` (`reconcile.sh` & `watchdog.sh`)**:
+2. **`multi-agent-mux-monitor` (`reconcile.sh`)**:
-   * **Watchdog Integration**: Starts a subscriber monitoring loop (`watchdog.sh`) to detect orphaned agent panes or locked workspaces.
+    * **Wildcard Monitor Integration**: Runs a unified background subscriber loop (`reconcile.sh --subscribe`) to capture progress, verify security tokens (HMAC) and sequences, write audit logs, and automatically clean up tmux sessions upon terminal events.
    * **Reconciliation loop**: Subscribes to the global job topic. On terminal events, it invokes `lib.sh::atomic_dump_yaml` to sync status drifts (e.g. setting tmux sessions to `terminated` in `agent-sessions.yaml` once the agent exits).
-3. **`tmux-agent-orchestrate-create / stop / resume`**:
+3. **`multi-agent-mux-create / stop / resume`**:
    * Integrates the job life status into session metadata updates, ensuring standard tmux cleanup triggers state updates in the registry and audit logs.
 
 ---
@@ -308,7 +308,7 @@ graph LR
 ### 6.1 Limitations
 
 1. **Single-Host File Locking Vulnerability**:
-   The advisory locking system previously relied heavily on `fcntl.flock`. While `agent-sessions.yaml` has been migrated to SQLite WAL to solve concurrent writes, the job metadata in `.hermes/jobs/` still relies on `fcntl.flock` which may behave non-atomically on NFS.
+   The advisory locking system previously relied heavily on `fcntl.flock`. While `agent-sessions.yaml` has been migrated to SQLite WAL to solve concurrent writes, the job metadata in `.mam/jobs/` still relies on `fcntl.flock` which may behave non-atomically on NFS.
 2. **Bearer Token Leakage over Plaintext (Public Broker)**:
    The `auth_token` mechanism is a simple plaintext bearer comparison. If the transport layer is unencrypted (e.g., using `broker.hivemq.com` on port `1883`), any eavesdropper on the network can steal the token and spoof legitimate events.
 3. **Subscriber Network Drop Orphanage**:
@@ -336,8 +336,8 @@ graph LR
 
 This project manages **two distinct state domains** that are often confused:
 
-### Session States (YAML — `.hermes/agent-sessions.yaml`)
+### Session States (YAML — `.mam/agent-sessions.yaml`)
-Managed by `skills/lib.sh` and the 6 `tmux-agent-orchestrate-*` skills.
+Managed by `.agents/skills/lib.sh` and the 6 `multi-agent-mux-*` skills.
 Valid values (see `lib.sh` valid-status set):
 
 | State | Meaning | Set by |
@@ -347,8 +347,8 @@ Valid values (see `lib.sh` valid-status set):
 | `terminated` | hard-killed via `--mode hard`; tmux session destroyed | `stop` (hard mode), `monitor` reconcile |
 | `archived` | soft-stopped via `--mode soft`; tmux left alive, YAML-only update | `stop` (soft mode) |
 
-### Job States (Registry — `.hermes/jobs/<id>.json`)
+### Job States (Registry — `.mam/jobs/<id>.json`)
-Managed by `skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py`.
+Managed by `.agents/skills/multi-agent-mux-delegate-job/scripts/registry.py`.
 Valid values:
 
