Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automa...
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automa...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Lightweight pull-based daemon that monitors sub-agent health. Writes a status file every N seconds. The heartbeat handler reads it โ no push, no noise.
overseer.sh (bash, runs in background) โโโ /proc/<pid> โ gateway alive? CPU? threads? โโโ openclaw sessions list โ sub-agent count + ages โโโ find -newer marker โ filesystem activity โโโ writes /tmp/overseer/status.json (atomic mv) heartbeat (agent, every 3min) โโโ reads /tmp/overseer/status.json โ summarize or HEARTBEAT_OK Key principle: The overseer does all data collection. The heartbeat handler does zero tool calls if the status file is fresh and healthy.
setsid scripts/overseer.sh \ --workdir /path/to/repo \ --interval 180 \ --max-stale 4 \ --voice \ &>/dev/null &
cat /tmp/overseer/status.json
FieldMeaningsubagents.countActive sub-agent sessionssubagents.details[].staleConsecutive cycles with no filesystem changessubagents.details[].statusactive / idle / warning / stuckgateway.health.aliveIs openclaw-gateway running?filesystem.changes_since_lastFiles modified since last check
stale countTimeStatusAction0-10-3 minactive/idleNormal2-36-9 minwarningVoice alert (if --voice)โฅ4โฅ12 minstuckAgent should investigate/kill
When HEARTBEAT.md fires: Read /tmp/overseer/status.json โ if missing or stale (>10 min), restart overseer If subagents.count == 0 for 2+ cycles โ overseer auto-exits โ reply HEARTBEAT_OK If all agents active โ brief one-line status โ HEARTBEAT_OK If any stuck โ report which labels are stuck โ consider killing via subagents kill Never cache a previous heartbeat response. Always read the status file fresh.
FlagDefaultDescription--interval180Seconds between checks--workdircwdDirectory to watch for file changes--labels(all)Comma-separated labels to filter--max-stale4Cycles before marking stuck--voiceoffLocal TTS alerts via jarvis command
Gateway health: Reads /proc/<pid>/status for CPU, memory, threads, FD count. Pure kernel data. Sub-agent list: Single openclaw sessions list call per cycle. Parses grep output. Filesystem diff: find -newer marker โ detects any file writes in the workdir. Status file: JSON written atomically (write to temp, mv into place). Any reader sees a complete file. Self-exit: If no sub-agents for 2 consecutive cycles, the overseer stops itself. Dedup: flock ensures only one overseer instance runs at a time.
Overseer: $0.00 (bash + /proc + one CLI call per cycle) Voice alerts: $0.00 (local sherpa-onnx via jarvis) Heartbeat reads status file: $0.00 (one cat command) Only cost is the heartbeat model itself (qwen3 local = free)
agent-superpowers โ the three-agent review pipeline that Overseer was built to monitor smart-model-router โ auto-select models for each sub-agent role ๐ https://github.com/globalcaos/tinkerclaw Clone it. Fork it. Break it. Make it yours.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.