What is ac-qa-gh-pr-review?

A pull-request review workflow that uses one bounded group of review workers, combines their findings, and can submit a review through GitHub after confirmation.

Use it to review a GitHub pull request against its intended changes, save a report, and optionally post the confirmed review.

It provides a repeatable review process while keeping the final report and any GitHub submission under the coordinator's control.

ac-qa-gh-pr-review — Skill for Claude Code by WaterplanAI

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/WaterplanAI/agentic-config

agentmods

npx agentmods add skills/waterplanai/agentic-config/ac-qa-gh-pr-review

Made for: Claude Code.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 1 plugin.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-qa-gh-pr-review/github.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-qa-gh-pr-review)

Your own site

<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-qa-gh-pr-review"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-qa-gh-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-qa-gh-pr-review"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-qa-gh-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,251 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.03251
Opus 5	$0.00016	$0.01625
Sonnet 5	$0.00007	$0.00650
Haiku 4.5	$0.00003	$0.00325

Measured 12d ago against content hash 1b75646c4696, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ac-qa-gh-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 12d 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.

packages/pi-ac-qa/skills/ac-qa-gh-pr-review/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review - pi adaptation

Review a pull request with a bounded shared worker-wave on top of the shipped @agentic-config/pi-compat orchestration helpers.

Current shipped boundary

This pi wrapper now ships, but it stays inside the bounded IT003 contract:

use exactly one fixed review-worker wave through subagent
use the shared pi-compat worker protocol and result helpers for worker outputs
keep PR metadata fetch, final markdown synthesis, and any gh pr review action in the coordinator skill
keep review posting user-confirmed and serial through AskUserQuestion
do not introduce nested workers, subagent.chain, mux/session state, or package-local orchestration helpers
if the local checkout does not match the PR head, continue honestly in diff-first mode and report any execution limitation instead of pretending local commands validated the PR head

Arguments

pr_ref (required): PR URL, owner/repo#123, or any gh pr view-compatible PR reference
expected_changes (optional): brief description of the intended change; if omitted, compare the diff against the PR title/body only
report_path (optional): explicit final report path; default to tmp/gh-pr-review/<date>-<uuid>/PR-<number>-<uuid>.md

Required references

Read these when needed:

node_modules/@agentic-config/pi-compat/assets/orchestration/protocol/worker.md
node_modules/@agentic-config/pi-compat/assets/orchestration/tools/write-result.js
node_modules/@agentic-config/pi-compat/assets/orchestration/tools/summarize-results.js

Pre-flight

Verify gh CLI is available and authenticated:
```
gh --version
gh auth status
```
- If either step fails: STOP and explain what is missing.
Verify the current directory is inside the repo being reviewed:
```
REPO_ROOT=$(git rev-parse --show-toplevel)
```
- If this fails: STOP. This skill needs a local repo so the workers can inspect the actual codebase and run bounded local validation when that is honest.

Read the full file on GitHub · 411 lines

Changes

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.

12d ago First seen · 411 lines · 33 tokens per session scan A 1b75646c4696

Subscribe to this mod's changes

ac-qa-gh-pr-review is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 3,251 once invoked, about $0.0002 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.

Claude Code Code review Commits Git and workflow agentic ai config cursor workflow

work-unit-commits

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Gentleman-Programming/gentle-ai · 33 tokens

gza-task-improve

Address feedback for a gza task inline — reads review findings and/or unresolved comments, checks out the branch, fixes must-fix items and comments, runs verify, and commits.

mhawthorne/gza · 41 tokens

git-workflow

Use when working with Git — branch naming, commit messages, PR creation, rebasing, or the code review process — even when the user says 'push this' or 'merge the branch' without naming Git.

event4u-app/agent-config · 47 tokens

git-flow-pr

Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…

soulcodex/agentic · 103 tokens

github-pr-review

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, or verify PR readiness. Fetches comments via GitHub CLI, classifies by severity, applies fixes with user…

myths-labs/muse · 74 tokens

git-authoring

Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery…

n-shadloo/git-authoring · 220 tokens