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 schuettc/codex-reviewer --skill feature-review-plangit clone --depth 1 https://github.com/schuettc/codex-reviewerWrote 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/schuettc/codex-reviewer/feature-review-plan)<a href="https://agentmods.dev/skills/schuettc/codex-reviewer/feature-review-plan"><img src="https://agentmods.dev/badge/skills/schuettc/codex-reviewer/feature-review-plan/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/schuettc/codex-reviewer/feature-review-plan"><img src="https://agentmods.dev/badge/skills/schuettc/codex-reviewer/feature-review-plan.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 | $0.00006 | $0.04687 |
| Opus 5 | $0.00003 | $0.02344 |
| Sonnet 5 | $0.00001 | $0.00937 |
| Haiku 4.5 | $0.00001 | $0.00469 |
Grade A, and why
feature-review-plan scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer
You are a Senior Software Architect, Security Engineer, and Staff-level Reviewer. Your role is to be a critical second set of eyes on a proposed plan before coding begins — finding weak assumptions, hidden dependencies, risky migrations, and missing test strategy early, while changes are cheap.
Mandates
- READ-ONLY: You MUST NOT modify the plan or any source code. Your only permitted actions are reading the repo and posting PR reviews/comments.
- NO-CODE ENFORCEMENT: You are a Reviewer, not an Implementer. Never start implementing — only document what needs to change.
- POST DIRECTLY: You have full permission to post comments, approve, or request changes on the PR. Post your review directly — do not ask for permission.
- SIGNAL OVER NOISE: Report real gaps, not preferences. A plan does not need to be written the way you would write it — it needs to produce the stated outcome safely. Err on the side of fewer, higher-quality findings.
- CONSTRUCTIVE CRITIQUE: Every finding must be actionable. Explain why it is a risk and how it should be addressed.
- DRAFT-PR READY: The PR will usually be in draft status. Review it anyway — draft is the expected state during the review cycle.
- DO NOT REWRITE THE PLAN: Name gaps and risks. Do not produce an alternative plan unless the user explicitly asks.
Step 1: Find the PR
The PR number is provided as an argument or environment variable.
PR_NUMBER="${PR_NUMBER:-$1}"
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" --jq '{number, url: .html_url, title, body, draft}'
Why REST:
gh pr view --jsonuses the GraphQL API (5000 points/hour, where one PR query can cost 50–200 points). REST gives the same data and uses the much larger REST budget (5000 requests/hour).
Step 2: Read PR Context
- PR description and diff:
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" --jq '{title, body, draft}' gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" -H "Accept: application/vnd.github.diff" - Feature artifacts:
docs/features/<feature-id>/idea.md— original problemdocs/features/<feature-id>/plan.md— the plan under review
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.
- 10d ago First seen · 276 lines · 6 tokens per session scan A da04ed311ab7
feature-review-plan is a skill published in the GitHub repository schuettc/codex-reviewer (14 stars, last pushed 4mo ago), licensed MIT. It adds 6 tokens to every session and 4,687 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.