ai-code-review

ai-code-review is a cursor rule for coding agents from bambooshadow-studio/mcp-power-pack. It costs 333 tokens per session, scanned A, original, MIT.

A code-review checklist for Python, JavaScript, TypeScript, Rust, and related files. It checks security, speed, correctness, and ease of maintenance before code is submitted.

In plain words
What is it for?
Use it to review code changes, find security and performance issues, check asynchronous and boundary cases, and improve names, structure, and documentation.
Why use it?
It helps catch common problems such as injection attacks, exposed passwords, missing error handling, slow database access, and unsafe edge cases before they reach users.

Cursor rule

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 rules/bambooshadow-studio/mcp-power-pack/ai-code-review
Clone the repo
git clone --depth 1 https://github.com/bambooshadow-studio/mcp-power-pack

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 ai-code-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/bambooshadow-studio/mcp-power-pack/ai-code-review.svg)](https://agentmods.dev/rules/bambooshadow-studio/mcp-power-pack/ai-code-review)
Your own site
<a href="https://agentmods.dev/rules/bambooshadow-studio/mcp-power-pack/ai-code-review"><img src="https://agentmods.dev/badge/rules/bambooshadow-studio/mcp-power-pack/ai-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 333 This file is loaded in full into every session.
When invoked 333 The same file — it is already loaded in full.
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 $0.00333 $0.00333
Opus 5 $0.00167 $0.00167
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00033 $0.00033

Measured 4d ago against content hash 2c36af53eb22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-code-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 4d 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.

pro/cursor-rules/ai-code-review.mdc · 52 lines

What it actually says

Rule Name: ai-code-review Description: Always review code for security, performance, correctness, and maintainability before submitting. Filters:

  • file: "*.py"
  • file: "*.js"
  • file: "*.ts"
  • file: "*.jsx"
  • file: "*.tsx"
  • file: "*.rs"

// CODE REVIEW CHECKLIST // Priority: Security > Performance > Correctness > Maintainability

Security

  • Check for injection vulnerabilities (SQL, XSS, command injection)
  • Verify authentication and authorization checks
  • Look for hardcoded secrets, API keys, passwords
  • Validate input sanitization

Performance

  • Identify N+1 query patterns
  • Check for unnecessary API calls or database queries
  • Look for memory leaks in closures and event listeners
  • Verify caching opportunities

Correctness

  • Check error handling paths (try/catch, error boundaries)
  • Verify edge cases (empty states, null/undefined, boundary values)
  • Check race conditions in async code
  • Validate type safety

Maintainability

  • Meaningful variable and function names
  • Single responsibility per function
  • DRY principle violations
  • Adequate documentation for complex logic

Output Format

## Security Issues (X found)
- CRITICAL: [issue] at [file:line]

## Performance Issues (X found)
- HIGH: [issue] at [file:line]

## Correctness Issues (X found)
- HIGH: [issue] at [file:line]

## Maintainability (X found)
- MEDIUM: [issue] at [file:line]
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. 4d ago First seen · 52 lines · 333 tokens per session scan A 2c36af53eb22

Subscribe to this mod's changes

ai-code-review is a cursor rule published in the GitHub repository bambooshadow-studio/mcp-power-pack (1 stars, last pushed 2mo ago), licensed MIT. It adds 333 tokens to every session, about $0.0017 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.