Agent-First-Organization: Skill for Claude Code

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

review-pr is a skill for Claude Code from arklexai/Agent-First-Organization. It costs 10 tokens per session (424 once invoked), scanned A, original, MIT.

A checklist for reviewing a pull request, a proposed set of code changes, against a project's standards.

In plain words
What is it for?
Use it to inspect a pull request's description and code changes, check tests and coverage, and report functional or architectural findings.
Why use it?
It focuses review on behavior, edge cases, security, compatibility, scope, and tests instead of only formatting.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

This is arklexai/Agent-First-Organization's own configuration. It tells Claude Code how to work on Agent-First-Organization 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 Agent-First-Organization configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arklexai/Agent-First-Organization. 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/arklexai/Agent-First-Organization/main/.claude/skills/review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arklexai/Agent-First-Organization

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 review-pr

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/arklexai/agent-first-organization/review-pr"><img src="https://agentmods.dev/badge/skills/arklexai/agent-first-organization/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 424 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 $0.00010 $0.00424
Opus 5 $0.00005 $0.00212
Sonnet 5 $0.00002 $0.00085
Haiku 4.5 $0.00001 $0.00042

Measured 10d ago against content hash 1f707f2decac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 10d 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-pr/SKILL.md · 68 lines

What it actually says

Review PR

Review a PR for functional correctness and project conventions. Focus on logic, architecture, and behavior. Formatting issues are caught by CI (ruff, pre-commit) and do not need manual review.

Steps

1. Load PR context

gh pr view $ARGUMENTS --json title,body,files,additions,deletions
gh pr diff $ARGUMENTS

2. Validate PR title and description

  • Title matches Conventional Commits regex, under 72 chars
  • Description sections meet word minimums (Summary 5w, Description 10w, Tests 10w)
  • These are also CI-enforced, so flag only if CI somehow missed them

3. Review functional changes

Focus on:

  • Logic correctness: does the code do what the PR claims?
  • Edge cases: are error paths handled?
  • API changes: are they backwards compatible or properly marked as breaking?
  • Security: no hardcoded secrets, no unsanitized input in dangerous contexts
  • Performance: any obvious inefficiencies?

5. Check scope

  • Single concern per PR
  • Flag unrelated changes bundled together

6. Check test coverage

  • New behavior should have tests
  • Coverage minimum is 45%. Flag large additions without tests.

Output

## Summary
One-sentence assessment.

## Findings
- List issues grouped by severity (blocking, suggestion, nit)

## Checklist
- [ ] Title matches Conventional Commits
- [ ] Description sections meet word minimums
- [ ] Functional correctness verified
- [ ] Tests cover new/changed code
- [ ] No secrets in diff

End with: APPROVED, CHANGES REQUESTED, or NEEDS DISCUSSION.

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. 10d ago First seen · 68 lines · 10 tokens per session scan A 1f707f2decac

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository arklexai/Agent-First-Organization (699 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 424 once invoked, about $0.0001 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.