fix(skills): claude review items 4-7 (subscribe timeout, atomic_dump_yaml, hardcoded paths, lifecycle helper)

Item 4: --subscribe gains --timeout/--idle-timeout (idle default raised
        120s->600s, 0=disable); connect-error AND non-zero CONNACK now fall
        back to a polling loop. SKILL.md matches actual behaviour.
Item 5: --subscribe terminal-event YAML writes routed through
        lib.sh::atomic_dump_yaml (flock + schema-validate + .bak).
Item 6: removed hardcoded /home/godopu16/PuKi fallbacks in lib.sh,
        status.sh (x2) and reconcile.sh; paths now BASH_SOURCE-relative.
Item 7: lib.sh::delegate_publish_event helper consolidates the 4 duplicated
        lifecycle publish blocks; delete cwd|jid parser replaced with JSON.

Also: subscribe loop runs under the project venv python (paho) and delegates
all YAML work to atomic_dump_yaml on system python3 (PyYAML), since neither
interpreter has both modules — the original env_python path could never import
paho. Items 3 + 8 out of scope (per user). Verified on -L claude-phase4-test
(kill-server after).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

skills/agent-sessions-monitor/SKILL.md

@@ -94,16 +94,20 @@ The worker calls this script every 30s. It:
 
 ```bash
 # Reconcile + auto-update YAML (atomic, flock-guarded). Emits JSON drift to stdout.
-bash ~/PuKi/lab/agent_sessions/skills/agent-sessions-monitor/scripts/reconcile.sh --once --emit-diff
+bash skills/agent-sessions-monitor/scripts/reconcile.sh --once --emit-diff
 
 # Read-only: compute drift WITHOUT writing the YAML (use for "what's running?" checks).
-bash ~/PuKi/lab/agent_sessions/skills/agent-sessions-monitor/scripts/reconcile.sh --once --emit-diff --dry-run
+bash skills/agent-sessions-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.
-bash ~/PuKi/lab/agent_sessions/skills/agent-sessions-monitor/scripts/reconcile.sh --subscribe
+# Bounded run that exits after 5 min idle, or 1 h wall-clock; falls back to polling if the broker is down.
+bash skills/agent-sessions-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/agent-sessions-monitor/scripts/reconcile.sh --subscribe --idle-timeout 0
 ```
 
-Flags: `--once` (single pass), `--emit-diff` (print JSON), `--dry-run` (P1-E — no mutation), `--subscribe` (persistent push-based MQTT subscription monitoring; falls back to polling if connection fails). There are **no** `--workspace` / `--agent` / `--comment-card` flags; the worker turns the emitted JSON `drifts[]` into `kanban_comment` calls itself.
+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 `600`, `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.
 
 ## Drift classes (what the script handles)
 

skills/agent-sessions-monitor/scripts/reconcile.sh

@@ -22,6 +22,11 @@ ONCE=0
 EMIT_DIFF=0
 DRY_RUN=0
 SUBSCRIBE=0
+# --subscribe controls (review item 4): 0 = no overall timeout; idle default 600s
+# (raised from the old hardcoded 120s); idle 0 = never idle-out.
+SUB_TIMEOUT=0
+SUB_IDLE_TIMEOUT=600
+POLL_INTERVAL="${RECONCILE_POLL_INTERVAL:-15}"
 
 while [ $# -gt 0 ]; do
   case "$1" in
@@ -29,7 +34,9 @@ while [ $# -gt 0 ]; do
     --emit-diff) EMIT_DIFF=1; shift ;;
     --dry-run) DRY_RUN=1; shift ;;
     --subscribe) SUBSCRIBE=1; shift ;;
-    -h|--help) echo "Usage: $0 [--once] [--emit-diff] [--dry-run] [--subscribe]"; exit 0 ;;
+    --timeout) SUB_TIMEOUT="$2"; shift 2 ;;
+    --idle-timeout) SUB_IDLE_TIMEOUT="$2"; shift 2 ;;
+    -h|--help) echo "Usage: $0 [--once] [--emit-diff] [--dry-run] [--subscribe [--timeout N] [--idle-timeout N]]"; exit 0 ;;
     *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
   esac
 done
@@ -37,122 +44,176 @@ done
 [ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }
 
 if [ "$SUBSCRIBE" = "1" ]; then
-  SUBSCRIBE_MODE=1 env_python "$AGENT_SESSIONS_YAML" <<'PYEOF'
+  # Paths resolved relative to this script (review item 6): skills/ dir + lib.sh.
-import os, sys, json, fcntl, tempfile, subprocess
+  SKILLS_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
-from datetime import datetime, timezone
+  LIB_SH="$SKILLS_DIR/lib.sh"
-import yaml
+  # MQTT client lives in the project venv (has paho). All YAML work is delegated
+  # to lib.sh::atomic_dump_yaml, which runs the system python3 (has PyYAML) — so
+  # no single interpreter needs both paho and PyYAML (review items 4/5/6).
+  PYBIN="$(_delegate_py_bin)"
 
