Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ForgeyClap/claude-forgenpx agentmods add skills/forgeyclap/claude-forge/forge-doctorWrote 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-doctor)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-doctor"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-doctor"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-doctor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.00495 |
| Opus 5.5 | $0.00016 | $0.00198 |
| Sonnet 5.5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
forge-doctor 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 1mo 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.
What it actually says
forge-doctor — self-test + leak scan
One command that proves the Forge install in this project actually works and leaks nothing.
When to use
- The owner asks to "test everything", "check it all executes", or "find leaks".
- Before a sync/handoff, or after a batch of tooling changes.
- As the Security Boss's evidence step (the leak scan is a real security check).
How to run
node .claude/forge-bin/forge-doctor.cjs # print a green/red summary, exit 0/1
node .claude/forge-bin/forge-doctor.cjs --run <run_id> # also write <run>/doctor.json + log doctor_run
node .claude/forge-bin/forge-doctor.cjs --json # full machine-readable report
What it checks (all real — no fabrication)
- node --check on every
.cjs/.jsunderforge-bin/+forge-dashboard/. - tests — runs every
forge-bin/*.test.cjsand tallies passed/failed. - honesty gate — feeds
log-event.cjsa known type (expect accept) and an unknown type (expect hard-reject / exit 2), then deletes the throwaway run. Proves strict events still reject junk. - dashboard SPA — the render files are all present.
- leak scan — scans git-tracked files with the hardened
SECRET_PATTERNS; reports only{file, pattern}, never the matched secret..env.example+ binaries are skipped.
Writes <run>/doctor.json (read by the dashboard Doctor panel + the Project Registry's test_status).
Exit code 0 = all green, 1 = a check failed — safe to gate a hook/CI on it.
Honesty
Real command output only. A failing check is reported as failing; the leak scan never prints a secret,
only the file + which pattern matched. test_status in the registry mirrors this doctor.json.
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.
- 1mo ago First seen · 37 lines · 40 tokens per session scan A 7ed858345cb4
forge-doctor is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 495 once invoked, about $0.0002 per session on Opus 5.5. 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
validate
Use when operating as the Fabrik Validate stage agent. This skill guides final validation of an implementation, verifying requirements are met, tests pass, and the PR is ready to merge.
implement
Use when operating as the Fabrik Implement stage agent. This skill guides the implementation of a planned feature, following the task checklist to produce committed, tested, pushed code on a feature branch.
validate-comment
Use when operating as the Fabrik Validate comment reviewer. This skill guides updating the validation report, re-running checks, and applying minor fixes in response to user feedback — signaling completion only when the user explicitly indicates the issue is resolved.
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.
coding-quality-loop
Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.
test-integrity-gate
Use when AI-written code or tests claim green and you need deterministic proof that the new test catches the old bug.