A guide for documenting a software component or feature by examining its purpose, interfaces, behavior, errors, testing, and connections to other parts.

Use it to write overviews, usage examples, API or parameter details, component relationships, state behavior, error handling, performance notes, accessibility information, and testing guidance.

It turns code-level understanding into documentation that explains how the component works and how other developers should use it.

create-docs — Cursor rule for Cursor by steipete/agent-rules

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/steipete/agent-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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/steipete/agent-rules/create-docs/github.svg)](https://agentmods.dev/rules/steipete/agent-rules/create-docs)

Your own site

<a href="https://agentmods.dev/rules/steipete/agent-rules/create-docs"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/create-docs/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/rules/steipete/agent-rules/create-docs"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/create-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 284 This file is loaded in full into every session.

When invoked 284 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.

Model	Per session	Once invoked
Fable 5.1	$0.00284	$0.00284
Opus 5.5	$0.00114	$0.00114
Sonnet 5.5	$0.00057	$0.00057
Haiku 4.5	$0.00028	$0.00028

Measured 1mo ago against content hash cd543301b4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-docs 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

create-docs — 100% identical, 0 lines differ

project-rules/create-docs.mdc · 61 lines

What it actually says

Create Docs

Create comprehensive documentation for specified components or features.

Analysis Areas:

Code structure and purpose
Inputs, outputs, and behavior
User interaction flows
Edge cases and error handling
Integration points with other components/systems

Documentation Template:

Overview

Brief 1-2 paragraph overview explaining purpose and value

Usage

How to use this component/feature with examples

API / Props / Parameters

Detailed specification of interfaces

Component Hierarchy

Structure and relationships (if applicable)

State Management

How state is handled and flows through the system

Behavior

Expected behavior in different scenarios

Error Handling

How errors are caught, handled, and reported

Performance Considerations

Optimization notes and performance characteristics

Accessibility

Accessibility features and compliance

Testing

How to test this component/feature

Related Components/Features

Links to related documentation

Process:

Analyze the target code thoroughly
Identify all public interfaces
Document expected behaviors
Include code examples
Add diagrams where helpful
Follow project documentation standards
Ensure clarity, completeness, and actionability

Output Formats:

Markdown for general documentation
JSDoc/TSDoc for code comments
API documentation format
README files
Architecture decision records (ADRs)

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.

1mo ago First seen · 61 lines · 284 tokens per session scan A cd543301b4f3

Subscribe to this mod's changes

create-docs is a cursor rule published in the GitHub repository steipete/agent-rules (5,677 stars, last pushed 5mo ago), licensed MIT. It adds 284 tokens to every session, about $0.0011 per session on Opus 5.5. 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 2026-08-30.

Writing and docs agent claudecode cursor llms rules

create-docs