 | State | Meaning | Set by |

README.ko.md

@@ -0,0 +1,193 @@
+# tmux-agent-orchestration (다중 에이전트 Tmux 오케스트레이션 및 메시징 백플레인)
+
+Tmux와 MQTT 브로커를 기반으로 구축된 고신뢰성 **다중 에이전트 오케스트레이션 및 메시징 백플레인** 프레임워크입니다. Claude, Hermes 등 다중 LLM 백엔드 에이전트 전반에 걸쳐 장시간 수행되는 작업(코드 생성, 리팩토링, 보안 검토 등)을 조정, 격리 및 감사할 수 있도록 설계되었습니다.
+
+---
+
+## 🚀 개요
+
+최근의 에이전트 워크플로우는 세션 타임아웃, 프로세스 격리 부재, 터미널 뷰포트 잘림(스크롤백 한계로 인한 디버그 로그 유실), 복잡한 동시성 경쟁 등의 문제를 자주 겪습니다.
+
+**tmux-agent-orchestration**은 다음과 같은 솔루션을 통해 이를 해결합니다:
+1. **Tmux 기반 프로세스 격리:** 개별적으로 격리된 tmux 환경 내부에 에이전트 CLI 세션을 띄워, 백그라운드에서 끊김 없이 장시간 작업이 영속되도록 보장합니다.
+2. **비동기 이벤트 기반 아키텍처:** MQTT 브로커를 메시징 백플레인으로 활용하여, 에이전트 간 상태 전이 단계(`started`, `progress`, `completed`, `error`)를 긴밀하게 제어 및 조정합니다.
+3. **Multi-Agent Mux (MAM):** 파일 기반의 어드바이저리 락(`fcntl`) 및 SQLite WAL 데이터베이스(`.mam/agent-sessions.db`)를 결합하여, 동시성 작업 선점 경쟁을 방지하고 에이전트 세션의 라이프사이클을 드리프트 없이 관리합니다.
+4. **리뷰어 기반 고신뢰 검증 루프:** Worker 에이전트가 구현한 코드 변경 사항에 대해 상이한 강점을 지닌 전문 검증 에이전트(예: 논리 흐름을 정밀 검토하는 Claude, 셸 문법 및 안전성을 빠르게 확인하는 Hermes)들로부터 최종 `PASS` 판정을 획득한 뒤 머지하도록 교차 검증 루프를 자동화합니다.
+
+---
+
+## 🛠️ 핵심 스킬 및 구조
+
+모든 오케스트레이션 스킬들은 `.agents/skills/` 디렉터리 하위에 정의되어 있습니다:
+
+*   **`multi-agent-mux-create`**: 격리된 tmux 세션을 생성하고 특정 에이전트 CLI를 백그라운드에서 구동합니다. 프로세스 PID 캡처, 메타데이터 레지스트리 업데이트 및 에이전트 인증 검증을 처리합니다.
+*   **`multi-agent-mux-stop`**: 에이전트 CLI 세션을 정상 종료 키 입력(`/exit` 또는 `Exit`)을 통해 안전하게 닫고, 격리된 대화 히스토리 및 데이터베이스 로그를 삭제(purge)하는 클린업 작업을 수행합니다.
+*   **`multi-agent-mux-resume`**: 디스크 또는 캐시에서 특정 워크스페이스의 세션 UUID를 조회하여 기존 대화 상태(`claude -r <uuid>` 또는 `hermes --resume <uuid>`) 그대로 세션을 복구하고 재개합니다.
+*   **`multi-agent-mux-status`**: 활성화된 모든 세션의 실시간 작동 상태를 쿼리하여 PID 정합성, 실행 명령 포맷, tmux 실제 상태와 데이터베이스 간의 동기화 드리프트를 감지합니다.
+*   **`multi-agent-mux-monitor`**: 백그라운드에서 Kanban Reconcile 프로세스로 실행되어, 실시간 tmux 세션 변화를 모니터링하고 `.mam/agent-sessions.yaml` 메타데이터 파일에 상태를 동기화합니다.
+*   **`multi-agent-mux-delegate-job`**: 태스크를 비동기식 독립 잡으로 위임 및 관리하는 핵심 모듈입니다:
+    *   `registry.py`: 파일 락(`fcntl`)을 활용해 경쟁 조건 없이 잡을 원자적으로 등록 및 점유(claim)합니다.
+    *   `job_subscriber.py`: MQTT 백플레인 채널을 구독하여 실시간 상태 이벤트를 수집하고 이를 감사 로그(audit trail)에 기록합니다.
+    *   `publish_event.py`: 실행 상태 전환 및 세부 에러 내용을 워크스페이스 스크립트에서 백플레인으로 발행합니다.
+    *   `mqtt_common.py`: 브로커 접속 규칙, 크레덴셜 인증 및 HMAC 서명 기능을 공통 관리합니다.
+
+---
+
+## 📐 전체 아키텍처 구성 (Big-Picture Architecture)
+
+이 시스템은 크게 두 가지 계층(Layer)을 통해 다중 워크스페이스에서 작동하는 LLM 에이전트들을 조율합니다:
+
+1. **Layer A — Tmux 오케스트레이션 (lib.sh + status/resume/stop/create)**: 워크스페이스별 에이전트 세션을 독립된 tmux 인스턴스로 분리 실행하고, `.mam/agent-sessions.yaml` 및 SQLite 데이터베이스(`.mam/agent-sessions.db`)를 통해 에이전트 세션 메타데이터의 단일 참조 지점(Single Source of Truth)을 유지합니다.
+2. **Layer B — 비동기 잡 위임 (delegate-job)**: 에이전트에 특정 태스크를 전송하고 비동기 이벤트 채널(MQTT)을 통해 진행 상황과 완료 여부를 모니터링합니다.
+
+두 레이어는 파일 I/O 처리를 위한 하나의 핵심 관문인 `lib.sh::atomic_dump_yaml`을 공유합니다. 모든 YAML/DB 쓰기 작업은 독점 파일 락(`flock`)과 데이터 스키마 유효성 검증을 거칩니다.
+
+### 데이터 흐름 개요 (Data Flow)
+
+```text
+  +-----------+   register_job    +-------------------+
+  | delegator | ---------------> | .mam/jobs/<id>.json|  <-- 실시간 잡 정보
+  +-----------+                   +---------+---------+
+                                                |
+                                                | atomic rename + fsync
+                                                v
+                                       +-----------------+
+                                       |   audit log     |  <-- 추가 전용
+                                       | .mam/delegate_  |      events.ndjson
+                                       |  job_logs/<id>/ |
+                                       +--------+--------+
+                                                ^
+                                                | (최선 노력 미러링)
+                                                |
+  +-----------+   publish_event    +-----+-----+      +---------+
+  |  agent    | ---------------> | MQTT broker | <--- | monitor |
+  | (claude)  |                   +-------------+      +----+----+
+  +-----------+                                            |
+       ^                                                  v
+       | 구독자(subscriber)                           atomic_dump_yaml
+       | (job_subscriber.py)                          (.mam/agent-sessions.yaml)
+       |                                                  ^
+       +-------- 위임 대기 영역 -----------------+        |
+                                                   +---+---+
+                                                   | reconcil|
+                                                   |  e.sh  |
+                                                   +--------+
+```
+
+### 🔒 Tmux 서버 격리 (Tmux Server Isolation)
+
+에이전트 세션 간의 충돌 및 시스템 전역 tmux 프로세스와의 혼선을 막기 위해 독립된 서버 소켓 환경을 보장합니다:
