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/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/bman654/clodex/pr-review"><img src="https://agentmods.dev/badge/skills/bman654/clodex/pr-review.svg" alt="Reviewed on agentmods" width="80" 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 5.5 | $0.00032 | $0.01679 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 244 lines · 79 tokens per session scan A 8f940f9900c0
pr-review is a skill published in the GitHub repository bman654/clodex (108 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 4,198 once invoked, about $0.0003 per session on Opus 5.5. 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
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…