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 carofi-auto/agent-skills --skill pr-reviewgit clone --depth 1 https://github.com/carofi-auto/agent-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/carofi-auto/agent-skills/pr-review)<a href="https://agentmods.dev/skills/carofi-auto/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/carofi-auto/agent-skills/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/carofi-auto/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/carofi-auto/agent-skills/pr-review.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 | $0.00087 | $0.01758 |
| Opus 5.5 | $0.00035 | $0.00703 |
| Sonnet 5.5 | $0.00017 | $0.00352 |
| Haiku 4.5 | $0.00009 | $0.00176 |
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 1mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review — Pre-Raise Self Review
Attribution: Coverage and severity model from the PR & Code Review Playbook by Mohamed ElZanaty (Engineering Manager, VOXI — vfuk-digital/Digital). Review standard from Google's Code Review Developer Guide (google.github.io/eng-practices).
Run this on your own branch before you raise the PR. It reads your local diff, reviews every changed line the way a senior reviewer would, and reports only findings worth acting on — so the PR you raise is already clean. No GitHub, no CI, no posting: it runs locally and reports back to you.
When this skill activates
- "Review my changes" / "review my diff" / "self-review this branch"
- "Is this ready to raise a PR?" / "what would a reviewer flag?"
- After finishing a feature/fix, before pushing or opening the PR
The standard
Judge the change against one question: does this improve the overall code health of the system? Report what blocks that. Do not demand perfection — a clean, correct, self-contained change is ready, even if not ideal.
Signal over noise. This is a self-review tool, not a linter. Report real issues a senior engineer would stop on. Suppress nitpicks a human wouldn't bother raising, and anything a linter/typechecker/CI already catches.
Phase 0 — Get the diff
- Read the change.
git diff <base>...HEAD(or staged:git diff --cached).<base>= the branch you'll target (usuallymain/master/develop). - Read the intent. Infer what this change is for from the diff and commit messages. If intent is genuinely unclear, say so — don't invent it.
- Classify — picks what to weight hardest:
| Type | Weight hardest on |
|---|---|
| Feature | Design, logic correctness, tests, separation of concerns, UX/a11y |
| Bugfix | Root cause vs symptom, regression test added, blast radius |
| Refactor | Behavior preserved (no functional change smuggled in), test parity |
| API / schema | Backward compatibility, versioning, consumer impact |
| Config / infra | Secrets, rollback path, environment differences |
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.
- 1mo ago First seen · 179 lines · 87 tokens per session scan A 0de217ad1264
pr-review is a skill published in the GitHub repository carofi-auto/agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,758 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 2026-08-31.
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"…
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…
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…
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…