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 suyoumo/ClawProBench --skill parallel-pr-reviewgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/parallel-pr-review)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/parallel-pr-review"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/parallel-pr-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.02345 |
| Opus 5 | $0.00034 | $0.01172 |
| Sonnet 5 | $0.00013 | $0.00469 |
| Haiku 4.5 | $0.00007 | $0.00234 |
Grade A, and why
parallel-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 7d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel PR Review
Overview
Review many open PRs at once by fanning out one read-only review subagent per PR (or per stack), each producing a structured verdict, then synthesizing a cross-PR summary and posting reviews. The reviewer (you) stays in the loop holding conclusions; subagents absorb the per-diff reading.
Core principle: one agent per independent unit of review, a consistent rubric and output format across all of them, then a synthesis pass that finds what no single PR review can see.
When to Use
- "Review the open PRs" / "anything new to review?" / recurring review loops
- A batch of PRs from one author, or a stacked series (PR based on another PR's branch)
- Any time reading every diff yourself would blow context
When NOT to use: a single PR (just review it directly); a PR you authored mid-task (use normal self-review).
Workflow
-
Enumerate + triage. List PRs with the metadata that drives decisions:
gh pr list --state open --limit 100 --json number,title,author,additions,deletions,baseRefName,mergeable \ --jq 'sort_by(.number) | reverse[] | "#\(.number) @\(.author.login) +\(.additions)/-\(.deletions) base:\(.baseRefName) \(.mergeable) \(.title)"'base != main⇒ stacked PR (review with its stack, note merge order).CONFLICTING⇒ flag; have the agent diagnose cause + resolution. Re-check: some "conflicting" clears after an upstream rebase.- Compare against PRs already reviewed in prior passes — only review what's new (and re-check any that grew).
-
Group. One agent per PR for standalone changes; one agent per stack (review each stacked PR's own
gh pr diff, in dependency order). Give security-sensitive PRs (contracts, crypto/keys, auth/attestation, money/billing, DoS bounds) their own dedicated agent with an adversarial prompt. For large or structural PRs (big refactors, new modules, files crossing ~1k lines), add a dedicated maintainability-lens agent (see Maintainability lens below).
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.
- 7d ago First seen · 152 lines · 67 tokens per session scan A bad1b8f5b089
parallel-pr-review is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 13d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,345 once invoked, about $0.0003 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
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
changelog
Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc. sections into a single X.Y.Z section). Invoke before tagging a release.
explain-pr
Explain a PR: the background problem and the proposed solution.