Borrowing it
Nothing to install: this file belongs to bablsoft/accessflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bablsoft/accessflow/main/.claude/skills/review-gh-pr/SKILL.mdgit clone --depth 1 https://github.com/bablsoft/accessflowWrote 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/bablsoft/accessflow/review-gh-pr)<a href="https://agentmods.dev/skills/bablsoft/accessflow/review-gh-pr"><img src="https://agentmods.dev/badge/skills/bablsoft/accessflow/review-gh-pr/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/bablsoft/accessflow/review-gh-pr"><img src="https://agentmods.dev/badge/skills/bablsoft/accessflow/review-gh-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 226 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Excessive Agency · line 260 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00092 | $0.03641 |
| Opus 5.5 | $0.00037 | $0.01456 |
| Sonnet 5.5 | $0.00018 | $0.00728 |
| Haiku 4.5 | $0.00009 | $0.00364 |
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 2mo 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 — 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.
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.
- 2mo ago First seen · 262 lines · 92 tokens per session scan A df4afc91c933
review-gh-pr is a skill published in the GitHub repository bablsoft/accessflow (11 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 3,641 once invoked, about $0.0004 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
app-store-compliance
Run an enterprise pre submission compliance audit on a mobile app project before uploading to the Apple App Store or Google Play. Use when the user is about to submit, ship, or release an iOS or Android app, when an app was rejected and needs a fix plan, when reviewing App Store Review Guidelines or Google Play policy…
reviewable-pr
Prepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance. Trigger: 'make easy to review', 'tidy PR', 'clean up commits', 'annotate diff'.
standup-summary
Summarize work completed over a time period using git commits + CK session data. Trigger: 'what did I get done', 'standup', 'weekly summary', 'status update'.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.