Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jasonm4130/claude-skills --skill codex-plan-reviewgit clone --depth 1 https://github.com/jasonm4130/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jasonm4130/claude-skills/codex-plan-review)<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/codex-plan-review"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/codex-plan-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/codex-plan-review"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/codex-plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.02690 |
| Opus 5 | $0.00083 | $0.01345 |
| Sonnet 5 | $0.00033 | $0.00538 |
| Haiku 4.5 | $0.00017 | $0.00269 |
Grade C, and why
codex-plan-review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
> | 2 | the deep-dive integrity branch — *after* 3 plan rounds + an audit | a host guard that let a fabricated finding aim the verifier's `WebFetch` at `169.254.169.254`; `startsWith`-only placeholder matching; unvalidat How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Plan Review
Send a finalized plan/spec/design/ADR to OpenAI Codex (Terra, high effort, read-only sandbox) for adversarial review. The script handles mechanics; you handle judgment. Script path (resolve via this skill's base directory): scripts/codex-review.mjs, run with node.
The one non-negotiable prompt rule: the reviewer must never see your self-assessment. The script builds prompts from the file path only — never paste plan content, your confidence, or "tests pass" claims into any codex invocation. (Research: implementer framing degrades Codex review thoroughness 3–4×.)
Flow
- Announce: "Running Codex plan review (Terra, high effort) — round 1." If
codexis missing or not logged in (codex login status), say so, skip, and continue without blocking the plan. - Preflight: the artifact must be a file. Write conversation-only plans to their canonical path first (
docs/superpowers/specs/…, the repo's own plans directory, or scratchpad for throwaways). - Round 1:
node <skill-dir>/scripts/codex-review.mjs review <file> --auto(use--forceonly when the user explicitly asked for a re-run). If it refuses with "chain already exists", tell the user this artifact version was already reviewed and stop unless they ask to force. - On
REVISE: walk findings one at a time. For accepted findings, amend the plan file. Dismissals require a stated reason in your reply — never silent. Then verify fixes:… review <file> --resume <sessionId> --chain <chainId>. Max 3 review rounds total — the script now refuses a 4th before spending any paid call. Plans do reachAPPROVED: 12 of 63 review chains in the first 20 days, 9 of them at round 3 (first on 2026-07-16). If stillREVISEafter folding round-3 findings in, proceed to the audit anyway (see step 5) rather than stopping — the audit is most valuable exactly here, after three rounds of findings have been folded in. Only skip it if the user stops before folding the findings in; then log the note ascap-revise. - Run the final audit — after either an
APPROVEDround or a round-3REVISEwhose findings have been folded in:… audit <file> --chain <chainId>(fresh Codex session, holistic scope; the script refuses a second audit on the same chain before spending any paid call).AUDIT: PASS→ done.AUDIT: CONCERNS→ surface findings verbatim and block: the plan is not review-complete until the user dispositions each concern. Never re-run the audit; if the user amends in response, the outcome class isaudit-concerns-user-approved(user-approved, audit-unverified); if the user dismisses the concerns with reasons instead, it isaudit-concerns-dismissed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · -21 tokens per session ef9d7bf01270
- 10d ago First seen · 104 lines · 187 tokens per session scan C 44a90ef7de8c
codex-plan-review is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 166 tokens to every session and 2,690 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
challenge
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.