-yaml_path = os.environ['YAML_PATH']
+  # The MQTT subscribe loop exits 3 to signal "broker unavailable → poll instead".
-home = os.environ['HOME_DIR']
+  set +e
+  YAML_PATH="$AGENT_SESSIONS_YAML" HOME_DIR="$HOME" \
+    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
 
-# Add skills/delegate-job/scripts to path to import mqtt_common
+lib_sh = os.environ.get('LIB_SH', '')
-script_dir = os.path.dirname(os.path.abspath(__file__)) if '__file__' in globals() else os.getcwd()
+skills_dir = os.environ.get('SKILLS_DIR', '')
-path_candidate = os.path.join('/home/godopu16/PuKi/laa/canary_projects/advanced_multi_agent', 'skills', 'delegate-job', 'scripts')
+timeout = int(os.environ.get('SUB_TIMEOUT', '0') or '0')          # 0 = no overall timeout
-if os.path.isdir(path_candidate):
+idle_timeout = int(os.environ.get('SUB_IDLE_TIMEOUT', '600') or '0')  # 0 = no idle timeout
-    sys.path.append(path_candidate)
+
+# Locate skills/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, 'delegate-job', 'scripts') if skills_dir else ''
+if cand and os.path.isdir(cand):
+    sys.path.append(cand)
 else:
-    d = script_dir
+    d = os.getcwd()
-    found = False
+    while d and d != '/':
-    while d != '/' and d:
+        hit = None
-        p = os.path.join(d, 'skills', 'delegate-job', 'scripts')
+        for sub in (('skills', 'delegate-job', 'scripts'), ('delegate-job', 'scripts')):
+            p = os.path.join(d, *sub)
             if os.path.isdir(p):
-            sys.path.append(p)
+                hit = p
-            found = True
                 break
-        p2 = os.path.join(d, 'delegate-job', 'scripts')
+        if hit:
-        if os.path.isdir(p2):
+            sys.path.append(hit)
-            sys.path.append(p2)
-            found = True
             break
         d = os.path.dirname(d)
 
 import mqtt_common
 
-cfg = mqtt_common.broker_config_from_env()
+# Executed INSIDE lib.sh::atomic_dump_yaml (system python3 + PyYAML), under the
-client = mqtt_common.make_client("monitor_sub", cfg)
+# YAML flock with schema-validate + .bak (review item 5). Marks matching running
+# sessions terminated and kills their tmux (review item 3 behaviour preserved),
+# or aborts the write entirely when nothing matches. The untrusted MQTT job id /
+# event arrive via env (MQTT_JID / MQTT_EVENT) — never spliced into source (P1-B).
+_MUTATION = r'''
+import os, subprocess
+from datetime import datetime, timezone
+_jid = os.environ['MQTT_JID']
+_event = os.environ['MQTT_EVENT']
+_now = datetime.now(timezone.utc)
+_changed = False
+for s in d.get('tmux_sessions', []):
+    if s.get('delegate_job_id') == _jid and s.get('status') == 'running':
+        s['status'] = 'terminated'
+        s['terminated_at'] = _now.strftime('%Y-%m-%dT%H:%M:%SZ')
+        s['terminated_at_epoch'] = int(_now.timestamp())
+        s['termination_mode'] = 'auto-detected (MQTT ' + _event + ')'
+        _name = s.get('name')
+        _srv = s.get('tmux_server') or 'default'
+        _cmd = ['tmux'] + (['-L', _srv] if _srv != 'default' else []) + ['kill-session', '-t', _name]
+        subprocess.run(_cmd, capture_output=True)
+        print('MQTT Monitor: terminated + killed ' + str(_name) + ' on ' + str(_srv), flush=True)
+        _changed = True
+if not _changed:
+    raise SystemExit(0)  # nothing matched — skip the write entirely
+'''
 