+*   **워크스페이스별 심(Shim):** `_init_tmux_isolation` 및 `_resolve_real_tmux_path` 함수가 `/tmp/multi-agent-tmux-shim/<TMUX_SERVER_NAME>/tmux` 경로에 독립된 심 디렉터리를 구성하고, 일반 tmux 명령 실행 시 자동으로 `tmux -L <server>` 형태의 독립 소켓 서버를 사용하게 만듭니다.
+*   **PATH 환경변수 변조:** 자식 프로세스를 생성할 때 `PATH` 변수 맨 앞에 심 디렉터리 경로를 삽입합니다. 이로 인해 에이전트의 내부 셸에서 수행되는 모든 `tmux` 명령어는 해당 격리 서버 소켓으로 강제 제약됩니다.
+*   **환경 복구:** `TMUX_SERVER_NAME`을 `default`로 설정하는 경우 PATH 오버라이드가 정리되고 기본 전역 tmux 서버를 사용하게 됩니다.
+
+### 🛡️ 동시성 설계 및 쓰기 직렬화
+
+여러 에이전트가 동시에 실행될 때의 레이스 컨디션을 방지하기 위해 락 기반의 실행 패턴을 고수합니다:
+*   **POSIX 파일 락 (`flock`):** `agent-sessions.yaml` 또는 SQLite 레지스트리에 쓰기 연산을 진행할 때, 반드시 `lib.sh` 내부의 `atomic_dump_yaml` 함수를 거쳐 `.mam/agent-sessions.yaml.lock` 파일에 독점 락(`flock`)을 획득하도록 직렬화합니다.
+*   **이중 인터프리터 분리 구조:** 라이브러리 간 의존성 충돌과 실행 도구의 안정성을 보장하기 위해 환경을 이원화했습니다. MQTT 및 비동기 작업 통신에는 가상환경 `.venv` (paho-mqtt 필요)의 Python을 사용하고, YAML 직렬화 쓰기 및 유효성 검증을 담당하는 `atomic_dump_yaml`은 시스템 전역 `python3` (시스템 PyYAML 필요)을 호출합니다.
+*   **NFS 및 네트워크 파일시스템 대응:** 네트워크 디바이스(NFS, CIFS, SSHFS)에서는 `flock`이 무력화되는 특성이 있습니다. `lib.sh`는 쓰기 대상 파일시스템 경로의 마운트 타입을 체크하여, 네트워크 파일시스템 감지 시 경고 로그를 출력하고 SQLite의 저널 모드를 `WAL`에서 `DELETE`로 자동 전환해 동시성 안전을 강화합니다.
+
+---
+
+## 📐 아키텍처 및 조정 루프 (Review Loop)
+
+Project Manager(PM), Worker, Reviewer 역할 간의 협업 구조는 엄격한 교차 검증 루프를 따릅니다:
+
+```mermaid
+sequenceDiagram
+    autonumber
+    actor User as User
+    participant PM as Project Manager
+    participant W as Worker
+    participant R as Reviewers
+    participant M as MQTT Backplane
+
+    User->>PM: 요구사항 전달
+    Note over PM: 태스크 수립 및 Job 등록
+    PM->>M: Job 등록 및 Subscriber 시작
+    PM->>W: 작업 위임 (Job ID 및 가이드 제공)
+    W->>M: 'started' 이벤트 발행
+    Note over W: 코드 변경 및 자체 검증 수행
+    W->>M: 'completed' (또는 'error') 발행
+    PM->>R: 병렬 리뷰 요청 (Diff 제공)
+    Note over R: 에이전트 교차 검증 (Claude, Hermes)
+    alt 리뷰 피드백 (NOT PASS)
+        R->>PM: NOT PASS (대안 코드 블록과 함께 피드백 전달)
+        Note over PM: PM 직접 수정 또는 다시 위임 결정
+        PM->>W: 리뷰 피드백 반영 재요청
+    else 검증 통과 (PASS)
+        R->>PM: PASS
+    end
+    PM->>User: 최종 머지 완료 보고 및 변경사항 커밋
+```
+
+---
+
+## 🔒 보안 프로토콜 및 Replay 공격 방어
+
+공용 MQTT 브로커 환경에서도 통신의 무결성을 보장하기 위해 **HMAC-SHA256 암호화 서명** 체계를 갖추고 있습니다:
+*   **PoC 모드 (무인증):** 기본 설정 모드로 `auth_token`이 `null`로 세팅되어 간단한 로컬 환경 검증 시 암호화 시그니처 체크를 건너뜁니다.
+*   **프로덕션 모드 (인증 필수):** 각 잡마다 무작위 암호화 토큰이 발급되며, 백플레인을 오가는 모든 페이로드에 토큰 기반으로 생성된 `hmac_sig` 서명을 탑재해야 수신측에서 수용합니다.
+*   **Replay 공격 방어:** 각 이벤트는 단조 증가하는 정수형 시퀀스 번호(`seq`)를 포함합니다. 구독자(`job_subscriber.py`)는 특정 잡에 대해 이미 수용한 최대 시퀀스 번호보다 크지 않은 시퀀스 번호를 가진 페이로드를 즉시 폐기합니다. 페이로드 바디에 대한 HMAC 서명과 결합하여, 이 메커니즘은 클록 동기화에 의존하지 않고 재전송(re-injected) 및 순서가 바뀐 패킷을 차단합니다. 메시지 내 타임스탬프 필드는 참고용 메타데이터이며, 백플레인은 시간 오차(clock-skew) 윈도우를 별도로 검증하지 않습니다.
+
+---
+
+## 📁 리포지토리 구성
+
+```text
+.
+├── .agents/
+│   └── skills/                  # 코어 오케스트레이션 셸 스크립트 및 라이브러리
+│       ├── lib.sh               # 공통 오케스트레이션 셸 함수 라이브러리
+│       ├── multi-agent-mux-create/
+│       ├── multi-agent-mux-stop/
+│       ├── multi-agent-mux-resume/
+│       ├── multi-agent-mux-status/
+│       ├── multi-agent-mux-monitor/
+│       └── multi-agent-mux-delegate-job/
+│           ├── requirements.txt # 파이썬 의존성 패키지 선언
+│           └── scripts/         # 파이썬 기반 백플레인 구현체
+├── .mam/                        # Multi-Agent Mux 메타데이터 (git-ignored)
+│   ├── agent-sessions.db        # SQLite WAL 세션 데이터베이스
+│   ├── agent-sessions.yaml      # 텍스트 형식의 세션 레지스트리 스냅샷
+│   └── jobs/                    # 비동기 잡 메타데이터 JSON 파일들
+├── scripts/
+│   └── generate-env.sh          # 환경 파일(.env) 템플릿 복사 스크립트
+├── AGENT.ko.md                  # 에이전트 역할 행동 강령 (한국어 백업)
+├── AGENT.md                     # 에이전트 역할 행동 강령 및 뷰포트 스냅샷 규칙
+├── BOOTSTRAP.ko.md              # 프로젝트 초기 설치 가이드 (한국어 백업)
+├── BOOTSTRAP.md                 # 프로젝트 초기 설치 및 검증 상세 가이드
+├── MESSAGING.md                 # MQTT 메시징 프로토콜 와이어 규격서
+└── README.md                    # 프로젝트 대표 소개 파일
+```
+
+---
+
+## 🚦 빠른 시작
+
+자세한 빌드 절차는 **[BOOTSTRAP.md](./BOOTSTRAP.md)** 문서를 참조하십시오. 아래는 간략한 요약입니다:
+
+1.  **환경 설정 파일(.env) 생성:**
+    ```bash
+    ./scripts/generate-env.sh
+    ```
+2.  **가상환경 생성 및 의존성 패키지 설치:**
+    ```bash
+    python3 -m venv .venv
+    source .venv/bin/activate
+    pip install -r .agents/skills/multi-agent-mux-delegate-job/requirements.txt
+    ```
+3.  **레지스트리 및 환경 작동 자가 검증:**
+    ```bash
+    .venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py list
+    ```
+
+---
+
+## 📝 협업 에이전트 준수 사항
+
+이 프로젝트에 새로 합류한 에이전트는 다음 규칙을 준수해야 합니다:
+1.  **[AGENT.md](./AGENT.md)** 문서를 정독하여 프로젝트 매니저(PM), 작업자(Worker), 리뷰어(Reviewer) 간의 역할 및 개발 제약조건을 인지하십시오.
+2.  장시간 명령을 실행하는 경우 터미널 스크롤백 로그 유실을 방지하기 위해 `AGENT.md` (제4장)에 기재된 **뷰포트 스냅샷 규칙(Pane Snapshotting Rules)**을 반드시 적용하십시오.
+3.  리뷰어 세션에 diff 검증을 요청하기 전에는 어떠한 코어 파일의 임의 수정도 프로덕션 브랜치에 승인 없이 머지할 수 없습니다.

