output-rules

A set of rules for formatting answers as Markdown documents and placing documentation files in the right folders. It defines which files may be in the project root and when to use a docs directory.

In plain words
What is it for?
Use it when creating documentation, deciding where a new file belongs, and checking the required answer format.
Why use it?
It prevents documentation from being scattered in the wrong locations or written in an inconsistent format.

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/elirancv/cursormd/output-rules
Clone the repo
git clone --depth 1 https://github.com/elirancv/CursorMD

Made for: Cursor.

Per session 674 This file is loaded in full into every session.
When invoked 674 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 $0.00674 $0.00674
Opus 5 $0.00337 $0.00337
Sonnet 5 $0.00135 $0.00135
Haiku 4.5 $0.00067 $0.00067

Measured 2d ago against content hash 4e61d212daff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

output-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/output-rules.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output Rules

Format

  • One document per answer, Markdown only
  • Use headings, lists, tables, code blocks where helpful

File Placement Rules (STRICT)

Root Directory (Only These)

Allowed in root:

  • README.md - Project overview
  • PROJECT_EVALUATION.md - Project assessment
  • CONTRIBUTING.md - Contribution guidelines
  • CHANGELOG.md - Version history
  • LICENSE - License file
  • Configuration files (.env.example, package.json, etc.)

NEVER create in root:

  • ❌ Architecture documents
  • ❌ Technical specs
  • ❌ PRD, VISION, or any other documentation files
  • ❌ Any .md files except README.md, PROJECT_EVALUATION.md, CONTRIBUTING.md

Documentation Directory

All other documentation → docs/ directory:

  • docs/VISION.md
  • docs/PRD_MVP.md
  • docs/ARCHITECTURE_OVERVIEW.md
  • docs/TECH_SPEC_MVP.md
  • docs/PIPELINE_MVP.md
  • All other document types → docs/

Structure Detection

Before creating files:

  1. Check if docs/ directory exists
  2. Check for alternative docs directories (documentation/, doc/)
  3. Follow existing structure if present
  4. If no docs directory exists, create docs/ and use it

Important: If user has existing structure, follow theirs instead. But maintain organization - don't create files randomly.

Document Presentation

Show Summary First

Default behavior:

  1. Display document content in chat - Show the full document
  2. Ask for confirmation - "Should I create this file at docs/[filename].md?"
  3. Wait for approval - Only create file after user confirms
  4. Respect user choice - If they say "just show me", don't create files

Only create files automatically if:

  • User explicitly says "create", "write", "save", "generate file"
  • User explicitly approves after seeing summary
  • Context clearly indicates file creation intent

Never create files:

  • ❌ Without asking first
  • ❌ In wrong locations
  • ❌ When user just wants to see content
  • ❌ In root directory (except allowed files)
  • ❌ In code directories (src/, lib/, app/)

Read the full file on GitHub · 84 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 · 84 lines · 674 tokens per session scan A 4e61d212daff

Subscribe to this mod's changes

output-rules is a cursor rule published in the GitHub repository elirancv/CursorMD (1 stars, last pushed 9mo ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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 2026-08-31.

Related

Other cursor rules, from other repositories

create-rule-agent

This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…

usrrname/cursorrules · 3,429 tokens

cloudflare-workers-hono-auto

Cloudflare Workers with Hono framework development standards and best practices.

usrrname/cursorrules · 0 tokens

security-scan-agent

This rule provides comprehensive security scanning for dependencies, complementing the dependency analysis rule with deep security insights including CVE analysis, license compliance, and supply chain risk assessment.

usrrname/cursorrules · 0 tokens

cloudflare-workers-auto

Cloudflare Workers development standards and best practices.

usrrname/cursorrules · 0 tokens

changelog-generator-manual

This rule generates a comprehensive changelog.md file by analyzing all git tags and commits, creating a chronological record of all project changes with proper semantic versioning structure. The changelog.md file is stored at the root of the project.

usrrname/cursorrules · 0 tokens

mysql-auto

This rule enforces MySQL-specific best practices to enhance readability, performance, security, and maintainability. It targets MySQL features (e.g., storage engines, character sets) and common pitfalls, and adds concrete guidance for schema design and creation.

usrrname/cursorrules · 0 tokens