derived-cursor-rules

A set of coding rules generated from a project's past interactions with an AI assistant. It covers documentation, naming, coding standards, workflow, and release practices.

In plain words
What is it for?
It is for guiding AI-assisted work in a project, including file naming, documentation, build commands, and release-related procedures.
Why use it?
It gives the assistant project-specific guidance so future changes follow established conventions instead of starting without context.

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/kevinslin/skillz/derived-cursor-rules
Clone the repo
git clone --depth 1 https://github.com/kevinslin/skillz

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,368 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 $0.01368
Opus 5 $0.00000 $0.00684
Sonnet 5 $0.00000 $0.00274
Haiku 4.5 $0.00000 $0.00137

Measured 2d ago against content hash 5ee52b9b5b9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

derived-cursor-rules 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.

.cursor/rules/derived-cursor-rules.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Headers

This document defines the rules, coding standards, workflow guidelines, references, documentation structures, and best practices for the AI coding assistant. It is a living document and will be updated as needed.

TECH STACK

(Add details of the tech stack being used, including languages, frameworks, libraries, and tools.)

PROJECT DOCUMENTATION & CONTEXT SYSTEM

(Describe how project documentation is structured and accessed by the AI assistant. Include details about file naming conventions, locations, and the tools used to manage documentation.)

  • New files should be named with a DESIGN-combined.md format when combining design documents.

CODING STANDARDS

(Define the coding standards to be followed, including naming conventions, code formatting, commenting, and error handling.)

WORKFLOW & RELEASE RULES

(Describe the project workflow, including branching strategies, code review processes, testing procedures, and release management.)

  • After running npm run build to create ./dist/cli.js, execute the CLI using either node ./dist/cli.js … directly. Alternatively, after running npm link (or installing the package), the CLI can be called directly using skillz ….
  • The skillz list command should, by default, provide a concise output, displaying each skill as a markdown bullet point with its name and the first 100 characters of its description. The description should have whitespace normalized, be trimmed, and have an ellipsis appended if truncated. If no description is available, the output should display "No description provided".

DEBUGGING

(Specify debugging strategies and tools. Detail how the AI assistant should approach debugging tasks.)

  • When encountering ESLint errors related to tsconfig.json inclusion, consider creating a separate tsconfig.eslint.json that includes test files. This allows for type-aware linting in tests without affecting the main build configuration. The tsconfig.eslint.json should:
    • Extend the main tsconfig.json.
    • Set "noEmit": true.
    • Set "rootDir": ".".
    • Include source and test files in the "include" array (e.g., "include": ["src/**/*.ts", "tests/**/*.ts"]).
    • Exclude node_modules and dist directories in the "exclude" array (e.g., "exclude": ["node_modules", "dist"]).
  • Ensure ESLint configuration (.eslintrc.cjs) uses the correct tsconfig.eslint.json for parser options:

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 1,368 tokens per session scan A 5ee52b9b5b9b

Subscribe to this mod's changes

derived-cursor-rules is a cursor rule published in the GitHub repository kevinslin/skillz (9 stars, last pushed 22d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,368 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.