README.md

@@ -1 +1,191 @@
-# README.md
+# tmux-agent-orchestration
+
+An advanced, high-reliability **Multi-Agent Orchestration & Messaging Backplane** framework built on Tmux and MQTT. It is designed to coordinate, isolate, and audit long-running agent tasks (such as code generation, refactoring, and security reviews) across multiple LLM backend clients (e.g., Claude, Hermes).
+
+---
+
+## 🚀 Overview
+
+Modern agentic workflows often suffer from session timeout, lack of process isolation, terminal viewport truncation (scrollback limits), and complex concurrency issues. 
+
+**tmux-agent-orchestration** addresses these problems by providing:
+1. **Tmux-based Process Isolation:** Spawning LLM client sessions inside dedicated, isolated tmux environments to support persistent background runs.
+2. **Asynchronous Event-Driven Architecture:** Leveraging an MQTT broker as a message backplane to coordinate state transitions (`started`, `progress`, `completed`, `error`) between collaborating agents.
+3. **Multi-Agent Mux (MAM):** Combining local file-based locks (fcntl) and an ACID-compliant SQLite WAL database (`.mam/agent-sessions.db`) to manage concurrent job claims and track running agent sessions without drift.
+4. **Automated Review & Quality Loop:** Implementing parallel reviewer loops where worker agents must receive a `PASS` rating from various specialized verification agents (e.g., Claude for high-level logic, Hermes for shell syntax/safety) before merging code.
+
+---
+
+## 🛠️ Core Skills & Scaffolding
+
+All orchestration functionalities are structured under the `.agents/skills/` directory:
+
+*   **`multi-agent-mux-create`**: Spawns isolated tmux sessions running specified agent CLI wrappers. It captures system processes, updates metadata registries, and enforces authentication checks.
+*   **`multi-agent-mux-stop`**: Gracefully terminates agent CLI sessions (using key macros like `/exit` or `Exit`) and handles disk purge operations (removing conversation JSON files and SQLite logs for deleted workspaces).
+*   **`multi-agent-mux-resume`**: Restores stopped sessions by resolving workspace UUIDs from disk or cache, and invokes the underlying agent using session-resume parameters (e.g., `claude -r <uuid>` or `hermes --resume <uuid>`).
+*   **`multi-agent-mux-status`**: Queries the running states of all active sessions, detecting PID mismatches, command signatures, and drifts between actual tmux instances and the registry database.
+*   **`multi-agent-mux-monitor`**: A long-running Kanban reconcile worker that dynamically monitors tmux sessions and synchronizes states to `.mam/agent-sessions.yaml`.
+*   **`multi-agent-mux-delegate-job`**: The core asynchronous task distribution module containing:
+    *   `registry.py`: Atomically registers and claims jobs using file advisory locks (`fcntl`).
+    *   `job_subscriber.py`: Connects to the MQTT backplane, captures live events, and appends them to audit trails.
+    *   `publish_event.py`: Emits execution status transitions and error details from workspace scripts.
+    *   `mqtt_common.py`: Manages connection policies, authentication, and HMAC signing.
+
+---
+
+## 📐 Big-Picture Architecture
+
+The system coordinates LLM agents across multiple workspaces through two core layers:
+
+1. **Layer A — Tmux Orchestration (lib.sh + status/resume/stop/create)**: Runs the agents (one tmux session per agent-workspace combination) and maintains an authoritative registry in `.mam/agent-sessions.yaml` (+ `.mam/agent-sessions.db`).
+2. **Layer B — Async Job Delegation (delegate-job)**: Dispatches a task to an agent and observes progress and completion via an event channel.
+
+These two layers share one lock-guarded chokepoint for file I/O: `lib.sh::atomic_dump_yaml`. Every write is protected by an exclusive `flock` and schema validation.
+
+### Data Flow Overview
+
+```text
+  +-----------+   register_job    +-------------------+
+  | delegator | ---------------> | .mam/jobs/<id>.json|  <-- live record
+  +-----------+                   +---------+---------+
+                                                |
+                                                | atomic rename + fsync
+                                                v
+                                       +-----------------+
+                                       |   audit log     |  <-- append-only
+                                       | .mam/delegate_  |      events.ndjson
+                                       |  job_logs/<id>/ |
+                                       +--------+--------+
+                                                ^
+                                                | (best-effort mirrors)
+                                                |
+  +-----------+   publish_event    +-----+-----+      +---------+
+  |  agent    | ---------------> | MQTT broker | <--- | monitor |
+  | (claude)  |                   +-------------+      +----+----+
+  +-----------+                                            |
+       ^                                                  v
+       | subscriber                                   atomic_dump_yaml
+       | (job_subscriber.py)                          (.mam/agent-sessions.yaml)
+       |                                                  ^
+       +-------- delegator waits here ----------+        |
+                                                  +---+---+
+                                                  | reconcil|
+                                                  |  e.sh  |
+                                                  +--------+
+```
+
+### 🔒 Tmux Server Isolation
+
+To prevent workspace tmux processes from interfering with each other or with system tmux servers, the framework enforces isolated tmux environments:
+*   **Per-Workspace Shim:** `_init_tmux_isolation` and `_resolve_real_tmux_path` instantiate a per-workspace shim directory under `/tmp/multi-agent-tmux-shim/<TMUX_SERVER_NAME>/tmux` that intercepts tmux commands and wraps them in `tmux -L <server>`.
