# Consulting Codex

> 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.

- **Type:** Skill
- **Install:** `agentstack add skill-raccrompton-claude-codex-skills-consulting-codex`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [raccrompton](https://agentstack.voostack.com/s/raccrompton)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [raccrompton](https://github.com/raccrompton)
- **Source:** https://github.com/raccrompton/claude-codex-skills/tree/main/skills/consulting-codex

## Install

```sh
agentstack add skill-raccrompton-claude-codex-skills-consulting-codex
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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 ``. 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 ``. 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):**
   ```sh
   codex exec --sandbox read-only --skip-git-repo-check ''
   ```
   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 ``. 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: `, 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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [raccrompton](https://github.com/raccrompton)
- **Source:** [raccrompton/claude-codex-skills](https://github.com/raccrompton/claude-codex-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-raccrompton-claude-codex-skills-consulting-codex
- Seller: https://agentstack.voostack.com/s/raccrompton
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.