pr-review

pr-review is a skill for Claude Code from summarybotng/summarybot-ng. It costs 17 tokens per session (517 once invoked), scanned A, original, MIT.

A workflow for reviewing GitHub pull requests, which are proposed code changes awaiting approval. It reads the full change, checks whether it stays within the intended scope, and validates trust levels for changed skills.

In plain words
What is it for?
Reviewing a pull request from its number, summarizing what changed, checking included files and skills, and assessing trust-tier assignments.
Why use it?
It reduces missed changes, scope leaks, unclear review comments, and incorrect trust assignments. The review is written in plain language with specific actions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Reviewing a pull request from its number, summarizing what changed, checking included files and skills, and assessing trust-tier assignments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/summarybotng/summarybot-ng/pr-review
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.

Any agent
npx skills add summarybotng/summarybot-ng --skill pr-review
Clone the repo
git clone --depth 1 https://github.com/summarybotng/summarybot-ng

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 pr-review

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

agentmods 80×15 button for pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/pr-review"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 517 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 $0.00017 $0.00517
Opus 5 $0.00009 $0.00259
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00002 $0.00052

Measured 5d ago against content hash e3d4b9588806, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 5d 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/pr-review/SKILL.md · 62 lines

What it actually says

PR Review Workflow

Review pull requests with correct AQE scope boundaries, clear communication, and actionable feedback.

Arguments

  • <pr-number> — GitHub PR number to review. If omitted, prompt the user.

Steps

1. Read the Full Diff

gh pr diff <pr-number>
gh pr view <pr-number>

Read the complete diff and PR description. Do not skim — read every changed file.

2. Scope Check

  • Only analyze AQE/QE skills (NOT Claude Flow platform skills)
  • Platform skills to EXCLUDE: v3-, flow-nexus-, agentdb-, reasoningbank-, swarm-, github-, hive-mind-advanced, hooks-automation, iterative-loop, stream-chain, skill-builder, sparc-methodology, pair-programming, release, debug-loop, aqe-v2-v3-migration
  • If the PR touches skills, verify the count/scope matches expectations (~78 AQE skills)
  • Flag any platform skill changes that may have leaked into an AQE-focused PR

3. Summarize Changes

Write a user-friendly summary of what changed and why:

  • Focus on outcomes, not implementation details
  • Avoid overly technical jargon
  • Keep it to 3-5 bullet points

4. Trust Tier Validation

For any skill changes, validate trust_tier assignments:

  • tier 3 = has eval infrastructure (evals/, schemas/, scripts/)
  • tier 2 = tested but no eval framework
  • tier 1 = untested
  • Flag inconsistencies (e.g., a skill with evals at tier 2 should be tier 3)

5. Code Quality Review

Check for:

  • Hardcoded version strings
  • Production safety concerns (adapter changes, breaking changes)
  • Missing test coverage for new code
  • Security issues (exposed secrets, injection risks)

6. Post Review

gh pr review <pr-number> --body "review comments"

Communication Rules

  • Keep tone constructive and actionable
  • Be outcome-focused: what should the author do, not what's wrong
  • Group related comments together instead of posting many small ones
  • If approving with minor suggestions, use APPROVE with comments, not REQUEST_CHANGES
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. 5d ago First seen · 62 lines · 17 tokens per session scan A e3d4b9588806

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 517 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 2026-09-03.