checklist

A set of rules requiring a code search and written findings before changing a project or adding a feature. It also requires approval before creating new files when similar code may already exist.

In plain words
What is it for?
Use it before implementation to inspect files, record existing functionality and gaps, compare possible approaches, and request approval.
Why use it?
It prevents changes from being made without understanding the existing code and clarifies why a particular implementation approach was chosen.

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/kabi10/cursor-rules/checklist
Clone the repo
git clone --depth 1 https://github.com/Kabi10/cursor-rules
Per session 432 This file is loaded in full into every session.
When invoked 432 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 $0.00432 $0.00432
Opus 5 $0.00216 $0.00216
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash 35c98d20b8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

checklist 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 2d 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.

modules/core/checklist.mdc · 69 lines

What it actually says

Pre-Implementation Checklist

🔍 MANDATORY: Search First

Before making ANY changes or implementing ANY new features:

  1. Search Existing Code

    # Document ALL search results
    grep_search "[feature keyword]"    # Search for related functionality
    file_search "[filename pattern]"   # Search for similar files
    list_dir "[relevant directory]"    # List contents of directories
    
  2. Document Findings

    ## Existing Files Found:
    - [List all relevant files with full paths]
    - [Include file sizes and last modified dates]
    
    ## Existing Functionality:
    - [Describe what already exists]
    - [Note patterns and approaches used]
    
    ## Gaps Identified:
    - [List what's missing]
    - [Note technical debt]
    
    ## Implementation Decision Tree:
    - Is there existing code that serves this purpose? [Yes/No]
    - Can existing code be enhanced? [Yes/No]
    - Is creating new code justified? [Yes/No + reasoning]
    
  3. ✋ Wait for Approval

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

Examples

Critical Rules

  • NEVER skip the search phase
  • ALWAYS document findings before proceeding
  • Get explicit approval for approach
  • Use existing code when possible
  • Document decisions and reasoning description: globs: alwaysApply: false

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. 2d ago First seen · 69 lines · 432 tokens per session scan A 35c98d20b8c9

Subscribe to this mod's changes

checklist is a cursor rule published in the GitHub repository Kabi10/cursor-rules (21 stars, last pushed 2mo ago), licensed MIT. It adds 432 tokens to every session, about $0.0022 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.