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 Magnus-Gille/claude-skills --skill review-pr-codexgit clone --depth 1 https://github.com/Magnus-Gille/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/magnus-gille/claude-skills/review-pr-codex)<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/review-pr-codex"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/review-pr-codex/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/magnus-gille/claude-skills/review-pr-codex"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/review-pr-codex.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 | $0.00040 | $0.00377 |
| Opus 5 | $0.00020 | $0.00188 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
review-pr-codex 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 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.
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.
What it actually says
Review PR With Codex
Perform this review directly in the current Codex session. Do not shell out recursively to codex exec unless the user explicitly requests a separate child Codex run.
Workflow
- Determine the scope.
- For a PR number, run
gh pr view <number> --json baseRefName,headRefName,title,url. - For a branch, resolve its intended base from the PR or remote metadata.
- Without an argument, use the current branch's open PR when available; otherwise discover the remote default branch instead of assuming
main. Stop clearly if no reliable base exists.
- For a PR number, run
- Read the selected diff and nearby code in proportion to its size. Start with changed files, direct callers, and tests. Keep the review read-only.
- Review for bugs/regressions, security, API/doc/config drift, error paths, tests, and deployment or portal contracts when they are in scope.
- Present grounded findings first, ordered by severity, with file/line, evidence, impact, and a concrete fix. Say clearly when no findings are supported and include residual test gaps.
- If the user explicitly asks to fix findings, or the already-authorized task includes fixing them, implement them and run focused tests; otherwise do not modify, commit, merge, push, or post comments. The review process itself remains read-only.
Do not invent findings from names or conventions alone. Confirm the path is reachable and the claimed behavior is affected by the reviewed change.
This is a native Codex review in the current session, not Claude invoking an external Codex CLI process.
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 · -155 lines · -1 tokens per session 1d18624ceffb
- 12d ago First seen · 179 lines · 41 tokens per session scan A f97a0e4481fe
review-pr-codex is a skill published in the GitHub repository Magnus-Gille/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 377 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
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…