+*   **PATH Rewriting:** The `PATH` environment variable is dynamically prepended with the shim path in all child processes. This ensures any `tmux` invocation within the agent's process tree is restricted to its isolated socket server.
+*   **Environment Restoration:** If `TMUX_SERVER_NAME` is set to `default`, the PATH override is removed, reverting to the default global tmux server.
+
+### 🛡️ Concurrency Design & Write Serialization
+
+The framework implements lock-guarded execution pathways to prevent race conditions during parallel agent operations:
+*   **POSIX File Locks (`flock`):** Every mutation of `agent-sessions.yaml` and the SQLite registry runs through `atomic_dump_yaml` inside `lib.sh`, which serializes writes via an exclusive `flock` on `.mam/agent-sessions.yaml.lock`.
+*   **Dual-Interpreter Strategy:** To minimize dependency bloat and guarantee stability, the backplane splits execution environments: the virtual environment `.venv` handles MQTT communication and async jobs (requiring `paho-mqtt`), while the system `python3` executes `atomic_dump_yaml` (relying on system-wide `PyYAML`).
+*   **NFS and Network FS Safeguards:** Since `flock` behaves unreliably over network protocols (NFS, CIFS, SSHFS), `lib.sh` performs filesystem detection. If a network mount is identified, it outputs a safety warning and SQLite automatically switches its journaling mode from `WAL` to `DELETE`.
+
+---
+
+## 📐 Architecture & Coordination Loop
+
+The interaction between roles (Project Manager, Worker, and Reviewer) is structured as a strict iterative loop:
+
+```mermaid
+sequenceDiagram
+    autonumber
+    actor User as User
+    participant PM as Project Manager
+    participant W as Worker
+    participant R as Reviewers
+    participant M as MQTT Backplane
+
+    User->>PM: Hand over requirements
+    Note over PM: Plan tasks & register jobs
+    PM->>M: Register Job & start Subscriber
+    PM->>W: Delegate task (Provide Job ID & Brief)
+    W->>M: Publish 'started' event
+    Note over W: Implement & verify code
+    W->>M: Publish 'completed' (or 'error')
+    PM->>R: Request parallel reviews (Provide Diff)
+    Note over R: Parallel analysis (Claude, Hermes)
+    alt Review Feedback (NOT PASS)
+        R->>PM: NOT PASS (Feedback with code blocks)
+        Note over PM: Apply fixes or re-delegate
+        PM->>W: Re-delegate with comments
+    else Verification PASS
+        R->>PM: PASS
+    end
+    PM->>User: Commit changes & Report completion
+```
+
+---
+
+## 🔒 Security & Replay Attack Defense
+
+To ensure communication integrity across public MQTT brokers, the backplane integrates an **HMAC-SHA256 signature protocol**:
+*   **PoC Mode (Unauthenticated):** Default mode where `auth_token` is `null`, skipping cryptographic validations for quick setups.
+*   **Production Mode (Authenticated):** A unique cryptographic token is issued per job. Event payloads must include an `hmac_sig` computed with the token.
+*   **Replay Attack Mitigation:** Each event carries a monotonically increasing integer sequence counter (`seq`). The subscriber (`job_subscriber.py`) drops any payload whose sequence number is not strictly greater than the highest sequence number it has already accepted for that job. Combined with the HMAC signature on the payload body, this rejects both re-injected and out-of-order packets without relying on clock synchronization. The wire-format timestamp field is advisory metadata only; the backplane does not enforce a clock-skew window.
+
+---
+
+## 📁 Repository Layout
+
+```text
+.
+├── .agents/
+│   └── skills/                  # Core orchestration shell wrappers & libraries
+│       ├── lib.sh               # Shared orchestration library
+│       ├── multi-agent-mux-create/
+│       ├── multi-agent-mux-stop/
+│       ├── multi-agent-mux-resume/
+│       ├── multi-agent-mux-status/
+│       ├── multi-agent-mux-monitor/
+│       └── multi-agent-mux-delegate-job/
+│           ├── requirements.txt # Python dependency declaration
+│           └── scripts/         # Core backplane implementation (Python)
+├── .mam/                        # Multi-Agent Mux metadata (git-ignored)
+│   ├── agent-sessions.db        # SQLite WAL session database
+│   ├── agent-sessions.yaml      # Human-readable session registry
+│   └── jobs/                    # Asynchronous job metadata files
+├── scripts/
+│   └── generate-env.sh          # Environment bootstrap helper
+├── AGENT.md                     # Agent roles, snapshottings, and execution charter
+├── BOOTSTRAP.md                 # Detailed installation and verification guide
+├── MESSAGING.md                 # MQTT wire protocol specification
+└── README.md                    # Project introduction and overview (this file)
+```
+
+---
+
+## 🚦 Quick Start
+
+For detailed setup instructions, please consult the **[BOOTSTRAP.md](./BOOTSTRAP.md)** file. Below is a quick summary:
+
+1.  **Initialize Environment Config:**
+    ```bash
+    ./scripts/generate-env.sh
+    ```
+2.  **Create Virtual Environment and Install Dependencies:**
+    ```bash
+    python3 -m venv .venv
+    source .venv/bin/activate
+    pip install -r .agents/skills/multi-agent-mux-delegate-job/requirements.txt
+    ```
+3.  **Run Registry Diagnostics:**
+    ```bash
+    .venv/bin/python3 .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py list
+    ```
+
+---
+
+## 📝 Guidelines for Collaborating Agents
+
+If you are an AI agent newly onboarded to this project:
+1.  Read **[AGENT.md](./AGENT.md)** to align on development constraints and roles (PM, Worker, Reviewer).
+2.  Adhere to the **Pane Snapshotting Rules** in `AGENT.md` (Section 4) to prevent scrollback data loss during long execution steps.
+3.  Never modify core logic without submitting a diff to the reviewer sessions for evaluation.

