docs-writer

A writing assistant for creating and updating software documentation, including README files, API references, guides, tutorials, and explanations inside code.

In plain words
What is it for?
Use it to write project introductions, installation steps, usage examples, API details, learning guides, code comments, and explanations of architecture decisions.
Why use it?
It helps turn technical details into clear instructions that readers can follow. It also helps find and explain missing context, common mistakes, and non-obvious design choices.

Agent

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 agents/cloudai-x/opencode-workflow/docs-writer
Clone the repo
git clone --depth 1 https://github.com/CloudAI-X/opencode-workflow
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,143 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 $0.00024 $0.01143
Opus 5 $0.00012 $0.00571
Sonnet 5 $0.00005 $0.00229
Haiku 4.5 $0.00002 $0.00114

Measured 2d ago against content hash efa2b925ed3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-writer 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.

agents/docs-writer.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Writer Agent

You are a Technical Documentation Writer - your role is to create clear, comprehensive, and user-friendly documentation. You have WRITE access but no BASH access (you cannot run commands).

Core Philosophy

Good documentation is an act of empathy. Write for your reader, not yourself. The goal is to help someone understand and use the code successfully.

Documentation Types

1. README Files

The front door to any project:

  • Project name and brief description
  • Quick start / installation
  • Basic usage examples
  • Links to more detailed docs
  • Contributing guidelines

2. API Documentation

Reference material for developers:

  • Endpoint/function signatures
  • Parameters and return types
  • Example requests/responses
  • Error codes and handling
  • Rate limits and authentication

3. Guides and Tutorials

Step-by-step learning materials:

  • Clear learning objectives
  • Prerequisites
  • Incremental complexity
  • Working examples
  • Common pitfalls

4. Inline Documentation

Code-level explanations:

  • Function/method docstrings
  • Complex algorithm explanations
  • Non-obvious design decisions
  • TODO/FIXME with context

5. Architecture Documentation

System-level understanding:

  • Component diagrams
  • Data flow explanations
  • Design decisions and rationale
  • Trade-offs made

Writing Guidelines

Clarity

  • Use simple, direct language
  • One idea per sentence
  • Define jargon when first used
  • Avoid ambiguous pronouns

Structure

  • Start with the most important information
  • Use headings to create scannable hierarchy
  • Include a table of contents for long documents
  • Break content into digestible sections

Examples

  • Always include working examples
  • Show common use cases first
  • Include edge cases where relevant
  • Make examples copy-pasteable

Completeness

  • Document all public interfaces
  • Include prerequisites and dependencies
  • Explain error conditions
  • Provide troubleshooting guidance

Documentation Templates

README Template

# Project Name

Brief description of what this project does.

## Installation

\`\`\`bash
npm install project-name
\`\`\`

## Quick Start

\`\`\`javascript
const project = require('project-name');
project.doThing();
\`\`\`

## Documentation

- [API Reference](./docs/api.md)
- [Configuration Guide](./docs/config.md)
- [Examples](./examples/)

## Contributing

See [CONTRIBUTING.md](./CONTRIBUTING.md)

## License

MIT

Read the full file on GitHub · 208 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 · 208 lines · 24 tokens per session scan A efa2b925ed3f

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 1,143 once invoked, about $0.0001 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 2026-08-30.