-def on_message(client, userdata, msg):
+
+def handle_terminal(jid, event):
+    if not lib_sh or not os.path.isfile(lib_sh):
+        print('MQTT Monitor: lib.sh not found, cannot update YAML', flush=True)
+        return
+    env = dict(os.environ)
+    env['MQTT_JID'] = jid
+    env['MQTT_EVENT'] = event
+    cmd = ['bash', '-c',
+           'source "$LIB_SH"; atomic_dump_yaml "$YAML_PATH" MQTT_JID="$MQTT_JID" MQTT_EVENT="$MQTT_EVENT"']
+    r = subprocess.run(cmd, input=_MUTATION, text=True, env=env, capture_output=True)
+    if (r.stdout or '').strip():
+        print(r.stdout.strip(), flush=True)
+    if r.returncode != 0 and (r.stderr or '').strip():
+        print('MQTT Monitor: atomic_dump_yaml stderr: ' + r.stderr.strip(), flush=True)
+
+
+state = {'last_msg': time.time(), 'connected': False, 'failed': False}
+
+
+def on_message(_client, _userdata, msg):
+    state['last_msg'] = time.time()
     try:
         payload = json.loads(msg.payload.decode("utf-8"))
         jid = payload.get("job_id")
         event = payload.get("event")
-        if not jid or not event:
+        if jid and event in ("completed", "error"):
-            return
-        
-        if event in ("completed", "error"):
             print(f"MQTT Monitor: received terminal event {event} for job {jid}", flush=True)
-            update_session_by_job(jid, event)
+            handle_terminal(jid, event)
     except Exception as e:
         print(f"MQTT Monitor error parsing message: {e}", flush=True)
 
-def update_session_by_job(jid, event):
-    lock_path = yaml_path + '.lock'
-    lock_fh = open(lock_path, 'w')
-    fcntl.flock(lock_fh, fcntl.LOCK_EX)
-    try:
-        if os.path.exists(yaml_path):
-            with open(yaml_path) as f:
-                d_local = yaml.safe_load(f) or {}
-        else:
-            d_local = {}
-        
-        sessions = d_local.setdefault('tmux_sessions', [])
-        updated = False
-        for s in sessions:
-            if s.get('delegate_job_id') == jid and s.get('status') == 'running':
-                s['status'] = 'terminated'
-                now_iso = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
-                s['terminated_at'] = now_iso
-                s['terminated_at_epoch'] = int(datetime.now(timezone.utc).timestamp())
-                s['termination_mode'] = f"auto-detected (MQTT {event})"
-                name = s.get('name')
-                srv = s.get('tmux_server') or 'default'
-                kill_tmux_session(name, srv)
-                updated = True
-        
-        if updated:
-            dir_ = os.path.dirname(yaml_path) or '.'
-            fd, tmp = tempfile.mkstemp(dir=dir_, prefix='.agent-sessions.', suffix='.tmp')
-            try:
-                with os.fdopen(fd, 'w') as f:
-                    yaml.safe_dump(d_local, f, default_flow_style=False, sort_keys=False,
-                                   allow_unicode=True, width=4096)
-                os.replace(tmp, yaml_path)
-                print(f"MQTT Monitor: updated YAML for job {jid} to terminated", flush=True)
-            except Exception as e:
-                if os.path.exists(tmp):
-                    os.remove(tmp)
-                print(f"MQTT Monitor error writing YAML: {e}", flush=True)
-    finally:
-        fcntl.flock(lock_fh, fcntl.LOCK_UN)
-        lock_fh.close()
-
-def kill_tmux_session(name, srv):
-    try:
-        cmd = ['tmux']
-        if srv != 'default':
-            cmd += ['-L', srv]
-        cmd += ['kill-session', '-t', name]
-        subprocess.run(cmd, capture_output=True)
-        print(f"MQTT Monitor: killed tmux session {name} on server {srv}", flush=True)
-    except Exception as e:
-        print(f"MQTT Monitor error killing tmux: {e}", flush=True)
-
-client.on_message = on_message
 
 def on_connect(_c, _u, _flags, reason_code, _props):
     rc = mqtt_common.reason_code_value(reason_code)
     if rc == 0:
+        state['connected'] = True
         _c.subscribe("python/mqtt/jobs/+/events", qos=1)
         print("MQTT Monitor: subscribed to python/mqtt/jobs/+/events", flush=True)
     else:
-        print(f"MQTT Monitor connection failed: {rc}", flush=True)
+        state['failed'] = True
+        print(f"MQTT Monitor connection failed: rc={rc}", flush=True)
 
