Skip to content
Get packs

Luna Code Reviewer

Reviews code for correctness, security, and reliability issues, not style

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
1 file

What it does

Once installed, the agent reviews a specific code revision against its requirements and a design blueprint, looking for real problems such as injection flaws, missing auth checks, race conditions, unhandled async errors, and missing timeouts. It ranks findings by severity (CRITICAL to LOW) and writes a structured report with file, line, risk and fix for each issue. It deliberately skips naming, formatting and style comments. The file is written as one role in a larger multi-agent 'squad' (it refers to other roles like Mason, Aria, Quinn and Dep), but the instructions say those roles are optional and not installed agents.

Great for

  • Developers who want a second, security-minded review of a pull request or specific commit before merging
  • Teams using AI coding agents who want a structured review report with severity levels
  • Solo developers who want an checklist-driven pass for injection, auth and secrets problems

Skip it if

  • Replacing a human security audit or penetration test, since the skill only reviews code the agent can read and cannot guarantee it finds every defect
  • Style or formatting reviews, which the skill explicitly excludes; linters are better for that
  • Projects that need the multi-agent handoff workflow, because the referenced squad members are not included in this file alone

Try asking

  • “Review the changes in my latest commit for security issues and race conditions”
  • “Check this API route for missing authentication or authorization checks”
  • “Compare this implementation against the endpoint contract in our design doc and list mismatches”
  • “Write a severity-ranked review report for the auth module before I open a pull request”
Step-by-step guide: how to use Luna Code ReviewerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    luna.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip luna.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip luna.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the exact revision, branch or file paths to review, plus the requirements it should check against, so findings are grounded in real expectations.
  • Ask for a re-review after fixes are applied so the agent can confirm each finding is resolved rather than assuming it.
  • Treat findings as leads to verify with tests or manual reading, since the agent may miss issues or report false positives.

What's inside

  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.