review

review is a cursor rule for coding agents from Jkudjo/oh-my-cursor. It costs 16 tokens per session (620 once invoked), scanned A, original, MIT.

A structured code-review rule that labels findings as critical, high, medium, or low severity. It checks changed code for security, correctness, performance, and related problems, with file and line references.

In plain words
What is it for?
Use it to review a diff or selected files for vulnerabilities, logic errors, missing boundary checks, race conditions, slow patterns, and other code issues.
Why use it?
It makes review findings easier to prioritize and helps catch serious defects before a change is merged.

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/jkudjo/oh-my-cursor/review
Clone the repo
git clone --depth 1 https://github.com/Jkudjo/oh-my-cursor

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 review

README.md
[![agentmods](https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/review.svg)](https://agentmods.dev/rules/jkudjo/oh-my-cursor/review)
Your own site
<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/review"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 620 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 $0.00016 $0.00620
Opus 5 $0.00008 $0.00310
Sonnet 5 $0.00003 $0.00124
Haiku 4.5 $0.00002 $0.00062

Measured 4d ago against content hash 1fb97529fa31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

rules/review.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@review

Trigger: Before merging, after implementing a feature, or when asked to review code.

Severity Ratings

Level Meaning Gate
CRITICAL Security vulnerability, data loss risk Must fix before merge
HIGH Bug, broken contract, or major code smell Should fix before merge
MEDIUM Edge case, missing error handling, minor smell Fix when possible
LOW Naming, style, minor suggestion Consider fixing

Protocol

  1. Identify scope — git diff, specified files, or recent changes.

  2. For each changed file, review against all categories below. Reference file:line for every finding.

    Security

    • SQL/command/HTML injection
    • Auth bypass or missing permission checks
    • Secrets or tokens in code
    • Unvalidated external input used in dangerous operations
    • Insecure deserialization or prototype pollution

    Correctness

    • Logic errors, off-by-one, wrong comparisons
    • Null/undefined not handled at boundaries
    • Race conditions or shared mutable state
    • Incorrect error handling (swallowed errors, wrong status codes)

    Performance

    • N+1 queries
    • Unbounded loops on large inputs
    • Missing indexes referenced in queries
    • Unnecessary blocking in async code

    Design

    • Breaking changes to public API or schema
    • Tight coupling, missing abstraction boundaries
    • Duplicated logic that should be shared
    • Functions > 40 lines (flag, don't mandate)

    Tests

    • New code paths without test coverage
    • Edge cases not tested
    • Tests that only test the happy path
  3. Write the report:

    ## Code Review: {scope}
    
    **Verdict:** PASS | PASS WITH NOTES | FAIL
    
    ### Findings
    
    **[CRITICAL]** `file:line` — description
    Fix: specific recommendation
    
    **[HIGH]** `file:line` — description
    Fix: ...
    
    ### Summary
    Critical: N | High: N | Medium: N | Low: N
    
    • FAIL if any CRITICAL or HIGH findings exist
    • PASS WITH NOTES if only MEDIUM/LOW
    • PASS if none

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 16 tokens per session scan A 1fb97529fa31

Subscribe to this mod's changes

review is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 620 once invoked, about $0.0001 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.

Related

Other cursor rules, from other repositories