How do I install the Forge Heartbeat skill?

Run npx skillmds@latest add forgeyclap/forge-heartbeat-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Forge Heartbeat safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Forge Heartbeat?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Forge Heartbeat free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Forge Heartbeat?

ForgeyClap (@forgeyclap) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Forge Heartbeat by forgeyclap — Agent Skill

Name: Forge Heartbeat
Author: ForgeyClap

Forge Heartbeat

Detect a dispatched agent that has gone silent mid-run — reads the run's events.jsonl and flags any started-but-not-finished agent that hasn't logged anything for longer than a window (default 10 minutes). Use during multi-agent runs, periodically or whenever a run feels quiet, and as a check forge-doctor can call later.

ForgeyClap Updated Sep 22, 2026

File contents

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 /forge run — 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 result

What STALLED means

An agent is tracked once it has logged agent_started or subagent_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, or subagent_failed anywhere 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 timestamp are 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.jsonl is skipped, never crashes the check, and is reported in the malformed count.

---name: forge-heartbeat-2description: Detect a dispatched agent that has gone silent mid-run — reads the run's events.jsonl and flags any started-but-not-finished agent that hasn't logged anything for longer than a window (default 10 minutes). Use during multi-agent runs, periodically or whenever a run feels quiet, and as a check forge-doctor can call later.---# forge-heartbeat — stall/silence watchdogFlags a dispatched Boss that went quiet mid-work — crashed, stuck in a loop, or waiting on somethingnobody is watching. Read-only: it never touches a live agent, it only reads the real events alreadylogged.## When to use- **During a multi-agent `/forge` run** — 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 stallednode .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 result```## What STALLED means- An agent is **tracked** once it has logged `agent_started` or `subagent_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`, or `subagent_failed` anywhere 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 `timestamp` are 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.jsonl` is skipped, never crashes the check, and is reported in the `malformed` count.

Frequently asked questions