+
+cfg = mqtt_common.broker_config_from_env()
+client = mqtt_common.make_client("monitor_sub", cfg)
+client.on_message = on_message
 client.on_connect = on_connect
 print(f"MQTT Monitor: connecting to {cfg.host}:{cfg.port} (TLS={cfg.tls})...", flush=True)
+
+# Connection failure → fall back to polling (review item 4).
+try:
     client.connect(cfg.host, cfg.port, cfg.keepalive)
-client.loop_forever()
+except Exception as e:
+    print(f"MQTT Monitor: connect failed ({e}); falling back to polling", flush=True)
+    sys.exit(3)
+
+client.loop_start()
+_wait = time.time()
+while time.time() - _wait < 5 and not state['connected'] and not state['failed']:
+    time.sleep(0.1)
+if not state['connected']:
+    print("MQTT Monitor: broker did not accept connection; falling back to polling", flush=True)
+    client.loop_stop()
+    sys.exit(3)
+
+start = time.time()
+try:
+    while True:
+        now = time.time()
+        if timeout and (now - start) >= timeout:
+            print(f"MQTT Monitor: --timeout {timeout}s reached, exiting", flush=True)
+            break
+        if idle_timeout and (now - state['last_msg']) >= idle_timeout:
+            print(f"MQTT Monitor: --idle-timeout {idle_timeout}s reached, exiting", flush=True)
+            break
+        time.sleep(0.5)
+finally:
+    client.loop_stop()
+    try:
+        client.disconnect()
+    except Exception:
+        pass
+sys.exit(0)
 PYEOF
+  sub_rc=$?
+  set -e
+
+  if [ "$sub_rc" = "3" ]; then
+    echo "MQTT Monitor: broker unavailable — falling back to polling (interval ${POLL_INTERVAL}s)" >&2
+    _self="$SKILLS_DIR/agent-sessions-monitor/scripts/reconcile.sh"
+    _start=$(date +%s)
+    while :; do
+      bash "$_self" --once --emit-diff >/dev/null 2>&1 || true
+      if [ "$SUB_TIMEOUT" != "0" ] && [ "$(( $(date +%s) - _start ))" -ge "$SUB_TIMEOUT" ]; then
+        break
+      fi
+      sleep "$POLL_INTERVAL"
+    done
+  fi
   exit 0
 fi
 

skills/lib.sh

@@ -362,37 +362,66 @@ PYEOF
 }
 
 # ---------------------------------------------------------------------------
-# delegate_submit_job <prompt> <agent> <agent_session>
+# delegate-job integration helpers
 #
-# Register a job in the delegate-job registry. Auto-detects the virtualenv python
+# All paths are resolved relative to lib.sh's own location (BASH_SOURCE), so the
-# and prints the new JID on stdout.
+# skill tree is relocatable — no hardcoded absolute paths (review item 6).
 # ---------------------------------------------------------------------------
-delegate_submit_job() {
-  local prompt="$1" agent="$2" session="$3"
-  local skill_dir
-  skill_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
-  local py_bin="python3"
+# _delegate_py_bin — echo the virtualenv python (walk up from skills/), else python3.
-  local d="$skill_dir"
+_delegate_py_bin() {
+  local d
+  d="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
   while [ "$d" != "/" ] && [ -n "$d" ]; do
     if [ -x "$d/.venv/bin/python" ]; then
-      py_bin="$d/.venv/bin/python"
+      printf '%s\n' "$d/.venv/bin/python"; return 0
-      break
     fi
     d="$(dirname "$d")"
   done
+  printf '%s\n' "python3"
+}
 
-  local registry_py="$skill_dir/delegate-job/scripts/registry.py"
+# _delegate_script <name> — echo the path to a delegate-job script, resolved
-  if [ ! -f "$registry_py" ]; then
+# relative to skills/ (lib.sh dir). Empty if not found.
-    registry_py="$(find "$skill_dir" -name "registry.py" | head -n 1 || echo "")"
+_delegate_script() {
-  fi
+  local name="$1" skill_dir cand
+  skill_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+  cand="$skill_dir/delegate-job/scripts/$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 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 "$registry_py" ]; then
-    registry_py="/home/godopu16/PuKi/laa/canary_projects/advanced_multi_agent/skills/delegate-job/scripts/registry.py"
+    echo "ERROR: delegate-job registry.py not found under skills/" >&2
+    return 1
   fi
-
   "$py_bin" "$registry_py" register \
     --prompt "$prompt" \
     --agent "$agent" \
     --agent-session "$session"
 }
 
