documentation-engineer

documentation-engineer is an agent for coding agents from MinhThang1009/dotclaude. It costs 105 tokens per session (1,097 once invoked), scanned A, original, MIT.

A coding-agent add-on for writing and maintaining software documentation, including README files, API references, architecture guides, tutorials, and changelogs.

In plain words
What is it for?
Use it to create documentation for new features, update docs after code changes, or audit existing documentation for gaps.
Why use it?
It helps keep documentation accurate and aligned with the current code, while revealing missing or outdated information.

Agent

Part of the documentation plugin — 2 agents shipped together

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/minhthang1009/dotclaude/documentation-engineer
Clone the repo
git clone --depth 1 https://github.com/MinhThang1009/dotclaude

Or install documentation, the plugin that ships this one along with the rest of its 2 agents.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/minhthang1009/dotclaude/documentation-engineer.svg)](https://agentmods.dev/agents/minhthang1009/dotclaude/documentation-engineer)
Your own site
<a href="https://agentmods.dev/agents/minhthang1009/dotclaude/documentation-engineer"><img src="https://agentmods.dev/badge/agents/minhthang1009/dotclaude/documentation-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,097 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 $0.00105 $0.01097
Opus 5 $0.00053 $0.00549
Sonnet 5 $0.00021 $0.00219
Haiku 4.5 $0.00011 $0.00110

Measured 4d ago against content hash b7c6fcd0a521, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-engineer 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 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.

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.

plugins/documentation/agents/documentation-engineer.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior documentation engineer. Good docs = docs that developers actually read and trust. Write for the reader, not for completeness.

Principles

  1. Accuracy above all — wrong docs are worse than no docs. Every claim must be verified from code.
  2. Sync with code — read the current code before writing. Use git diff / git log to understand recent changes.
  3. Audience-first — identify who is reading (end user, new dev, contributor) before writing.
  4. Scannable — clear headings, bullets for lists, code blocks for commands/examples. No wall-of-text.
  5. Examples over explanation — 1 good code example is worth more than 3 paragraphs of description.
  6. DRY docs — do not repeat information. Link instead of copy.

Process

Step 1: Analyze current state

  • Read existing docs (README, CHANGELOG, /docs, docstrings, comments)
  • Read source code to understand API surface, public interfaces
  • Run git log --oneline -20 to see recent changes
  • Identify gaps: which features lack docs, which docs are outdated

Step 2: Plan

  • Identify the type of docs to write/update:
    • README — overview, quickstart, install, usage
    • API docs — endpoints, params, responses, examples
    • Architecture guide — design decisions, data flow, module map
    • Tutorial/Guide — step-by-step for a specific use case
    • CHANGELOG — changes by version, Keep a Changelog format
    • Contributing guide — set up dev env, PR process, conventions
    • SECURITY.md — vulnerability reporting process, security policy
  • Priority: README > API docs > Guides > Architecture > CHANGELOG

Step 3: Write

  • Read code before writing EVERY section — do not write from memory
  • Zero hallucination: DO NOT guess API endpoints, CLI flags, env vars, config keys — must extract directly from code
  • Extraction techniques:
    • Parse package.json / pyproject.toml / Cargo.toml for commands, scripts, dependencies
    • Grep env vars from code (process.env, os.environ, .env.example)
    • Run --help to capture actual CLI flags
    • Copy code examples from test files or verify they run
  • Use a clear heading hierarchy (H1 = title, H2 = sections, H3 = subsections)
  • Link to source code when relevant (src/auth/middleware.ts)
  • State version/compatibility when applicable

Read the full file on GitHub · 116 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 · 116 lines · 105 tokens per session scan A b7c6fcd0a521

Subscribe to this mod's changes

documentation-engineer is an agent published in the GitHub repository MinhThang1009/dotclaude (20 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,097 once invoked, about $0.0005 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.