deploy/README.md

@@ -0,0 +1,52 @@
+# 🚀 Multi-Agent Mux (MAM) Deployment & Gitea Integration
+
+This directory contains packaging templates and installation scripts to deploy the **Multi-Agent Mux** framework into workspaces hosted on **Gitea** (or GitHub).
+
+---
+
+## 📁 Deployment Directory Structure
+
+*   **`install.sh`**: A self-contained, idempotent shell installer that checks system requirements (`tmux`, `python3`, `pip3`), detects NFS/network filesystem mounts, sets up a local python virtual environment (`.venv`), and initializes environment configuration (`.env`).
+*   **`plugin.json`**: Metadata declaration file to register MAM as an installable plugin for AI Agent coding platforms (such as Claude Code, Antigravity, or other TUI clients).
+*   **`gitea-ci.yml`**: CI/CD pipeline definition template for Gitea Actions (running ShellCheck linting on bash scripts, validation on python scripts, and compilation tests).
+
+---
+
+## 📦 How to Install and Deploy
+
+### 1. Simple One-Liner Installation (from Gitea repository)
+Once you push this repository to your Gitea instance, users can install it in their local workspace directory by running:
+
+```bash
+curl -fsSL https://<your-gitea-domain>/<username>/multi-agent-mux/raw/branch/main/deploy/install.sh | bash
+```
+
+Alternatively, if they have cloned the repository, they can execute:
+```bash
+bash deploy/install.sh
+```
+
+### 2. Registering as a Workspace Plugin
+To register these skills globally or for a specific workspace:
+*   **Workspace Level**: Copy the `.agents/` folder into your project root.
+*   **Global Level (Gemini/Antigravity)**: Register the plugin path in your global config file at `~/.gemini/config/skills.json`:
+    ```json
+    {
+      "entries": [
+        { "path": "/absolute/path/to/multi-agent-mux/.agents/skills" }
+      ]
+    }
+    ```
+
+---
+
+## 🤖 Gitea Actions CI/CD Setup
+
+To automate testing and script linting on your Gitea repository:
+1. Ensure Gitea Actions is enabled on your Gitea instance.
+2. Copy the Gitea CI workflow to your workspace's workflow folder:
+   ```bash
+   mkdir -p .gitea/workflows
+   cp deploy/gitea-ci.yml .gitea/workflows/ci.yml
+   ```
+3. Commit and push to your Gitea repository. The pipeline will validate shell syntax and python file compilation on every push to `main` and pull requests.

