agentleFS
Sign inStart free
raccromptonraccrompton/claude-codex-skills/skills/consulting-codex/SKILL.md

consulting-codex

Skill1 starsChanged 5 months agoMITView on GitHub

Use to get a Codex second opinion on a drafted spec or plan before it reaches the user's approval gate — invoked at the superpowers brainstorming spec-review gate and the writing-plans plan-approval gate. Read-only critique; iterates the artifact to convergence; returns a digest.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. atgreen/hackinator★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    NOT rewrite — critique only.

    line 22
  2. Very specific:

    If codex is missing from PATH, unauthenticated, exits non-zero, or a call exceeds ~120s: stop, emit Codex consult skipped: <reason>, and …

    line 45
  3. Distinctive:

    If Codex was clean on round 1: "Codex: no material issues." If skipped: the skip reason.

    line 56
  4. Distinctive:

    If skipped: the skip reason.

    line 57

≈ “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

Consulting Codex on a spec or plan

Get a second opinion from the local Codex CLI on a drafted spec or plan, iterate it to a stronger state, and hand back a digest. You (the agent) remain responsible for the edits and the judgment; the user remains the final gate.

Inputs

  • ARTIFACT — path to the drafted spec or plan doc.
  • TYPE — spec or plan.

Procedure

  1. Build the review prompt for the TYPE:
    • spec: "Review the design spec at <ARTIFACT>. Identify gaps, ambiguities, contradictions, unstated assumptions, scope creep, missing error/edge cases, and simpler alternatives. Cite sections concretely. Do NOT rewrite — critique only. If it is solid, say so plainly."
    • plan: "Review the implementation plan at <ARTIFACT>. Check task ordering, hidden/implicit dependencies, missing steps, risky or untestable steps, and anything underspecified for an engineer with zero context. Cite tasks concretely. Do NOT rewrite — critique only. If it is solid, say so."
  2. Run Codex (read-only):
    codex exec --sandbox read-only --skip-git-repo-check '<prompt>'
    The repo is readable, so Codex can ground its critique in surrounding code.
  3. Filter the critique using superpowers:receiving-code-review: verify each point against the artifact and codebase. Incorporate the valid ones by editing <ARTIFACT>. Reject wrong/over-engineered ones and record a one-line reason for each.
  4. Iterate to convergence: re-run step 2 on the revised artifact. Stop when Codex raises nothing material OR after 3 rounds total.
  5. Return a digest (see Output).

Error handling — never block

If codex is missing from PATH, unauthenticated, exits non-zero, or a call exceeds ~120s: stop, emit Codex consult skipped: <reason>, and return control so the workflow proceeds to the user's gate. A missing/flaky Codex must never stall the workflow.

Output (the digest)

Return a short digest for the user's gate:

  • Raised: what Codex flagged (bulleted).
  • Incorporated: what was folded in.
  • Rejected: what was rejected and why.
  • Rounds: count, plus any items still open at the 3-round cap. If Codex was clean on round 1: "Codex: no material issues." If skipped: the skip reason.

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