forge-heartbeat
Skill2 starsChanged 7 days agoMITView on GitHub
Use when a multi-agent run feels stalled: finds the silent agent.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- ForgeyClap/claude-forgeedited, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- ForgeyClap/claude-forge★ 296% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository99 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- claude-md-improverSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- forge-a11ySkill
- forge-agent-reportSkill
- forge-agentSkill
- forge-apiSkill
- forge-authSkill
- forge-autoresearchSkill
- forge-botsSkill
- forge-brainstormSkill
- forge-cliSkill
- forge-cmsSkill
- forge-code-reviewSkill
- forge-contextSkill
- forge-councilSkill
- forge-craftSkill
- forge-databaseSkill
- forge-dataSkill
- forge-debugSkill
- forge-deeplearnSkill
- forge-devopsSkill
- forge-docdriftSkill
- forge-doctorSkill
- forge-ecc-adapterSkill
- forge-ecommerceSkill
- forge-electronSkill
- forge-extensionSkill
- forge-figmaSkill
- forge-fullstackSkill
- forge-gameSkill
- forge-graded-verifySkill
- forge-guardianSkill
- forge-i18n-docsSkill
- forge-intakeSkill
- forge-integrationSkill
- forge-long-form-writingSkill
- forge-mcp-clientsSkill
- forge-memorySkill
- forge-migrationSkill
- forge-mindmapSkill
- forge-mlopsSkill
- forge-mobileSkill
- forge-n8nSkill
- forge-nightshiftSkill
- forge-observabilitySkill
- forge-paymentsSkill
- forge-plan-largeSkill
- forge-prdSkill
- forge-predictionSkill
- forge-projectbrainSkill
- forge-prompt-coachSkill
- forge-qualitySkill
- forge-ragSkill
- forge-registrySkill
- forge-releaseSkill
- The first 60 shown.
The file
Files
forge-heartbeat — stall/silence watchdog
Flags a dispatched Boss that went quiet mid-work — crashed, stuck in a loop, or waiting on something nobody is watching. Read-only: it never touches a live agent, it only reads the real events already logged.
When to use
- During a multi-agent
/forgerun — periodically, or whenever the run "feels quiet" (no new dashboard activity for a while). - When the owner asks "is anything stuck?" or "did that agent die?"
- As a future forge-doctor check — same read-only, evidence-only pattern as
forge-doctor/forge-verify; can be wired in later without changing this tool's contract.
How to run
node .claude/forge-bin/forge-heartbeat.cjs check <run_id>
# print stalled agents (or "no stalled agents"), exit 0 clean / 1 stalled
node .claude/forge-bin/forge-heartbeat.cjs check <run_id> --window 15 # override the silence window (minutes)
node .claude/forge-bin/forge-heartbeat.cjs check <run_id> --root <projectRoot>
node .claude/forge-bin/forge-heartbeat.cjs check <run_id> --json # full machine-readable resultWhat STALLED means
- An agent is tracked once it has logged
agent_startedorsubagent_started. - An agent is finished — and never flagged, no matter how old its last event is — once it has
logged
agent_completed,subagent_completed,agent_failed, orsubagent_failedanywhere in its history. Silence after a real completion/failure is expected, not a stall. - An unfinished, tracked agent is STALLED when it has been silent for longer than the window (default 10 minutes) since its last real event.
- Within stalled agents, NEVER PROGRESSED is a stronger flag: the agent's start event is also its only event — it never logged a single progress/output event before going quiet.
- Events with no resolvable
timestampare never treated as "just happened" or invented a fake time for — they're tracked but excluded from the last-seen calculation, so a stall is never hidden or invented by a missing timestamp.
Honesty
- Reads only real events from
<run>/events.jsonl— it never pings a live agent process and never guesses at agent state. - Silence is a flag to CHECK the agent, not to auto-kill it. This tool never cancels, restarts, or reassigns work — it surfaces a signal for the Lead (or the owner) to look at. A stalled agent might simply be doing something slow and legitimate; treat the flag as "go look", not "it failed".
- A malformed line in
events.jsonlis skipped, never crashes the check, and is reported in themalformedcount.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

