feat(tmux-agent-orchestrate-monitor): integrate watchdog pattern as skill

Moved /tmp/subscriber-watchdog.sh → skills/tmux-agent-orchestrate-monitor/scripts/watchdog.sh
(skill-managed lifecycle, no longer lives outside workspace).

Added lib.sh::start_watchdog() helper:
- Spawns watchdog as background nohup process
- Writes watchdog log to .hermes/jobs/<JID>.watchdog.log
- Returns watchdog PID via stdout

Wired create_session.sh --submit-job to auto-start watchdog after JOB registration.

Fixes:
- Bug: registry.py get first-line parse was fragile (empty status → infinite loop)
  → Now uses python3 json.load for robust parsing
- Bug: old path skills/delegate-job/scripts/job_subscriber.py hardcoded
  → Now uses skills/tmux-agent-orchestrate-delegate-job/scripts/job_subscriber.py

Verified on isolated server -L agy-watchdog-skill-test (kill-server after):
- Syntax check PASS
- E2E: register job → start watchdog → publish completed → watchdog exits
- Global skill non-interference verified
- Main isolated server -L multi-agent-canary untouched

skills/lib.sh

@@ -425,3 +425,25 @@ delegate_publish_event() {
   "$py_bin" "$pub" --job "$job_id" --event "$event" --detail "$detail" || true
 }
 
+# start_watchdog <job_id> [workdir]
+# Spawns a watchdog process to monitor a delegate-job JOB in the background.
+# The watchdog re-spawns the subscriber every 2 minutes (or whatever hard
+# limit we set) and exits automatically when the JOB reaches terminal state.
+# Returns the watchdog PID via stdout.
+start_watchdog() {
+  local job_id="$1"
+  local workdir="${2:-$PWD}"
+  local watchdog_script="$workdir/skills/tmux-agent-orchestrate-monitor/scripts/watchdog.sh"
+  local log_file="$workdir/.hermes/jobs/${job_id}.watchdog.log"
+  
+  if [ ! -x "$watchdog_script" ]; then
+    echo "ERROR: watchdog not found or not executable: $watchdog_script" >&2
+    return 1
+  fi
+  
+  nohup "$watchdog_script" "$job_id" "$workdir" > "$log_file" 2>&1 &
+  local pid=$!
+  echo "$pid"
+}
+
+

skills/tmux-agent-orchestrate-create/scripts/create_session.sh

@@ -263,6 +263,8 @@ echo "tmux session: $SESSION_NAME (pane pid $PANE_PID, cmd $PANE_CMD, cwd $PANE_
 if [ -n "$DELEGATE_JOB_ID" ]; then
   echo "delegate job: $DELEGATE_JOB_ID"
   delegate_publish_event "$DELEGATE_JOB_ID" started "tmux-agent-orchestrate session created"
+  WD_PID=$(start_watchdog "$DELEGATE_JOB_ID" "$WORKSPACE")
+  echo "watchdog PID: $WD_PID"
 fi
 echo "agent-sessions.yaml updated"
 echo

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

@@ -0,0 +1,65 @@
+#!/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