pr-review

pr-review is a skill for Claude Code, Codex from xxxxxccc/devops-bot. It costs 26 tokens per session (431 once invoked), scanned A, original, MIT.

A set of guidelines for reviewing pull requests, which are proposed code changes waiting to be merged into a project. It prioritizes security, correctness, error handling, performance, and maintainability.

In plain words
What is it for?
Use it to inspect code diffs, identify vulnerabilities, catch logic and error-handling problems, review performance risks, and write specific review comments.
Why use it?
It helps reviewers focus on defects and risks instead of spending time on formatting or minor style preferences. It also explains what issues should not be reported.

Skill for Claude CodeCodex

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/xxxxxccc/devops-bot/pr-review
Any agent
npx skills add xxxxxccc/devops-bot --skill pr-review
Clone the repo
git clone --depth 1 https://github.com/xxxxxccc/devops-bot

Made for: Claude Code, Codex.

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/xxxxxccc/devops-bot/pr-review.svg)](https://agentmods.dev/skills/xxxxxccc/devops-bot/pr-review)
Your own site
<a href="https://agentmods.dev/skills/xxxxxccc/devops-bot/pr-review"><img src="https://agentmods.dev/badge/skills/xxxxxccc/devops-bot/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 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 $0.00026 $0.00431
Opus 5 $0.00013 $0.00216
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 5d ago against content hash 645882b90b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

skills/pr-review/SKILL.md · 46 lines

What it actually says

PR Review Guidelines

Review Priority (highest to lowest)

  1. Security — vulnerabilities, exposed secrets, injection, auth bypass
  2. Correctness — logic errors, edge cases, data loss, race conditions
  3. Error Handling — unhandled exceptions, missing null checks, unclear error messages
  4. Performance — N+1 queries, unbounded loops, memory leaks, blocking I/O
  5. Maintainability — unclear naming, DRY violations, missing types, excessive complexity

What to Flag

  • Breaking API changes without versioning
  • Missing input validation on public interfaces
  • Hardcoded secrets, credentials, or environment-specific values
  • Database queries without indexes (when schema is visible)
  • Promises without error handling (.catch or try/catch)
  • Resource leaks (unclosed connections, file handles, timers)

What NOT to Flag

  • Style/formatting issues (handled by linters/formatters)
  • Import ordering
  • Trailing whitespace
  • Minor naming preferences when existing conventions are followed
  • Generated files, lock files, build artifacts

Comment Quality

  • Be specific: "Line 42: users.find() without .lean() returns full Mongoose documents, adding ~30% memory overhead" is better than "Consider performance"
  • Suggest fixes: Include a code snippet when the fix is non-obvious
  • Explain impact: "This could cause a memory leak in long-running processes because..."
  • Acknowledge good patterns: "Good use of discriminated unions here for type safety"

Severity Levels

  • critical: Must fix before merge. Security issues, data loss risks, correctness bugs.
  • warning: Should fix. Performance issues, missing error handling, fragile patterns.
  • suggestion: Nice to have. Better approaches, minor improvements.
  • nitpick: Purely optional. Naming tweaks, minor style preferences.
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 · 46 lines · 26 tokens per session scan A 645882b90b21

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository xxxxxccc/devops-bot (47 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 431 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.

Related

Other skills, from other repositories

setup

Add or remove notification channels (telegram, slack, teams, lark, webhook).

dz1922/claude-notify · 19 tokens

add-adapter

Add a vendor-official or community adapter to the Chat SDK catalog and docs — adapters.json registry, chat/adapters catalog entry, the docs MDX page, meta.json, integration-test lists, and a changeset. Use when a developer wants to add, list, register, or submit a third-party (vendor-official or community) adapter to…

vercel/chat · 109 tokens

chat-sdk

Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to scaffold a bot with create-chat-sdk, build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files…

vercel/chat · 108 tokens

update-model-pricing

Verify and refresh AgentConnect's daemon-side public OpenAI fallback pricing, exact model aliases, long-context and cache rules, and regression tests. Use when OpenAI model prices or IDs change, fallback cost becomes missing or stale, codex-acp changes its token mapping, or someone asks to audit or update…

agentconnect-md/agentconnect · 79 tokens

metabase-data-app-semantic-layer

Use when building, creating, or editing data apps that should query Metabase tables and metrics through generated schema files like metabase.data.ts or .metabase.data.ts.

metabase/metabase · 42 tokens

metabase-data-app-setup

Scaffold a new Metabase data-app into the connected remote-sync repository's dataapps/ / directory from the data-app-template. Use when the user asks to start, create, scaffold, or set up a data-app from scratch.

metabase/metabase · 58 tokens