documentation

documentation is a cursor rule for Cursor from BOXELS/cursor-rules. It costs 474 tokens per session, scanned A, original, MIT.

A set of rules for keeping project documentation and agent-specific rules current. It explains where reference documents belong, how to name them, and what changes should be recorded.

In plain words
What is it for?
Use it when adding, changing, deprecating, or removing features, patterns, constraints, or architecture, so the relevant docs and agent rules stay aligned.
Why use it?
It prevents documentation from becoming stale or contradicting the code after features, architecture, or conventions change. It also discourages duplicate documents.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

Good fit Use it when adding, changing, deprecating, or removing features, patterns, constraints, or architecture, so the relevant docs and agent rules stay aligned.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/boxels/cursor-rules/documentation
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.

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

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

README.md
[![agentmods](https://agentmods.dev/badge/rules/boxels/cursor-rules/documentation/github.svg)](https://agentmods.dev/rules/boxels/cursor-rules/documentation)
Your own site
<a href="https://agentmods.dev/rules/boxels/cursor-rules/documentation"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/documentation/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.

agentmods 80×15 button for documentation

Your own site · 80×15
<a href="https://agentmods.dev/rules/boxels/cursor-rules/documentation"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 474 This file is loaded in full into every session.
When invoked 474 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00474 $0.00474
Opus 5 $0.00237 $0.00237
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured yesterday against content hash e440529ef134, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

documentation 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/rules/documentation.mdc · 31 lines

What it actually says

Documentation Rules

Always keep docs current

  • After any feature, architecture change, or removal: update relevant docs and .cursor/rules to match reality. Do not leave stale or contradictory documentation.
  • Prefer editing existing docs over creating duplicates. Search the doc folder before writing a new file.
  • What to document: architecture decisions, removed/deprecated patterns, new conventions, critical constraints (things agents must NOT do), and cross-references between docs and rules.

Doc location and naming

  • Agent-facing reference docs live in [doc folder, e.g. "docs/"].
  • Naming: [convention, e.g. "FEATURE_NAME.md in ALL_CAPS_WITH_UNDERSCORES", "kebab-case.md"]. Keep one convention and stick to it.
  • New feature docs should include: one-sentence purpose, files/routes/tables touched, how it works, critical constraints, and links to related docs.

Cursor rules maintenance

  • If a change affects patterns or conventions other agents need, update .cursor/rules/ as well as prose docs.
  • Cross-cutting concerns → [global rules file, e.g. "global-rules.mdc"]. Domain-specific guidance → the matching rule file (tech, design, security, models, etc.) or a new focused rule file. New rule files must use the .mdc extension.
  • Add a one-line "see docs/FOO.md" pointer from rules when a longer reference exists.
  • Model names in models.mdc go stale every few months. When updating docs after a Cursor model change, refresh that file against cursor.com/docs/models.

Trigger: "update docs"

When the user says "update documentation", "update docs", "update the docs", or similar, run the update-docs skill (.cursor/skills/update-docs/SKILL.md). It defines the full find → edit → create-if-needed → cross-reference → report workflow. Don't ask which files to update — the skill finds them.

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 · 31 lines · 474 tokens per session scan A e440529ef134

Subscribe to this mod's changes

documentation is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 474 tokens to every session, about $0.0024 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 2026-09-15.