define

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.

In plain words
What is it for?
Use it to create or update rules about naming, formatting, architecture, documentation, and other conventions, optionally combining them with instructions you provide.
Why use it?
It avoids repeating the same project conventions to each agent and helps agents follow the codebase’s existing patterns.

Command 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 commands/janumansky/startup/define
Clone the repo
git clone --depth 1 https://github.com/JanUmansky/startup

Made for: Cursor.

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. 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 $0.02786
Opus 5 $0.00000 $0.01393
Sonnet 5 $0.00000 $0.00557
Haiku 4.5 $0.00000 $0.00279

Measured yesterday against content hash 85e49a63954a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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/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.

  1. yesterday 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 7mo 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.