deploy/gitea-ci.yml

@@ -0,0 +1,70 @@
+# ==============================================================================
+# Gitea Actions CI/CD Workflow Template
+# ==============================================================================
+# Place this file in '.gitea/workflows/ci.yml' or use it directly in Gitea's CI.
+# It automatically validates shell scripts and checks Python formatting/syntax.
+# ==============================================================================
+name: Multi-Agent Mux CI
+
+on:
+  push:
+    branches: [ main, dev ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint-shell:
+    name: Lint Shell Scripts
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Install ShellCheck
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y shellcheck
+
+      - name: Run ShellCheck
+        run: |
+          echo "🔍 Linting shell scripts..."
+          shellcheck .agents/skills/lib.sh
+          shellcheck .agents/skills/multi-agent-mux-create/scripts/create_session.sh
+          shellcheck .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh
+          shellcheck .agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh
+          shellcheck deploy/install.sh
+          echo "✅ ShellCheck completed successfully."
+
+  lint-python:
+    name: Lint Python Backplane
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pylint
+          if [ -f .agents/skills/multi-agent-mux-delegate-job/requirements.txt ]; then
+            pip install -r .agents/skills/multi-agent-mux-delegate-job/requirements.txt
+          fi
+
+      - name: Run Flake8 (Syntax/Error Check)
+        run: |
+          echo "🔍 Checking Python syntax with flake8..."
+          flake8 .agents/skills/multi-agent-mux-delegate-job/scripts/ --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 .agents/skills/multi-agent-mux-delegate-job/scripts/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+      - name: Run Python Syntax Check (Compile test)
+        run: |
+          echo "🔍 Verifying Python file compilation..."
+          python -m py_compile .agents/skills/multi-agent-mux-delegate-job/scripts/*.py
+          echo "✅ All Python files compiled successfully."

deploy/install.sh

@@ -0,0 +1,130 @@
+#!/usr/bin/env bash
+# ==============================================================================
+# install.sh — Multi-Agent Mux (MAM) Orchestration Installer
+# ==============================================================================
+# Idempotent, robust installer to bootstrap MAM orchestration skills
+# and Python backplane dependencies on any local workspace.
+# ==============================================================================
+set -euo pipefail
+
+# --- Configuration & Defaults ---
+TARGET_DIR="${1:-$(pwd)}"
+VENV_NAME=".venv"
+MIN_PYTHON_VERSION="3.9"
+
+echo "===================================================================="
+echo "⚡ Starting Multi-Agent Mux (MAM) Installation"
+echo "📂 Target Workspace: $TARGET_DIR"
+echo "===================================================================="
+
+# --- 1. System Requirements Validation ---
+echo "🔍 Checking system dependencies..."
+
+check_cmd() {
+  local cmd="$1"
+  if ! command -v "$cmd" &>/dev/null; then
+    echo "❌ Error: '$cmd' is not installed. Please install it first." >&2
+    exit 1
+  fi
+}
+
+check_cmd tmux
+check_cmd python3
+
+# Verify Python Version
+PYTHON_VERSION=$(python3 -c 'import sys; print(f"{sys.version_info.major}.{sys.version_info.minor}")')
+PYTHON_MAJOR="${MIN_PYTHON_VERSION%%.*}"
+PYTHON_MINOR="${MIN_PYTHON_VERSION##*.}"
+if python3 -c "import sys; exit(0 if sys.version_info >= ($PYTHON_MAJOR, $PYTHON_MINOR) else 1)"; then
+  echo "✅ Python $PYTHON_VERSION detected."
+else
+  echo "❌ Error: Python version must be $MIN_PYTHON_VERSION or higher. Detected: $PYTHON_VERSION" >&2
+  exit 1
+fi
+
+# --- 2. Workspace Setup ---
+cd "$TARGET_DIR"
+echo "📂 Ensuring metadata directory structure (.mam/)..."
+mkdir -p .mam/jobs .mam/delegate_job_logs
+
+# File permission lockdown on database directory (if owned by the current user to prevent multi-user system issues)
+if [ -O .mam ]; then
+  chmod 0700 .mam
+fi
+
+# --- 3. Check Network File System (NFS) Warnings ---
+echo "💾 Detecting file system mount type..."
+if command -v df &>/dev/null && command -v mount &>/dev/null; then
+  MOUNTPOINT="$(df --output=target . 2>/dev/null | tail -1 || echo "")"
+  if [ -n "$MOUNTPOINT" ]; then
+    if mount | grep -q "$MOUNTPOINT.*nfs\|$MOUNTPOINT.*cifs\|$MOUNTPOINT.*fuse.sshfs"; then
+      echo "⚠️  WARNING: Target directory is on a network filesystem (NFS/CIFS/SSHFS)."
+      echo "   File locks (fcntl.flock) are UNRELIABLE on network storage."
+      echo "   The sqlite3 registry will fall back to 'DELETE' journaling instead of WAL."
+    else
+      echo "✅ File system supports WAL (Local storage detected)."
+    fi
+  fi
+fi
+
+# --- 4. Python Virtual Environment Setup ---
+echo "🐍 Bootstrapping Python virtual environment (.venv)..."
+if [ ! -d "$VENV_NAME" ]; then
+  python3 -m venv "$VENV_NAME"
+  echo "✅ Virtual environment created."
+else
+  echo "ℹ️  Virtual environment (.venv) already exists. Skipping creation."
+fi
+
+# Activate virtual environment
+# shellcheck disable=SC1091
+source "$VENV_NAME"/bin/activate
+
+# Upgrade pip
+pip install --upgrade pip
+
+# Install requirements
+REQ_FILE=".agents/skills/multi-agent-mux-delegate-job/requirements.txt"
+if [ -f "$REQ_FILE" ]; then
+  echo "📦 Installing backplane dependencies from $REQ_FILE..."
+  pip install -r "$REQ_FILE"
+  echo "✅ Dependencies installed successfully."
+else
+  echo "⚠️  WARNING: Could not find requirements file: $REQ_FILE"
+  echo "   Installing default packages (paho-mqtt, pyyaml) manually..."
+  pip install "paho-mqtt>=2.0.0" pyyaml
+fi
+
+# --- 5. Generate Environment Template ---
+ENV_FILE=".env"
+ENV_EXAMPLE=".env.example"
+if [ ! -f "$ENV_FILE" ]; then
+  if [ -f "$ENV_EXAMPLE" ]; then
+    echo "📝 Creating configuration from $ENV_EXAMPLE..."
+    cp "$ENV_EXAMPLE" "$ENV_FILE"
+  else
+    echo "📝 Creating default $ENV_FILE..."
+    touch "$ENV_FILE"
+  fi
+  
+  # Always append the active defaults to ensure they are set and not commented out
+  cat <<EOF >> "$ENV_FILE"
+
+# === Installer-applied active defaults ===
+MQTT_BROKER=broker.hivemq.com
+MQTT_PORT=1883
+MQTT_TLS=0
+MQTT_CLIENT_ID_PREFIX=mam-agent
+TMUX_SERVER_NAME=default
+EOF
+  chmod 0600 "$ENV_FILE"
+  echo "✅ Config file .env initialized with chmod 0600."
+else
+  echo "ℹ️  $ENV_FILE already exists. Skipping config override."
+fi
+
+echo "===================================================================="
+echo "🎉 Installation complete!"
+echo "✨ You can now run the status or monitor skills."
+echo "💡 Hint: Try executing: .venv/bin/python .agents/skills/multi-agent-mux-delegate-job/scripts/registry.py list"
+echo "===================================================================="

