A command that examines a repository and creates project-wide coding rules for all coding agents working in it. The rules are stored as Markdown files in the repository’s .cursor/rules directory.

Use it to create or update rules about naming, formatting, architecture, documentation, and other conventions, optionally combining them with instructions you provide.

It avoids repeating the same project conventions to each agent and helps agents follow the codebase’s existing patterns.

How JanUmansky/startup configures Claude Code and Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to JanUmansky/startup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/JanUmansky/startup/main/.cursor/commands/define.md

Clone the repo

git clone --depth 1 https://github.com/JanUmansky/startup

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/janumansky/startup/define/github.svg)](https://agentmods.dev/commands/janumansky/startup/define)

Your own site

<a href="https://agentmods.dev/commands/janumansky/startup/define"><img src="https://agentmods.dev/badge/commands/janumansky/startup/define/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/janumansky/startup/define"><img src="https://agentmods.dev/badge/commands/janumansky/startup/define.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,786 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02786
Opus 5.5	$0.00000	$0.01114
Sonnet 5.5	$0.00000	$0.00557
Haiku 4.5	$0.00000	$0.00279

Measured 2mo ago against content hash 85e49a63954a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

define 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 2mo 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/commands/define.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/define — Create project-wide coding rules and conventions

You are operating in a repository that supports scoped assistants. This command creates global rules that apply to ALL agents across the codebase.

Definitions:

RULES_DIR = ".cursor/rules"
Rules are stored as .mdc files (markdown with frontmatter) in RULES_DIR

Goal: Analyze the codebase and create (or update) rules that define project-wide conventions. These rules will be followed by all agents operating in this repository.

Input (from the user)

The user message invoking /define may contain:

No additional input: Analyze the codebase automatically and infer best practices
Specific instructions: Combine user preferences with code analysis

Examples:

"/define" → Full automatic analysis
"/define prefer arrow functions and single quotes" → User preference + analysis
"/define document all public functions with JSDoc" → Specific rule request

Rule Categories to Consider

When analyzing the codebase, focus on these general topics:

1. Naming Conventions

Variables: camelCase, snake_case, PascalCase
Functions: naming patterns, prefixes (get, set, is, has, handle, on)
Files: kebab-case, PascalCase, suffixes (.util, .service, .test)
Constants: SCREAMING_SNAKE_CASE vs other
Components/Classes: naming patterns

2. Folder Structure

Directory organization patterns
Separation of concerns (features, layers, domains)
Where different file types belong
Barrel files (index.ts) usage

3. Code Style

Arrow functions vs function declarations
Named exports vs default exports
Destructuring preferences
Ternary vs if/else for simple conditions
Early returns vs nested conditions

4. Text Formatting

Multiline strings: template literals, line breaks, concatenation
String quotes: single, double, template
Object/array formatting: single-line vs multi-line thresholds
Max line length preferences

5. Comments & Documentation

When to comment (complex logic, public APIs, non-obvious code)
Comment style (inline, block, JSDoc/TSDoc)
README requirements for folders/modules
TODO/FIXME conventions

Read the full file on GitHub · 350 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.

2mo ago First seen · 350 lines · 0 tokens per session scan A 85e49a63954a

Subscribe to this mod's changes

define is a command published in the GitHub repository JanUmansky/startup (2 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,786 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.

Building agents Planning

define next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
defineJanUmansky/startup	Command	2	9mo ago	MIT	A	0	Claude Code, Cursor
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

startup: Command for Claude Code