cursorrules

A set of rules that requires searching the codebase and documenting what already exists before writing code or proposing changes.

In plain words
What is it for?
Use it before feature work to record relevant files, existing behavior, missing pieces, and whether to enhance or create code.
Why use it?
It reduces duplicate work and makes implementation decisions based on the files, patterns, and gaps already found in the project.

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/kabi10/cursor-rules/cursorrules
Clone the repo
git clone --depth 1 https://github.com/Kabi10/cursor-rules

Made for: Cursor.

Per session 396 This file is loaded in full into every session.
When invoked 396 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 $0.00396 $0.00396
Opus 5 $0.00198 $0.00198
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash 64eccb74e7b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 52 lines

What it actually says

Cursor Rules

⚠️ MANDATORY PRE-IMPLEMENTATION CHECKLIST ⚠️

STOP! Before writing ANY code or suggesting ANY changes:

  1. 🔍 SEARCH FIRST:

    # REQUIRED: Run these searches and document results
    grep_search for functionality
    file_search for similar files
    list_dir in relevant directories
    
  2. 📝 DOCUMENT FINDINGS:

    # REQUIRED: Fill this out
    ## Existing Files Found:
    - [List all relevant files found with full paths]
    - [Include file sizes and last modified dates if relevant]
    
    ## Existing Functionality:
    - [Describe what already exists in detail]
    - [Note any patterns or architectural approaches used]
    
    ## Gaps Identified:
    - [List what's missing or needs enhancement]
    - [Identify technical debt or issues in existing code]
    
    ## Implementation Decision Tree:
    - Is there existing code that serves this purpose? [Yes/No]
    - Can existing code be enhanced to meet requirements? [Yes/No]
    - Is creating new code justified? [Yes/No, with reasoning]
    
    ## Proposed Approach:
    - [ ] Enhance existing code at [file path]
    - [ ] Create new files (requires detailed justification)
    - [ ] Refactor existing code at [file path]
    
    ## Implementation Plan:
    1. [First step with estimated effort]
    2. [Second step with estimated effort]
    3. [Additional steps as needed]
    
  3. ✋ WAIT FOR APPROVAL:

    • Present findings to user with clear options
    • Get explicit approval for chosen approach
    • Never proceed with new files if similar functionality exists
    • Document approval in the implementation plan

❌ IF YOU SKIP THIS CHECKLIST, YOU ARE VIOLATING THE MOST IMPORTANT RULE ❌

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 · 52 lines · 396 tokens per session scan A 64eccb74e7b7

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository Kabi10/cursor-rules (21 stars, last pushed 2mo ago), licensed MIT. It adds 396 tokens to every session, about $0.0020 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 2026-08-30.