+# delegate_publish_event <job_id> <event> [detail]
+#
+# Publish a lifecycle event to the 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.
+delegate_publish_event() {
+  local job_id="$1" event="$2" detail="${3:-}"
+  [ -n "$job_id" ] || return 0
+  local py_bin pub
+  py_bin="$(_delegate_py_bin)"
+  pub="$(_delegate_script publish_event.py)"
+  [ -n "$pub" ] && [ -f "$pub" ] || return 0
+  "$py_bin" "$pub" --job "$job_id" --event "$event" --detail "$detail" || true
+}
+

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

@@ -262,17 +262,7 @@ 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: $DELEGATE_JOB_ID"
-  py_bin="python3"
+  delegate_publish_event "$DELEGATE_JOB_ID" started "canary session created"
-  d_dir="$(dirname "${BASH_SOURCE[0]}")"
-  while [ "$d_dir" != "/" ] && [ -n "$d_dir" ]; do
-    if [ -x "$d_dir/.venv/bin/python" ]; then
-      py_bin="$d_dir/.venv/bin/python"
-      break
-    fi
-    d_dir="$(dirname "$d_dir")"
-  done
-  pub_script="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/delegate-job/scripts/publish_event.py"
-  "$py_bin" "$pub_script" --job "$DELEGATE_JOB_ID" --event started --detail "canary session created" || true
 fi
 echo "agent-sessions.yaml updated"
 echo

skills/multi-agent-delete/scripts/delete_session.sh

@@ -61,9 +61,10 @@ if [ -z "$AGENT" ]; then
   esac
 fi
 
-# 세션이 YAML 에 있는지 + 해당 row 의 워크스페이스 cwd 및 delegate_job_id 추출
+# 세션이 YAML 에 있는지 + 해당 row 의 워크스페이스 cwd 및 delegate_job_id 추출.
+# JSON 으로 emit — cwd 에 '|' 가 들어가도 안전 (review item 7; 기존 cwd|jid 파서 대체).
 MAPPED_DATA=$(env_python "$AGENT_SESSIONS_YAML" SESSION_NAME="$SESSION_NAME" <<'PYEOF'
-import os, yaml
+import os, json, yaml
 name = os.environ['SESSION_NAME']
 with open(os.environ['YAML_PATH']) as f:
     d = yaml.safe_load(f) or {}
@@ -71,7 +72,7 @@ for s in d.get('tmux_sessions', []):
     if s.get('name') == name:
         cwd = (s.get('pane') or {}).get('cwd', '')
         jid = s.get('delegate_job_id', '') or ''
-        print(f"{cwd}|{jid}")
+        print(json.dumps({"cwd": cwd, "job_id": jid}))
         raise SystemExit(0)
 raise SystemExit(7)
 PYEOF
@@ -80,8 +81,8 @@ PYEOF
   exit 1
 }
 
-TARGET_CWD="${MAPPED_DATA%|*}"
+TARGET_CWD=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("cwd",""))')
-DELEGATE_JOB_ID="${MAPPED_DATA#*|}"
+DELEGATE_JOB_ID=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("job_id",""))')
 
 # purge 확인
 if [ "$PURGE" = "1" ] && [ "$YES" != "1" ]; then
@@ -109,19 +110,7 @@ if tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
   LAST_STATUS=$(tmux capture-pane -t "$SESSION_NAME" -p -S -10 2>/dev/null | tr '\n' ' ' | head -c 500 || true)
 fi
 
-if [ -n "$DELEGATE_JOB_ID" ]; then
+delegate_publish_event "$DELEGATE_JOB_ID" progress "terminating"
-  py_bin="python3"
-  d_dir="$(dirname "${BASH_SOURCE[0]}")"
-  while [ "$d_dir" != "/" ] && [ -n "$d_dir" ]; do
-    if [ -x "$d_dir/.venv/bin/python" ]; then
-      py_bin="$d_dir/.venv/bin/python"
-      break
-    fi
-    d_dir="$(dirname "$d_dir")"
-  done
-  pub_script="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/delegate-job/scripts/publish_event.py"
-  "$py_bin" "$pub_script" --job "$DELEGATE_JOB_ID" --event progress --detail "terminating" || true
-fi
 
