agentleFS
Sign inStart free
tonmoy007tonmoy007/forge-plugins/skills/forge-health-check/SKILL.md

health-check

Skill2 starsChanged 5 months agoMITView on GitHub

Run a full self-diagnostic of the Forge plugin — executes hook unit

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use testing.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After a session where hooks behaved unexpectedly.

    line 23
  2. Distinctive:

    Before a release to verify the plugin is in good shape.

    line 24
  3. Distinctive:

    Run the health check:

    line 33
  4. Very specific:

    If FAILING and auto-disable fired (policy was true):

    line 48

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Forge Health Check

Runs the Health daemon (REQ-F-022..026). Executes hook unit tests as a subprocess, checks .forge/lessons.yaml for structural integrity, and produces a markdown health report. Overall status is healthy, degraded, or failing based on clear rules. Auto-disable of hooks is gated on explicit policy and is never silent.

When to Use

  • User types /forge:health-check or asks to check if the plugin/hooks are working.
  • After a session where hooks behaved unexpectedly.
  • Before a release to verify the plugin is in good shape.

When NOT to Use

  • The user wants to run the full test suite — use pytest tests/ directly.
  • The user wants pipeline status (stage gates) — that is /forge:status.

Steps

  1. Run the health check:
    python3 ${CLAUDE_PLUGIN_ROOT}/scripts/health_check.py --run --cwd "$(pwd)"
  2. Present the full markdown report verbatim. The report covers:
    • Hook tests: pass/fail counts from hook-focused pytest run.
    • Lesson store: any integrity issues in .forge/lessons.yaml (missing fields, out-of-range confidence, broken [[xref]] cross-references, malformed YAML).
    • Status summary: HEALTHY, DEGRADED, or FAILING.
  3. Interpret the status for the user:
    • HEALTHY — all hooks pass and lesson store is clean. No action needed.
    • DEGRADED — hooks pass but lesson store has issues. Recommend reviewing .forge/lessons.yaml and fixing flagged entries.
    • FAILING — hook tests failed. Show the failing detail and suggest running pytest tests/unit -k "hook or session_start" directly for full output.
  4. If FAILING and auto-disable fired (policy was true):
    • Tell the user that .forge/health-surface.txt has been written and will surface at the next session start.
    • Tell the user that .forge/events.jsonl has the audit record.
    • Emphasise this was NOT silent — the policy was explicitly opted into.

Verification

  • Exit code 0 = healthy, non-zero = degraded or failing.
  • Re-running /forge:health-check after fixing tests should flip status to HEALTHY.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free