agentleFS
Sign inStart free
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/module-auditor/SKILL.md

module-auditor

Skill2 starsChanged 7 months agoMITView on GitHub

Audit the runtime/script module according to BLOCKER/WARN/INFO criteria: syntax, path safety, PID/service logic, upgrade/uninstall safety, runtime healthcheck.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before releasing the zip module.

    line 31
  2. Distinctive:

    After editing the script service/install.

    line 32
  3. Distinctive:

    Do not hardcode the path in the wrong context

    line 44
  4. Distinctive:

    stop service + cleanup correct module scope

    line 54
  5. Distinctive:

    Check the results, state validation and next steps.

    line 80
  6. Distinctive:

    If input/permissions are missing: report what is missing and clearly request additional information.

    line 83
  7. Distinctive:

    If runtime/tool ​​error: brief error return + possible cause + suggested fix.

    line 84
  8. Distinctive:

    If there is a risk policy/safety: stop and escalate according to approval checkpoint.

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Module Auditor

Skill audit before flashing to reduce the risk of brick/service failure.

Scope

  • In-scope: audit the module according to the domain the skill describes, focusing on evidence, boundary safety, and verifiable findings.
  • Out-of-scope: packaging/build/refactor outside the audit scope if not explicitly requested.

Indexed Reference Map

  • @[SKILL.md#L1-L79] Standard Frontmatter (name, description).
  • @[SKILL.md#L6-L79] Module Auditor.
  • @[SKILL.md#L10-L79] When to use.
  • @[SKILL.md#L14-L79] Audit levels.
  • @[SKILL.md#L19-L79] Main Checklist.
  • @[SKILL.md#L36-L79] Output required.
  • @[SKILL.md#L43-L79] Internal Tools.

Supporting files

  • @[references/audit-checklist.md#L1-L22] Reference document/rulebook for technical decisions.
  • @[scripts/audit_module.sh#L1-L47] Execution/automation script for skill.

When to use

  • Before releasing the zip module.
  • After editing the script service/install.

Audit levels

  • BLOCKER: flash/install may fail, binary won't run, path is dangerous.
  • WARN: can run but prone to runtime/stale state errors.
  • INFO: optimization/cleanliness.

Main checklist

  1. Syntax & permissions
    • sh -n for the entire .sh
    • executable bit cho scripts/binaries
  2. Path correctness
    • Do not hardcode the path in the wrong context
    • Runtime dir consistent
  3. Service logic
    • stale PID handling
    • healthcheck endpoint
    • start timeout + fail-fast
  4. Installer safety
    • upgrade preserve data
    • Minimal rollback when install errors
  5. Uninstall safety
    • stop service + cleanup correct module scope

Required output

  • Audit report format:
    • BLOCKER
    • WARN
    • INFO
    • Final verdict (GO/NO-GO)

Internal tools

  • Audit support script: scripts/audit_module.sh
  • Detailed checklist: references/audit-checklist.md

Trigger Rules

  • Positive: Triggers when user request matches module-auditor according to description: Audit runtime/script module according to BLOCKER/WARN/INFO criteria: syntax, path safety, PID/service logic, upgrade/uninstall safety, runtime healthcheck.
  • Negative: Not enabled for requests outside scope or without the workflow/expertise of this skill.
  • Escalation: If there is an external action/network write or sensitive operation, an approval checkpoint must be added before executing.

Output Contract

  • Deliverable: target tracking result of module-auditor; Specify the artifact/path/steps performed (if any).
  • Validation: reports PASS/FAIL status and main checks have been run.
  • Failure mode: when there is an error, the root cause + proposed fix must be stated.

SOP

  1. Determine whether the request is within the scope of the skill or not.
  2. Execute the skill's main workflow/instructions in a safe order.
  3. Check the results, state validation and next steps.

Error Handling

  • If input/permissions are missing: report what is missing and clearly request additional information.
  • If runtime/tool ​​error: brief error return + possible cause + suggested fix.
  • If there is a risk policy/safety: stop and escalate according to approval checkpoint.

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