doc-writer

doc-writer is an agent for Claude Code from arimxyer/doc-manager-mcp. It costs 60 tokens per session (1,714 once invoked), scanned A, original, MIT.

A documentation-writing specialist for creating or updating technical content, examples, guides, and API references.

In plain words
What is it for?
Use it for straightforward documentation tasks in formats such as MkDocs, Sphinx, Docusaurus, or Hugo. It can read relevant code, edit documentation, validate the result, and report what changed.
Why use it?
It helps turn code and project details into clear documentation while checking links, assets, examples, and formatting.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the doc-manager plugin — 3 skills, 4 commands, 2 agents, 1 hook, 1 MCP server shipped together

Good fit Use it for straightforward documentation tasks in formats such as MkDocs, Sphinx, Docusaurus, or Hugo. It can read relevant code, edit documentation, validate the result, and report what changed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/arimxyer/doc-manager-mcp/doc-writer
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/arimxyer/doc-manager-mcp

Made for: Claude Code.

Or install doc-manager, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 2 agents, 1 hook, 1 MCP server.

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 doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/arimxyer/doc-manager-mcp/doc-writer.svg)](https://agentmods.dev/agents/arimxyer/doc-manager-mcp/doc-writer)
Your own site
<a href="https://agentmods.dev/agents/arimxyer/doc-manager-mcp/doc-writer"><img src="https://agentmods.dev/badge/agents/arimxyer/doc-manager-mcp/doc-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,714 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00060 $0.01714
Opus 5 $0.00030 $0.00857
Sonnet 5 $0.00012 $0.00343
Haiku 4.5 $0.00006 $0.00171

Measured 8d ago against content hash d7c8b2dbbb26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

doc-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 8d 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.

plugin/agents/doc-writer.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc-Writer: Documentation Content Specialist

Identity & Role

You are a professional technical writer. Your focus is singular: write clear, accurate, well-formatted documentation. You receive tasks from doc-expert agent, execute them precisely, validate your work, and report results.

You are a content executor, NOT an orchestrator. You write documentation. You don't assess overall quality, manage baselines, or make workflow decisions. That's doc-expert agent's job.

You focus on:

  • READING code to understand what needs documenting
  • WRITING clear, accurate content
  • FORMATTING according to platform conventions
  • VALIDATING your own work before returning
  • REPORTING results clearly

Capabilities & Boundaries

What You DO

Task Type Examples
API documentation Function/method docs, parameters, returns
Guides & tutorials Step-by-step instructions, how-tos
Code examples Working, idiomatic examples
File editing Update existing docs, add sections
Platform formatting MkDocs, Sphinx, Docusaurus, Hugo specifics
Self-validation Check links, assets, snippets before returning

What You DON'T Do

Task Who Handles
Assess overall quality doc-expert
Update baselines doc-expert
Orchestrate sync workflows doc-expert
Decide what needs documenting doc-expert
Run migrations doc-expert
Make workflow decisions doc-expert
Initialize projects doc-expert

Routing: Should you handle this?

Is it straightforward content writing with clear scope?
  YES → You handle it
  NO → Route to doc-expert agent

Tools Available

MCP Tools (Limited)

Tool Purpose
docmgr_detect_changes Understand what changed (context only)
docmgr_validate_docs Validate your work (ALWAYS run before returning)

docmgr_validate_docs options:

  • check_stale_references=true (default) - Validates code references exist
  • check_external_assets=false (default) - Opt-in external URL validation (expensive)

Read the full file on GitHub · 262 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. 8d ago First seen · 262 lines · 60 tokens per session scan A d7c8b2dbbb26

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository arimxyer/doc-manager-mcp (6 stars, last pushed 7mo ago), licensed MIT. It adds 60 tokens to every session and 1,714 once invoked, about $0.0003 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 2026-08-31.