Skip to main content
skill CX Codex

review-code — Claude Code skill: what it does, how to install

review-code reviews active git changes through an experienced engineering perspective. Identifies SOLID flaws, architecture issues, and security vulnerabilities.

no license ★ 155 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add serpro69/claude-toolbox --skill review-code -a claude-code
Open on GitHub

What review-code does

The skill inspects local changes and outputs a structured assessment without altering code files unless requested. Its workflow enforces a strict order: helper protocols, profile discovery rules, and domain checklists load before the diff inspection starts. This deliberate sequence keeps the model from jumping straight to superficial assumptions based only on raw patch snippets.

Issues receive severity ratings from P0 to P3, where P0 represents critical threats that immediately halt a merge. Any systemic P0 or P1 finding is automatically stored under the kk:review-findings index. The tool supports standard single-thread analysis as well as an isolated review path.

Running $kk:review-code:isolated demands a working PAL setup that exposes client observations via listmodels. It spins up an independent internal reviewer and external model CLI calls to deliver an unbiased second opinion.

What it helps with

  • detect architecture regressions and SOLID violations in current commits
  • catch critical security defects prior to merging pull requests
  • run uncorrupted external code reviews using isolated agent sessions
  • categorize discovered bugs across four strict severity tiers from P0 to P3

Example prompts for the agent

  • Inspect current repository diff using $kk:review-code
  • Run an external multi-reviewer check with $kk:review-code:isolated
  • Evaluate staged git modifications against SOLID rules and security baselines

How to install review-code

1Skills CLI (Vercel)

npx skills add serpro69/claude-toolbox --skill review-code -a claude-code

2Manually: put the files in place

~/.claude/skills/review-code/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/review-code/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about review-code

How to install review-code in Claude Code?

Run npx skills add serpro69/claude-toolbox --skill review-code -a claude-code in your project terminal.

What does the review-code skill do?

It evaluates uncommitted git patches against SOLID principles and security baselines, generating a prioritized breakdown of findings from P0 to P3.

What is required to run the isolated review mode?

The isolated mode needs a PAL build whose listmodels command exposes CLI observations, alongside external model permissions configured for clink or API reviews.

Similar skills

All skills for Code review and refactoring →

From the same set30

The whole set →
model model reads one bounded context and leaves a glossary, a traps page, and a queue of questions that need a human answer. CX Codex +1 ★ 155repo stars architecture-reviewer The architecture-reviewer subagent for Claude Code independently checks architectural documents against repository code. It verifies declared structures, not runtime behavior. CX Codex ★ 155repo stars chain-of-verification chain-of-verification is a Claude Code skill that checks answers through independent questions and follow-up verification. It runs for fact-checking, technical claims, and multi-step reasoning. CX Codex +1 ★ 155repo stars review-architecture review-architecture is a Claude Code skill that checks a written architecture artifact against the system it describes. CX Codex +1 ★ 155repo stars review-design review-design is a Claude Code skill that checks design documents before implementation begins. It runs after $kk:design and reviews all documents by default. CX Codex +1 ★ 155repo stars review-spec review-spec is a Claude Code skill that compares code with feature docs and reports mismatches in both directions. Run it mid-feature or after completion. CX Codex +1 ★ 155repo stars design-reviewer design-reviewer audits feature designs and implementation plans without conversational bias. Flags ambiguities, missing edge cases, and contradictions before implementation begins. CX Codex ★ 155repo stars spec-reviewer The spec-reviewer subagent checks code against design documents to find missing work, mismatches, and conflicting or unclear docs. Use it for an independent implementation review. CX Codex ★ 155repo stars

Project sponsors

Companies that keep this analytics open