 # hard 모드면 tmux 죽임
 if [ "$MODE" = "hard" ] && [ "$TMUX_ALIVE" = "1" ]; then
@@ -206,19 +195,7 @@ elif purge and not purge_uuid:
 print(f"updated: {name} status={target['status']}", flush=True)
 PYEOF
 
-if [ -n "$DELEGATE_JOB_ID" ]; then
+delegate_publish_event "$DELEGATE_JOB_ID" completed "session terminated"
-  py_bin="python3"
-  d_dir="$(dirname "${BASH_SOURCE[0]}")"
-  while [ "$d_dir" != "/" ] && [ -n "$d_dir" ]; do
-    if [ -x "$d_dir/.venv/bin/python" ]; then
-      py_bin="$d_dir/.venv/bin/python"
-      break
-    fi
-    d_dir="$(dirname "$d_dir")"
-  done
-  pub_script="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/delegate-job/scripts/publish_event.py"
-  "$py_bin" "$pub_script" --job "$DELEGATE_JOB_ID" --event completed --detail "session terminated" || true
-fi
 
 echo
 echo "=== delete complete ==="

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

@@ -118,16 +118,4 @@ snap.pop('terminated_at_epoch', None)
 print(f"updated: {name} status=running (resume id -> per-row own id)", flush=True)
 PYEOF
 
-if [ -n "$DELEGATE_JOB_ID" ]; then
+delegate_publish_event "$DELEGATE_JOB_ID" progress "resumed"
-  py_bin="python3"
-  d_dir="$(dirname "${BASH_SOURCE[0]}")"
-  while [ "$d_dir" != "/" ] && [ -n "$d_dir" ]; do
-    if [ -x "$d_dir/.venv/bin/python" ]; then
-      py_bin="$d_dir/.venv/bin/python"
-      break
-    fi
-    d_dir="$(dirname "$d_dir")"
-  done
-  pub_script="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/delegate-job/scripts/publish_event.py"
-  "$py_bin" "$pub_script" --job "$DELEGATE_JOB_ID" --event progress --detail "resumed" || true
-fi

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

@@ -24,7 +24,11 @@ if [ "$JSON" = "1" ]; then
   exit 0
 fi
 
-DRIFT_JSON="$DRIFT_JSON" env_python "$AGENT_SESSIONS_YAML" <<'PYEOF'
+# Project root (parent of skills/) holds the delegate-job .hermes registry.
+# Resolved relative to this script — no hardcoded absolute path (review item 6).
+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
 import yaml
 
@@ -65,8 +69,15 @@ def get_job_status(s):
     if not jid:
         return ('-', '-')
 
-    # Try workspace relative
+    project_root = os.environ.get('PROJECT_ROOT', '.')
-    path = os.path.join('.hermes', 'jobs', f"{jid}.json")
+    # 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(project_root, '.hermes', 'jobs', f"{jid}.json"),
+        os.path.join(project_root, '.hermes', 'delegate_job_logs', jid, 'status.json'),
+    ]
+    for path in candidates:
         if os.path.exists(path):
             try:
                 with open(path) as jf:
@@ -75,26 +86,6 @@ def get_job_status(s):
             except Exception:
                 pass
 
-    # Try fixed absolute path of registry
-    path_fixed = os.path.join('/home/godopu16/PuKi/laa/canary_projects/advanced_multi_agent', '.hermes', 'jobs', f"{jid}.json")
-    if os.path.exists(path_fixed):
-        try:
-            with open(path_fixed) as jf:
-                job_data = json.load(jf)
-            return (jid, job_data.get('status', 'unknown'))
-        except Exception:
-            pass
-
-    # Try audit log status.json
-    path_audit = os.path.join('/home/godopu16/PuKi/laa/canary_projects/advanced_multi_agent', '.hermes', 'delegate_job_logs', jid, 'status.json')
-    if os.path.exists(path_audit):
-        try:
-            with open(path_audit) as jf:
-                job_data = json.load(jf)
-            return (jid, job_data.get('status', 'unknown'))
-        except Exception:
-            pass
-
     return (jid, 'unknown')