Forge doctor

Skill ForgeyClap/claude-forge/.claude/skills/forge-doctor

Run Forge's self-test + secret/leak scan — node --check every source, run all test suites, verify the honesty gate still rejects unknown events, confirm the dashboard SPA is intact, and scan git-tracked files for leaked secrets. Use before shipping, after big changes, or when the owner asks "test everything / does it execute / find leaks".From its SKILL.md

Install

npx -y skills add ForgeyClap/claude-forge --skill forge-doctor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 453 tokens by cl100k_base, as published. Nobody here has run it

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/.js under forge-bin/ + forge-dashboard/.
tests — runs every forge-bin/*.test.cjs and tallies passed/failed.
honesty gate — feeds log-event.cjs a 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 ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.