deploy/plugin.json

@@ -0,0 +1,5 @@
+{
+  "name": "multi-agent-mux",
+  "description": "Multi-Agent Orchestration & Messaging Backplane on Tmux & MQTT.",
+  "disabled": false
+}

skills/tmux-agent-orchestrate-delegate-job/README.md

@@ -1,11 +0,0 @@
-# tmux-agent-orchestrate-delegate-job 스킬
-
-작업(Job)을 자율 에이전트(claude-code/codex/opencode/human)에게 위임하고 MQTT
-이벤트 채널로 비동기 관찰하는 Hermes 스킬. **시작점은 [`SKILL.md`](./SKILL.md).**
-
-- 프로토콜/스키마: [`job-protocol.md`](./job-protocol.md)
-- 브로커 PoC→운영 전환: [`mqtt-broker-setup.md`](./mqtt-broker-setup.md)
-- 레지스트리 포맷/동시성: [`registry.md`](./registry.md)
-- 참조 구현: [`tmux-agent-orchestrate-delegate-job`](./tmux-agent-orchestrate-delegate-job) (bash wrapper), [`scripts/publish_event.py`](./scripts/publish_event.py), [`scripts/job_subscriber.py`](./scripts/job_subscriber.py), [`scripts/registry.py`](./scripts/registry.py), [`scripts/mqtt_common.py`](./scripts/mqtt_common.py)
-- 영구 감사 로그: `.hermes/delegate_job_logs/<job_id>/` (`meta.json`·`events.ndjson`·`status.json`)
-  — `tmux-agent-orchestrate-delegate-job logs <id>` 또는 `tmux-agent-orchestrate-delegate-job logs --list`로 조회 (SKILL.md "Audit Logs" 참조)

skills/tmux-agent-orchestrate-monitor/scripts/watchdog.sh

@@ -1,65 +0,0 @@
-#!/usr/bin/env bash
-# watchdog.sh — tmux-agent-orchestrate-monitor 의 부속 스크립트
-#
-# Metadata for SKILL.md:
-# description: "Watchdog helper that keeps subscriber alive and exits when JOB is done"
-# usage: "watchdog.sh <job_id> <workdir> [--help]"
-
-if [ "${1:-}" = "--help" ] || [ "${1:-}" = "-h" ] || [ $# -lt 2 ]; then
-  echo "Usage: $0 <job_id> <workdir>"
-  exit 0
-fi
-
-JOB_ID="$1"
-WORKDIR="$2"
-LOG_DIR="$WORKDIR/.hermes/jobs"
-
-mkdir -p "$LOG_DIR"
-
-log() {
-  echo "[$(date -u +'%Y-%m-%dT%H:%M:%SZ')] $*"
-}
-
-log "watchdog started for JOB=$JOB_ID workdir=$WORKDIR"
-
-while true; do
-  # 1) Get current job status with robust Python parsing
-  STATUS=$(cd "$WORKDIR" && .venv/bin/python skills/tmux-agent-orchestrate-delegate-job/scripts/registry.py get --job "$JOB_ID" 2>/dev/null | python3 -c '
-import sys, json
-try:
-    data = json.load(sys.stdin)
-    print(data.get("status", "unknown"))
-except Exception:
-    print("unknown")
-' 2>/dev/null || echo "unknown")
-
-  log "JOB status: $STATUS"
-
-  # 2) Terminal check
-  case "$STATUS" in
-    completed|error|permission_required)
-      log "JOB reached terminal state ($STATUS), watchdog exiting"
-      exit 0
-      ;;
-  esac
-
-  # 3) Start subscriber (2min hard limit)
-  LOG_FILE="$LOG_DIR/subscriber-${JOB_ID}-$(date +%s).log"
-  log "starting subscriber (2min hard limit, log: $LOG_FILE)"
-
-  (
-    cd "$WORKDIR" && timeout 120 .venv/bin/python skills/tmux-agent-orchestrate-delegate-job/scripts/job_subscriber.py \
-      --job "$JOB_ID" --timeout 120 --idle-timeout 999999 --registry-dir .hermes/jobs > "$LOG_FILE" 2>&1
-    echo "[$(date -u +'%Y-%m-%dT%H:%M:%SZ')] subscriber exited" >> "$LOG_FILE"
-  ) &
-
-  SUB_PID=$!
-  log "subscriber PID=$SUB_PID"
-
-  # 4) Wait for subscriber to exit or timeout
-  wait $SUB_PID 2>/dev/null
-  EXIT_CODE=$?
-  log "subscriber exited code=$EXIT_CODE"
-
-  sleep 1
-done