agentleFS
ai-agent-assemblyai-agent-assembly/agent-assembly/.claude/skills/governance-doctor/SKILL.md

governance-doctor

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Check a Horonom repo (or the local $HORONOM_WORKSPACE_ROOT) for drift between its adopted governance projection and the current canonical content in horonomy/.github, and report it as PASS/WARN/FAIL — mirroring the horonom doctor CLI this skill wraps (HORO-510). Auto-used. Invoke before starting work in an adopted repo, and periodically during a long-running session. Any repo that has adopted Horonom governance (has a generated .claude/ or .codex/ projection, or a workspace-root CLAUDE.md/AGENTS.md). - A repo that has not adopted Horonom governance at…

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check a Horonom repo (or the local $HORONOM_WORKSPACE_ROOT) for drift between its adopted governance projection and the current canonical …

    line 8
  2. Very specific:

    Check for the security invariants in governance/engineering/security.md mechanically where practical (no secret-shaped content in a …

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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
<!-- horonom:generated --><!-- Source: horonomy/.github agents/skills/governance-doctor/SKILL.md. Do not hand-edit — rerun `python3 agents/common/project_skills.py`. -->

SKILL.md — governance-doctor

Purpose

Check a Horonom repo (or the local $HORONOM_WORKSPACE_ROOT) for drift between its adopted governance projection and the current canonical content in horonomy/.github, and report it as PASS/WARN/FAIL — mirroring the horonom doctor CLI this skill wraps (HORO-510).

Type

Auto-used. Invoke before starting work in an adopted repo, and periodically during a long-running session.

When to use

Any repo that has adopted Horonom governance (has a generated .claude/ or .codex/ projection, or a workspace-root CLAUDE.md/AGENTS.md).

When NOT to use

  • A repo that has not adopted Horonom governance at all — there is nothing to check drift against. Use repo-bootstrap first.
  • A repo whose own governance is intentionally ahead of what's projected (e.g. mid-adoption of a newer governance_version not yet regenerated everywhere) — report the drift, don't treat "ahead" as a failure to fix by reverting.

Procedure

  1. Run python3 scripts/doctor.py --repo <path> [--workspace-root <path>] [--product <name>] from a horonomy/.github checkout (HORO-510). It reports PASS/WARN/FAIL/ NOT_APPLICABLE per check with an actionable fix hint — read the fix field before doing any manual investigation.
  2. Compare each generated file's provenance header (governance_version=<N>) against metadata/governance.yaml's current governance_version in horonomy/.github.
    • Same version, content matches what regenerating would produce → PASS.
    • Recorded version behind current, but content still matches what that older version would have produced → WARN (merely stale, not corrupt).
    • Content differs from what regenerating the recorded version would produce → FAIL (someone hand-edited a generated file).
  3. Check for the security invariants in governance/engineering/security.md mechanically where practical (no secret-shaped content in a generated file; no broad-kill patterns in any script under agents/).
  4. Report findings; do not silently "fix" a FAIL by regenerating without telling the operator what was overwritten — a FAIL on a generated file means someone edited generated content, which is itself worth surfacing before it's clobbered.

References

  • governance/README.md — the drift/adoption contract (decision #9 in ADR-0005).
  • governance/engineering/security.md — the mechanical enforcement bar for a "non-waivable" claim.
  • scripts/doctor.py + scripts/doctor_checks.py — the real implementation (HORO-510); see governance/workspace/doctor.md for the full check list.
  • scripts/horonom_workspace.py status — the workspace-root half of this check (HORO-506), which doctor.py delegates to.

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.