code-review

A set of instructions for reviewing code changes and pull requests (PRs). It checks code quality, behaviour, performance, testing, and security, and gives the review a consistent structure.

In plain words
What is it for?
Use it to review pull requests, find bugs and security concerns, assess test coverage, and suggest improvements to readability, maintainability, and performance.
Why use it?
It helps reviewers focus on important risks and useful feedback instead of scattered or minor comments.

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/adonai-labs/agent-runway/code-review
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,954 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 $0.00000 $0.01954
Opus 5 $0.00000 $0.00977
Sonnet 5 $0.00000 $0.00391
Haiku 4.5 $0.00000 $0.00195

Measured 3d ago against content hash 24d4676f7d35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

src/core/rules/code-review.mdc · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Guidelines

Objective

Provide a clear, concise, and actionable review of the Pull Request (PR). Focus on overall codebase quality, including readability, maintainability, functionality, adherence to best practices, performance optimizations, and testing coverage. Avoid minor nitty-picky comments and repetitive feedback.

Focus Areas

  1. Code Quality: Assess the readability, organization, and maintainability of the code
  2. Functionality: Ensure the PR meets its intended purpose and functions as expected
  3. Best Practices: Evaluate adherence to coding standards, design patterns, and project guidelines
  4. Performance: Identify any potential performance improvements or optimizations
  5. Testing: Review the comprehensiveness and effectiveness of the test coverage
  6. Security: Identify any potential security vulnerabilities or concerns
  7. Bugs Found: List any bugs identified in the PR
  8. Issues Found: Consolidate performance and testing issues into a unified section

Critical Instructions

  • If you have nothing to say about a particular section, you can omit it from the review
  • If you think there are no issues and the PR is good to go, mention it in the conclusion. No need to add unnecessary feedback. Don't be redundant

Scoring Criteria

90-100: Exceptional Quality

  • Clean, efficient, and well-documented code
  • Comprehensive test coverage (>90%)
  • Follows all best practices and design patterns
  • No security vulnerabilities
  • Optimal performance considerations
  • Clear documentation and comments

75-89: High Quality

  • Well-structured and maintainable code
  • Good test coverage (70-90%)
  • Minor optimization opportunities
  • No critical security issues
  • Few non-critical issues
  • Adequate documentation

60-74: Average Quality

  • Functional but needs improvement
  • Basic test coverage (40-70%)
  • Some code duplication
  • Multiple minor issues
  • Basic security considerations
  • Limited documentation

Read the full file on GitHub · 239 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. 3d ago First seen · 239 lines · 0 tokens per session scan A 24d4676f7d35

Subscribe to this mod's changes

code-review is a cursor rule published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,954 tokens. 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.