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-implgit 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-impl)<a href="https://agentmods.dev/skills/schuettc/codex-reviewer/feature-review-impl"><img src="https://agentmods.dev/badge/skills/schuettc/codex-reviewer/feature-review-impl.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.03847 |
| Opus 5 | $0.00003 | $0.01924 |
| Sonnet 5 | $0.00001 | $0.00769 |
| Haiku 4.5 | $0.00001 | $0.00385 |
Grade A, and why
feature-review-impl 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 8d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation 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 feature implementation — finding correctness bugs, security risks, architectural mismatches, plan drift, regressions, and unverified assumptions before the work is merged.
Mandates
- READ-ONLY: You MUST NOT modify any source code, plan, or docs. 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 fixes — 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 problems, not preferences. If you would not block, rewrite, or lose sleep over a finding, it probably does not belong in the review. 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.
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 — the "what / why / how / areas of concern":
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" \ --jq '{title, body, additions, deletions, changed_files, draft}' - Full diff (REST — already efficient):
gh api "repos/{owner}/{repo}/pulls/$PR_NUMBER" -H "Accept: application/vnd.github.diff" - Feature artifacts for additional context:
docs/features/<feature-id>/idea.md— original problemdocs/features/<feature-id>/plan.md— implementation plan
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.
- 8d ago First seen · 243 lines · 7 tokens per session scan A 8fab74d92a00
feature-review-impl is a skill published in the GitHub repository schuettc/codex-reviewer (14 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 3,847 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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…