agentleFS
DarthJonathanDarthJonathan/guac-skills/skills/interrogate/SKILL.md

interrogate

Skill0 starsChanged 17 days agoMITView on GitHub

Adversarially review a diff from multiple available perspectives and synthesize actionable findings. Use for interrogate, stress-test, or multi-model review requests.

73 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. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Read the Codex runtime adapter once per session before using this skill.

    line 6
  2. Distinctive:

    Read the reviewer prompt, the rubric, and the code-quality lens.

    line 13
  3. Distinctive:

    Read the lead-judgment guidance.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 73 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

Read the Codex runtime adapter once per session before using this skill. Its tool, model, history, and authorization mappings apply to all linked instructions.

Interrogate

Review the requested change. Do not apply fixes unless the user also authorized them.

  1. Resolve the exact files, diff, and base from the request and repository. State the intended behavior from the user's goal, code, and existing PR description. Inspect enough surrounding code to judge real callers.
  2. Read the reviewer prompt, the rubric, and the code-quality lens.
  3. Use the interrogate reviewers panel when native delegation is available and permitted. With no configuration, use two separate sessions inheriting the host model. Give each the same intent, scoped diff, context paths, and read-only brief. Same-model sessions are not a multi-model review. If a requested different model is unavailable, report that limitation.
  4. Validate findings against source and real failure conditions. Merge duplicates, track who raised each issue, and investigate contradictions. Agreement is supporting evidence, not proof.
  5. Read the lead-judgment guidance. Classify findings as Act on, Consider, Noted, or Dismissed with a concrete reason. Prioritize actual correctness, security, and maintenance consequences under the stated goal.

Return intent, reviewers actually used, actionable findings with tight source locations and failure scenarios, other material findings, dismissals, and disagreements. Drop empty sections. When delegation is unavailable, perform a single-agent adversarial review and say so.

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.