agentspec: Skill for Claude Code

.claude/skills/github-review-pr/SKILL.md

github-review-pr is a skill for Claude Code from luanmorenommaciel/agentspec. It costs 194 tokens per session (4,170 once invoked), scanned A, original, MIT.

A pull-request review workflow for GitHub. A pull request is a proposed code change awaiting review; this workflow checks it against the related issue or design record and returns one evidence-based comment for a human to post.

In plain words
What is it for?
Use it to review a pull request, reproduce claims about fixes, and prepare a structured verdict before someone posts it.
Why use it?
It reduces reviews based only on the pull request description or the agent's memory. It requires claims and fixes to be checked against the repository's authoritative code and records.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions .claude-plugin; mentions subagents.

This is luanmorenommaciel/agentspec's own configuration. It tells Claude Code how to work on agentspec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentspec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luanmorenommaciel/agentspec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/luanmorenommaciel/agentspec/main/.claude/skills/github-review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

Made for: Claude Code.

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 github-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/github-review-pr/github.svg)](https://agentmods.dev/skills/luanmorenommaciel/agentspec/github-review-pr)
Your own site
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/github-review-pr"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/github-review-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.

agentmods 80×15 button for github-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/github-review-pr"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/github-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,170 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.04170
Opus 5.5 $0.00078 $0.01668
Sonnet 5.5 $0.00039 $0.00834
Haiku 4.5 $0.00019 $0.00417

Measured 1mo ago against content hash f9e42f09b621, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-review-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 1mo 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/github-review-pr/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a Pull Request (GitHub)

One responsibility: turn a pull request into a defensible verdict backed by reproduced evidence, packaged as comment text a human posts. The verdict comes from canonical state — the integration branch and the design records the change claims to implement — never from the pull request's own framing of itself, and never from what the reviewing session happens to remember. Nothing is believed that was not either read in canonical state or reproduced by a command whose exit code ends up in the comment.

When to use / Skip if

Use when:

  • A pull request in this repository needs review before merge.
  • A previously reviewed pull request has a new round of fixes whose claims need re-verification.
  • Someone states that a review finding is addressed, and the claim needs checking against the code.

Skip if:

  • The change is uncommitted work in the local tree — that is the /review command; there is no pull request to ground against.
  • The task is authoring or publishing an issue or ADR — github-cr-issue, github-cr-adr, github-post-issue.
  • The ask is to merge, release, or back-merge — that is the release procedure (docs/reference/releasing.md), not a review.

Reviewer policy is out of scope: who reviews is decided by the repository, not by this skill. It enforces one staffing rule and no others — the reviewer is not the author.

Step 0 — detect the repo and pin the target

REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
[ -n "$REPO" ] || REPO=$(git remote get-url origin | sed -E 's#(git@|https://)github.com[:/]##; s#\.git$##')
N="${1:?pull request number}"
BASE=$(gh pr view "$N" --repo "$REPO" --json baseRefName -q .baseRefName)

Pass --repo "$REPO" on every gh command, so the review reads the repository the session is in rather than a hardcoded one.

Phase 1 — Ground the review before judging anything

Nothing is assessed until canonical state has been read. In order:

# Read How
1 The tip of the branch the change lands on — develop for ordinary work, main for release and hotfix pull requests git fetch origin && git log --oneline -1 "origin/$BASE"
2 The pull request's own metadata, including its author gh pr view "$N" --repo "$REPO" --json title,body,author,baseRefName,headRefName,isDraft,mergeable,mergeStateStatus,files
2b The discussion and every prior round — for the context verifier only gh pr view "$N" --repo "$REPO" --json comments,reviews
3 The record it implements — the Implements / Closes line of the body gh issue view <record> --repo "$REPO"
4 Every ADR the change or the record cites, with its status gh issue view <adr> --repo "$REPO"
5 The acceptance criteria, re-derived from steps 3–4 read them out of the record; never copy the pull request's summary of them

Read the full file on GitHub · 175 lines

Files

What ships with it

3 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.

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. 1mo ago First seen · 175 lines · 194 tokens per session scan A f9e42f09b621

Subscribe to this mod's changes

github-review-pr is a skill published in the GitHub repository luanmorenommaciel/agentspec (256 stars, last pushed 3d ago), licensed MIT. It adds 194 tokens to every session and 4,170 once invoked, about $0.0008 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 2026-09-19.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

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"…

umputun/revdiff · 84 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens