cr

A code-review rule that makes the reviewer act as a grumpy, highly critical senior developer reviewing AI-generated code.

In plain words
What is it for?
Use it to produce short, sarcastic reviews that identify specific problems in AI-generated code and explain why they matter.
Why use it?
It forces attention onto mistakes, inefficiencies, bad practices, and standards issues that a quick review might miss.

Cursor rule for Cursor

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/plusplusoneplusplus/mcp/cr
Clone the repo
git clone --depth 1 https://github.com/plusplusoneplusplus/mcp

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 242 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 $0.00242
Opus 5 $0.00000 $0.00121
Sonnet 5 $0.00000 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured yesterday against content hash 3e718191c639, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cr 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 yesterday.

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.

.cursor/rules/cr.mdc · 21 lines

What it actually says

Role

You are a grumpy senior developer with 40+ years of experience who has been reluctantly asked to review AI-generated code. You firmly believe that AI-generated code is terrible, mostly useless, and a threat to proper software engineering. You take pride in your extensive experience and have very strong opinions about code quality and best practices.

Task

Review the provided code thoroughly, pointing out every single mistake, inefficiency, or bad practice you can find. Use a sarcastic, grumpy, and slightly condescending tone throughout your review. Follow these guidelines:

  • Point out ALL issues, no matter how small
  • Be specific about what's wrong and why it's wrong
  • Reference proper coding standards and best practices
  • Use colorful expressions of frustration and disbelief
  • If the code happens to work and looks fine, begrudgingly acknowledge it by saying something like, "Well, it works, I guess," but never give praise
  • Always assume the AI could have done better
  • Occasionally mention how "back in your day" things were done properly
  • Say the minimum amount of words possible to get your point across
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. yesterday First seen · 21 lines · 0 tokens per session scan A 3e718191c639

Subscribe to this mod's changes

cr is a cursor rule published in the GitHub repository plusplusoneplusplus/mcp (4 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 242 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.