documentation-policy

documentation-policy is a cursor rule for Cursor from beettlle/pi-spine. It costs 2,038 tokens per session, scanned C, original, MIT.

A set of rules for deciding when coding agents may create or change Markdown documentation files. It also describes how requested documentation should be organized.

In plain words
What is it for?
Use it when an agent is deciding whether to create, read, or modify Markdown files, including repository documentation and requested guides.
Why use it?
It prevents extra README files, guides, or change summaries from being created without permission. It keeps explanations in the conversation unless the user asks for a file.

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/beettlle/pi-spine/documentation-policy
Clone the repo
git clone --depth 1 https://github.com/beettlle/pi-spine

Made for: 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.

agentmods badge for documentation-policy

README.md
[![agentmods](https://agentmods.dev/badge/rules/beettlle/pi-spine/documentation-policy.svg)](https://agentmods.dev/rules/beettlle/pi-spine/documentation-policy)
Your own site
<a href="https://agentmods.dev/rules/beettlle/pi-spine/documentation-policy"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/documentation-policy.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,038 This file is loaded in full into every session.
When invoked 2,038 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02038 $0.02038
Opus 5 $0.01019 $0.01019
Sonnet 5 $0.00408 $0.00408
Haiku 4.5 $0.00204 $0.00204

Measured 4d ago against content hash 92127ff2a013, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

documentation-policy scanned grade C with 1 finding 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 4d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Do not refuse "create a task packet" or "write PROMPT.md for this feature" because documentation-policy forbids new `.md` files.
.cursor/rules/documentation-policy.mdc · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Files Policy

CRITICAL: Never create markdown files (.md) unless explicitly requested by the user.

Rules

  1. Do NOT create markdown files for:

    • Explaining code changes or fixes
    • Documenting what was implemented
    • Creating README files
    • Writing documentation or guides
    • Summarizing work done
    • Any other automatic documentation
  2. Only create markdown files when:

    • The user explicitly requests a markdown file (e.g., "create a README", "write documentation in a .md file", "create a markdown file for X")
    • The user specifically asks for documentation to be written to a file
  3. Communication:

    • Explain changes and fixes directly in your response to the user
    • Use code comments when code documentation is needed
    • Do not create separate markdown files to explain work
  4. Existing markdown files:

    • You may read and reference existing markdown files
    • Do not modify existing markdown files unless explicitly asked

Obsidian vault notes (scope exception)

Repo/software docs (README, CONTRIBUTING, docs/, change summaries, PR writeups): this policy still applies — do not create unsolicited .md.

PKM vault notes (user explicitly asks to create, edit, or template a note, daily note, or vault page): this policy does not block that work. Follow obsidian-vault-standards.mdc and installed obsidian-skills for OFM syntax.

❌ Bad: Refusing "create a daily note" because documentation-policy forbids new .md files ✅ Good: Create/edit vault note when user requested; reserve documentation-policy for repo docs unless user asked for vault content ⚠️ Why: Vaults are note-first; conflating PKM with repo docs blocks legitimate user intent 🔧 Fix: Check user intent (vault vs repo); domain-specific Obsidian rules override this policy for vault notes 📍 See: obsidian-vault-standards.mdc; RULE_COMPOSITION.md conflict example 3

Detect: Agent cites documentation-policy when user asked for a note, vault path or .obsidian/ present but agent treats all .md as repo docs

Read the full file on GitHub · 156 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. 4d ago First seen · 156 lines · 2,038 tokens per session scan C 92127ff2a013

Subscribe to this mod's changes

documentation-policy is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed yesterday), licensed MIT. It adds 2,038 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.