agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/agent-watchdog/SKILL.md

agent-watchdog

Skill4 starsChanged 11 days agoMITView on GitHub

Audit another agent against the original request and live evidence. Use for sessions, PRs, branches, comparisons, authorized fixes, or taking over stuck work.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Very specific:

    Read audit protocol before audits.

    line 6
  2. Distinctive:

    Use authorized sources and live host tools.

    line 8
  3. Distinctive:

    Default audit-only when edit authority is unclear.

    line 19

≈ “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

Read audit protocol before audits; read references/builder-upstream.md for complex/ambiguous audits. Use authorized sources and live host tools. Investigate inline; extra agents, monitoring, production access, and writes need separate authorization.

Modes

  • Watch: monitor session/PR/branch/CI/transcript to terminal; no edits.
  • Audit: compare request, evidence, diff, tests, CI, comments and claims; no edits.
  • Audit and fix: audit, then narrow authorized fixes.
  • Compare: judge agents/sessions against one request.
  • Takeover: explicit request to own stuck work; follow takeover through the requested endpoint, not just the previous approach.

Default audit-only when edit authority is unclear.

Workflow

Takeover uses its reference; otherwise:

  1. Resolve target and original ask/constraints; form your own hypotheses first.
  2. Inspect primary evidence; compare the agent's diff, checks and claims.
  3. Mark prior exposure; inline investigation is not an independent reviewer or model-family pass.
  4. Classify Gap|Bug|Verification miss|Scope drift|No issue.
  5. Fix only authorized gaps; never revert unrelated work or move branches unasked.
  6. Report exact evidence, actionable differences, risks and next action; follow the audit protocol for relay, completed worktrees and output.

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