review-gh-pr

review-gh-pr is a skill for Claude Code, Codex from bablsoft/accessflow. It costs 92 tokens per session (3,641 once invoked), scanned A, original, Apache-2.0.

A read-only workflow for reviewing an existing GitHub pull request, which is a proposed code change. It checks the change in a separate temporary worktree and combines reviews from several viewpoints.

In plain words
What is it for?
It explains what the pull request changes, checks conventions, security, frontend code, and broader inconsistencies, and can optionally run local build checks.
Why use it?
It lets you inspect a pull request without changing your current files or writing anything back to GitHub.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bablsoft/accessflow/review-gh-pr
Any agent
npx skills add bablsoft/accessflow --skill review-gh-pr
Clone the repo
git clone --depth 1 https://github.com/bablsoft/accessflow

Made for: Claude Code, Codex.

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.

agentmods badge for review-gh-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/bablsoft/accessflow/review-gh-pr.svg)](https://agentmods.dev/skills/bablsoft/accessflow/review-gh-pr)
Your own site
<a href="https://agentmods.dev/skills/bablsoft/accessflow/review-gh-pr"><img src="https://agentmods.dev/badge/skills/bablsoft/accessflow/review-gh-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.03641
Opus 5 $0.00046 $0.01820
Sonnet 5 $0.00018 $0.00728
Haiku 4.5 $0.00009 $0.00364

Measured 4d ago against content hash df4afc91c933, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-gh-pr 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 4d 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.

.claude/skills/review-gh-pr/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a GitHub pull request

CLAUDE.md is the authoritative rulebook and the agents under .claude/agents/ do the actual reviewing. This skill only adds the workflow that gets a PR onto disk, fans them out, and turns their reports into something you can choose from.

Three properties define it:

  • It explains the PR before it critiques it. The first thing you get is what the change actually does — read from the diff, not from the description — so the findings that follow have somewhere to land.
  • Your working tree is never touched. The PR head goes into a throwaway git worktree. You can review a PR in the middle of your own work, on a dirty tree, without stashing.
  • It never writes to GitHub. Not a comment, not a review, not an API call. The selected findings come back as markdown you paste yourself.

Inputs

A PR number (735), a #-prefixed number (#735), or a GitHub pull-request URL. Optional flag:

Flag Effect
--verify Also dispatch af-verifier to run the real build gates locally. Slow — a backend PR pays a full mvn verify -Pcoverage. Without it, report gh pr checks instead, since CI already ran them.

If the user omits the number, ask for it once and stop. Do not guess from gh pr list — the wrong PR reviewed silently is worse than a question.

Workflow

1. Resolve the PR

gh pr view <n> --json number,title,body,url,state,author,headRefName,headRefOid,baseRefName,isCrossRepository,additions,deletions,files
gh pr checks <n>
gh api repos/<owner>/<repo>/pulls/<n> --jq .base.sha      # the PR's base commit — see below

gh pr checks exits non-zero when checks are failing or pending — that is data, not an error; capture the output and carry on.

base.sha is load-bearing — do not substitute origin/<baseRefName> for it. For a merged PR the head is already an ancestor of the base branch, so git merge-base HEAD origin/main returns HEAD itself and the diff comes back empty — every agent would then report "no files touched, VERDICT: approve", which is the worst possible failure: a silent false pass. base.sha is the commit the PR was actually opened against, and it gives the right diff for open and merged PRs alike. Sanity-check it: git diff --shortstat <base.sha>...<headRefOid> must match the additions/deletions from gh pr view. If it does not, stop and say so rather than reviewing a diff you cannot account for.

Read the full file on GitHub · 262 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.

  1. 4d ago First seen · 262 lines · 92 tokens per session scan A df4afc91c933

Subscribe to this mod's changes

review-gh-pr is a skill published in the GitHub repository bablsoft/accessflow (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 3,641 once invoked, about $0.0005 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 2026-08-31.