A pull request review workflow for GitHub, GitLab, or Forgejo. A pull request, also called a merge request on GitLab, proposes changes for review before they are added to a project.

Use it to fetch a pull request's details and changes, then inspect the proposal for defects, security concerns, and missing or inadequate tests.

It brings code quality, security, and test-coverage checks into one review of the proposed changes.

analyze-pr — Skill for Claude Code by sgaunet/claude-plugins

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 sgaunet/claude-plugins --skill analyze-pr

Clone the repo

git clone --depth 1 https://github.com/sgaunet/claude-plugins

Made for: Claude Code.

Or install software-engineering, the plugin that ships this one along with the rest of its 18 skills, 7 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sgaunet/claude-plugins/analyze-pr/github.svg)](https://agentmods.dev/skills/sgaunet/claude-plugins/analyze-pr)

Your own site

<a href="https://agentmods.dev/skills/sgaunet/claude-plugins/analyze-pr"><img src="https://agentmods.dev/badge/skills/sgaunet/claude-plugins/analyze-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sgaunet/claude-plugins/analyze-pr"><img src="https://agentmods.dev/badge/skills/sgaunet/claude-plugins/analyze-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,572 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.01572
Opus 5.5	$0.00009	$0.00629
Sonnet 5.5	$0.00005	$0.00314
Haiku 4.5	$0.00002	$0.00157

Measured 22d ago against content hash 2ece7ebdcb4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

analyze-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 22d 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.

plugins/software-engineering/skills/analyze-pr/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Pull Request

Perform comprehensive analysis of a pull request including code review, security scan, and test coverage.

Process

Detect Repository Type: Use the detect-repo-host skill to identify the hosting service (GitHub, GitLab, or Forgejo) and extract owner/repo details.
Fetch PR Details: Use the appropriate CLI
- GitHub: gh pr view <number> --json title,body,author,files,commits, gh pr diff <number>
- GitLab: glab mr view <number>, glab mr diff <number>
- Forgejo: fgj pr view <number> -R <owner>/<repo> --json for metadata. fgj has no pr diff subcommand — obtain the diff via a git fallback:
  1. From the fgj pr view JSON, read the head and base branch names.
  2. git fetch origin
  3. git diff origin/<base>...origin/<head>
  This works for same-repo PRs (both branches exist on origin); it does not cover cross-fork PRs whose head lives in a different repository. As a secondary option, fetch the diff directly from the Forgejo API: GET <api_base>/repos/<owner>/<repo>/pulls/<n>.diff, where <api_base> is the field returned by the detect-repo-host skill (e.g. https://git.sylvlab.fr/api/v1). Never hardcode a host — it breaks on every other Forgejo instance.
Analyze Changes: Launch 4 parallel Sonnet agents to independently review the pull request:

Agent #1: Code Quality Review (code-review-enforcer agent)
- Review modified files for code quality issues
- Check for logic errors, error handling, performance issues
- Verify adherence to coding standards
- Return: list of issues with severity levels and line numbers
Agent #2: Security Analysis (security-auditor agent)
- Scan for security vulnerabilities in modified files
- Focus on auth/crypto changes, input validation, SQL injection
- Check for exposed secrets or sensitive data
- Return: list of security findings with CVSS-like severity ratings
Agent #3: Test Coverage Assessment
- Analyze modified files to identify new functionality
- Check if corresponding tests were added
- Evaluate test quality and edge case coverage
- Return: coverage report with missing test scenarios

Read the full file on GitHub · 143 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.

22d ago First seen · 143 lines · 23 tokens per session scan A 2ece7ebdcb4d

Subscribe to this mod's changes

analyze-pr is a skill published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 1,572 once invoked, about $0.0001 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 2026-09-25.

Claude Code Code review DevOps and cloud Security ai-agents claude-code-marketplace claude-code-plugins developer-tools

code-review

Review code for actionable defects. Correctness is the core; performance and security are optional sub-cases of the same engine. Anchors on agreements between participants across a boundary, forces a violating execution, and refutes every candidate before reporting. Use when asked to review changes, find bugs, audit a…

phuryn/pm-skills · 74 tokens

intended-vs-implemented

The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy…

phuryn/pm-skills · 95 tokens

team-review

Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…

NikiforovAll/claude-code-rules · 65 tokens

roslyn-query

Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.

NikiforovAll/claude-code-rules · 44 tokens

review-pr

Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…

jontsai/claude-plugins · 139 tokens

meta-review

Audits any SKILL.md in this repo against SKILL-SPEC.md, the skill authoring standard — checks frontmatter, the seven required sections, tier-appropriate sections, and quality-gate structure, then returns a scored checklist with prioritized fixes. Trigger on: "review this skill", "audit this SKILL.md", "does this skill…

stefanoskarakasis/Product-Marketing-Skills · 104 tokens