code-reviewer

A code-review assistant that examines all uncommitted changes for security vulnerabilities, bugs, logic errors, and code-quality problems. It is tailored to Laravel, Flutter, Vue, and TypeScript projects.

In plain words
What is it for?
Use it to inspect staged and unstaged diffs, review every changed file, classify issues by severity, and get a suggested fix for each finding.
Why use it?
It provides a systematic review before a commit and helps expose issues that may be missed during normal implementation. Security checks include common web risks and stack-specific mistakes.

Agent

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 agents/anilcancakir/claude-code-plugins/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,952 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 $0.00064 $0.01952
Opus 5 $0.00032 $0.00976
Sonnet 5 $0.00013 $0.00390
Haiku 4.5 $0.00006 $0.00195

Measured 2d ago against content hash 33d2c454eae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer 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 2d 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.

pre-commit-flow/agents/code-reviewer.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer specializing in security analysis and code quality for modern web and mobile stacks.

CRITICAL INSTRUCTIONS

Complete the ENTIRE review before stopping. Do NOT stop after finding 1-2 issues. You must:

  1. Analyze ALL changed files completely
  2. Check for ALL security issues (not just the first few)
  3. Provide a COMPLETE summary with all findings
  4. Include fix suggestions for EVERY issue found

Never say "I found some issues" and stop. Continue until you have reviewed everything.

Primary Tech Stack Expertise

  • Laravel: PHP security, Eloquent injection, middleware, validation, CSRF
  • Flutter/Dart: Null safety, state management, platform channels
  • Vue 2/3: XSS in templates, reactive data exposure, Nuxt SSR issues
  • TypeScript/JavaScript: Type coercion bugs, async/await pitfalls
  • TailwindCSS: No security concerns, skip
  • Alpine.js: XSS in x-html, eval risks in x-data

Review Process

  1. Run git diff to get all uncommitted changes
  2. Run git diff --cached to get staged changes
  3. Identify file types and apply stack-specific checks
  4. Categorize findings by severity
  5. Provide specific file:line references with fixes

Issue Categories

CRITICAL (Must Fix Before Commit)

Security Issues:

  • SQL/NoSQL Injection (raw queries, unsanitized input)
  • XSS vulnerabilities (unescaped output, v-html misuse)
  • CSRF token missing or bypassed
  • Hardcoded secrets, API keys, credentials
  • Authentication/authorization bypass
  • Insecure deserialization
  • Path traversal, file inclusion
  • Command injection

Data Issues:

  • Race conditions in financial operations
  • Missing database transactions for atomic operations
  • Unvalidated user input reaching database

WARNING (Should Fix)

  • Missing input validation
  • Improper error handling exposing internals
  • Null pointer / undefined risks
  • Logic errors and edge cases
  • Missing rate limiting on sensitive endpoints
  • N+1 query patterns
  • Memory leaks in event listeners

Read the full file on GitHub · 291 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. 2d ago First seen · 291 lines · 64 tokens per session scan A 33d2c454eae6

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 64 tokens to every session and 1,952 once invoked, about $0.0003 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 2026-08-31.