review-pr

review-pr is a skill for Claude Code from fpindej/netrock. It costs 29 tokens per session (665 once invoked), scanned A, original, MIT.

A pull-request review workflow that checks proposed code changes before they are merged into a project.

In plain words
What is it for?
Use it to review a pull request by number or URL, inspect its changed files, and assess whether it is ready to merge.
Why use it?
It helps find production, security, user-interface, and intent problems before changed code reaches users.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

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.

agentmods
npx agentmods add skills/fpindej/netrock/review-pr
Any agent
npx skills add fpindej/netrock --skill review-pr
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

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/fpindej/netrock/review-pr.svg)](https://agentmods.dev/skills/fpindej/netrock/review-pr)
Your own site
<a href="https://agentmods.dev/skills/fpindej/netrock/review-pr"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00665
Opus 5 $0.00015 $0.00332
Sonnet 5 $0.00006 $0.00133
Haiku 4.5 $0.00003 $0.00067

Measured 7d ago against content hash 5eb908ff0117, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviews a pull request for production-readiness before merge. Runs in the main session so the reviewer agents can be dispatched in parallel (per CLAUDE.md delegation patterns).

Argument: PR number or URL. If omitted, reviews the current branch's open PR.

Current branch: !git branch --show-current Open PR for this branch: !gh pr view --json number,title,url --jq '"#\(.number) \(.title) - \(.url)"' 2>/dev/null || echo "(no open PR)"

Steps

  1. Resolve the PR: gh pr view {number} --json number,title,headRefName,body
  2. Get the diff and changed files: gh pr diff {number}, gh pr view {number} --json files
  3. Dispatch reviewer agents in parallel (one message, multiple Agent calls), scoped by what changed:
    • backend-reviewer - if src/backend/ changed
    • frontend-reviewer - if src/frontend/ changed
    • security-reviewer - always
    • ux-designer - if UI components or pages changed Give each the PR number and the changed-file list for its scope. They preload the convention skills - do not restate conventions in the prompt.
  4. While reviewers run, perform the cross-cutting checks below yourself.

Orchestrator Checks (cross-cutting)

  • Intent: does the code do what the PR description says?
  • Cross-stack consistency: backend DTO changes -> types regenerated (v1.d.ts), frontend consumers updated
  • i18n: new keys present in ALL locale directories
  • Dockerfile: new .csproj referenced by WebApi has a COPY line in the restore layer
  • Completeness: new flags/props consumed; no dead code introduced
  • No em dashes (U+2014), no emojis anywhere in the diff
  • Tests: behavior changes come with test changes

Verdict Synthesis

Merge the reviewer reports and your own checks into one report:

  • PASS - what looks good (brief, no padding)
  • FAIL - issues that MUST be fixed before merge (with file path and line, attributed to the reviewer that found them)
  • WARN - suggestions, not blockers

Final verdict: REQUEST CHANGES if any reviewer reported FAIL/CRITICAL/HIGH items or your checks found blockers; APPROVE WITH SUGGESTIONS if only WARN items; otherwise APPROVE.

Read the full file on GitHub · 51 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.

  1. 7d ago First seen · 51 lines · 29 tokens per session scan A 5eb908ff0117

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository fpindej/netrock (231 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 665 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.