Borrowing it
Nothing to install: this file belongs to bman654/clodex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bman654/clodex/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/bman654/clodexWrote 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/bman654/clodex/pr-review)<a href="https://agentmods.dev/skills/bman654/clodex/pr-review"><img src="https://agentmods.dev/badge/skills/bman654/clodex/pr-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00079 | $0.04198 |
| Opus 5 | $0.00039 | $0.02099 |
| Sonnet 5 | $0.00016 | $0.00840 |
| Haiku 4.5 | $0.00008 | $0.00420 |
Grade A, and why
pr-review 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a clodex PR
The bar you are checking the change against is .claude/skills/pr-verification/SKILL.md — read that
first; this document is only about how to run the review itself. Everything here was paid for by a
review that got something wrong.
Orient before you read code
- Diff
head.shaagainst your notes before re-reviewing anything. GitHub does not make "what is new since my review" legible: a stale review request or an old force-push notification reads exactly like fresh work. Onegh api repos/bman654/clodex/pulls/N --jq .head.shasettles it. A PR timeline that ends on your own review is the other tell. - When the author rebased, diff patch-vs-patch, not head-vs-head. After a rebase onto a new
release,
git diff old..newis pure noise. Usegit diff $(git merge-base main X)..Xfor each head and thendiff -uthe two patches. This is how you find out a "small update" was actually a full rebuild. - Before alleging the author skipped work or misstated a result, read the PR body and the comments, and tie every claim to the head it describes. A reviewer once called a contributor's number an unsupported inference when the PR's own validation section stated the source in as many words — the same failure shape we warn contributors about, committed by the reviewer. Later, a panel drafted a note telling an author to re-run a gate his own transplant comment had already reported, with the exact numbers we had measured ourselves. After a rebase or transplant the current gate result often lands in a comment while the body still describes the dead head — but a comment ages the same way, so neither surface is authoritative until you match it to the head. Note what did not save us there: four lenses, a refuter pass, and a cross-family cross-check all missed it, and the cross-check actually endorsed the note and extended it. Only an explicit body-versus-comment check before drafting caught it. That is why this is a named step and not a thing you can expect the panel to notice.
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 · 244 lines · 79 tokens per session scan A 8f940f9900c0
pr-review is a skill published in the GitHub repository bman654/clodex (55 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 4,198 once invoked, about $0.0004 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…