Borrowing it
Nothing to install: this file belongs to ForgeyClap/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ForgeyClap/claude-forge/main/.claude/skills/forge-heartbeat/SKILL.mdgit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-heartbeat)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-heartbeat"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-heartbeat.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00709 |
| Opus 5 | $0.00020 | $0.00354 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
forge-heartbeat scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 result
What 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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 54 lines · 41 tokens per session scan A 83a25cb499b7
forge-heartbeat is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 709 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-contract
Phase 4 — propose verifiable completion criteria and mandatory hard gates; reach AGREED (1-pass default, multi-round negotiation in --strict).