Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yorrick/agent-skills/plugin install pr-reviewWrote 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/yorrick/agent-skills/pr-review)<a href="https://agentmods.dev/skills/yorrick/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/yorrick/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/yorrick/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/yorrick/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 | $0.00125 | $0.04038 |
| Opus 5 | $0.00063 | $0.02019 |
| Sonnet 5 | $0.00025 | $0.00808 |
| Haiku 4.5 | $0.00013 | $0.00404 |
Grade B, and why
pr-review scanned grade B with 1 finding 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/plugins ~/.codex/plugins ~/.agents -path "*pr-review*" \ How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Provider Interactive PR Review
Run three AI code reviewers in parallel on a PR, synthesize their findings, then interactively vet each issue before posting anything to GitHub.
The key principle: nothing gets posted to the PR until you've reviewed and approved it. You stay in control of every comment.
How It Works
- Gather — build prompts from PR metadata (deterministic script)
- Review — run Claude, Gemini, and Codex in parallel (none of them touch the PR)
- Synthesize — read all raw reviewer outputs, cluster by root issue, build consensus (LLM)
- Vet — walk through each finding interactively, discuss, approve or reject (LLM + user)
- Post — submit approved findings as inline file-level comments (deterministic script)
- Verdict — draft a PR-level review (approve/request changes/comment), let user edit, then post
Scripts in scripts/ handle deterministic work (prompt building, GitHub posting). The LLM handles semantic work (reading raw outputs, clustering duplicates, synthesizing consensus, interactive discussion).
Step 0: Locate the plugin
CLAUDE_PLUGIN_ROOT is set by Claude Code only — Codex sets no plugin-root variable
at all, so it would expand to an empty string. Resolve the root once, then reuse it:
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
[ -f "$PLUGIN_ROOT/scripts/build_prompts.py" ] || PLUGIN_ROOT=$(
find ~/.claude/plugins ~/.codex/plugins ~/.agents -path "*pr-review*" \
-name build_prompts.py 2>/dev/null | head -1 | xargs -r dirname | xargs -r dirname
)
echo "$PLUGIN_ROOT"
Step 1: Build Prompts
Run the prompt builder script to fetch PR metadata and create prompt files:
uv run "$PLUGIN_ROOT/scripts/build_prompts.py" <PR_NUMBER> --out-dir /tmp
This outputs JSON with paths to per-provider prompts:
{
"pr_number": 365,
"pr_title": "MEWS Integration",
"pr_url": "https://github.com/owner/repo/pull/365",
"repo": "owner/repo",
"commit_sha": "abc123...",
"review_prompt_claude": "/tmp/pr-review-prompt-claude-365.md",
"review_prompt_gemini": "/tmp/pr-review-prompt-gemini-365.md",
"review_prompt_codex": "/tmp/pr-review-prompt-codex-365.md",
"security_prompt_claude": "/tmp/pr-security-prompt-claude-365.md",
"security_prompt_gemini": "/tmp/pr-security-prompt-gemini-365.md",
"security_prompt_codex": "/tmp/pr-security-prompt-codex-365.md"
}
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 358 lines · 125 tokens per session scan B 7eeee7c18f7d
pr-review is a skill published in the GitHub repository yorrick/agent-skills (10 stars, last pushed 6d ago), licensed MIT. It adds 125 tokens to every session and 4,038 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.