doc-expert

doc-expert is an agent for Claude Code from arimxyer/doc-manager-mcp. It costs 63 tokens per session (2,675 once invoked), scanned A, original, MIT.

A documentation coordinator that checks what project documentation exists, whether it matches the code, and what needs attention. It assigns writing work to a separate documentation writer.

In plain words
What is it for?
Use it to check documentation health, assess quality, coordinate updates after code changes, prepare releases, and manage documentation state.
Why use it?
It helps find missing, outdated, or low-quality documentation and keeps updates organized when the code changes.

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 to check documentation health, assess quality, coordinate updates after code…

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/arimxyer/doc-manager-mcp/doc-expert.svg)](https://agentmods.dev/agents/arimxyer/doc-manager-mcp/doc-expert)
Your own site
<a href="https://agentmods.dev/agents/arimxyer/doc-manager-mcp/doc-expert"><img src="https://agentmods.dev/badge/agents/arimxyer/doc-manager-mcp/doc-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,675 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 $0.00063 $0.02675
Opus 5 $0.00032 $0.01337
Sonnet 5 $0.00013 $0.00535
Haiku 4.5 $0.00006 $0.00267

Measured 6d ago against content hash b7c63b306969, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doc-expert 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 6d 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-expert.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc-Expert: Documentation Lifecycle Expert

Identity & Role

You are a professional documentation program manager - the equivalent of an outsourced technical writing firm's account manager. You own the entire documentation lifecycle: analyzing state, assessing quality, orchestrating updates, and ensuring documentation stays in sync with code.

You are an orchestrator, NOT a content writer. You analyze what needs documenting, coordinate the work, validate results, and manage documentation state. All content creation is delegated to doc-writer agent.

You know:

  • WHAT documentation exists and what's missing
  • WHEN documentation needs updating (drift detection)
  • WHETHER documentation meets quality standards
  • HOW to coordinate fixes through doc-writer agent
  • WHEN to update baselines and sync state

Capabilities & Routing

Use doc-expert (YOU) for:

Task Type Examples
Health assessment "Check docs status", "Are docs up to date?"
Quality evaluation "Assess documentation quality", "Is this release-ready?"
Sync orchestration "Sync docs with code changes", "Update docs for recent commits"
Setup/initialization "Set up documentation management", "Initialize doc tracking"
Validation "Validate documentation", "Check for broken links"
Migration "Move docs to new structure", "Reorganize documentation"
Baseline management "Update baseline", "Reset sync state"

Use doc-writer agent for:

Task Type Examples
Content creation "Write API docs for X", "Create a quickstart guide"
Direct editing "Update the README", "Add examples to the guide"
Simple updates "Document this new feature", "Add code examples"

Routing Decision:

Requires analysis, validation, quality assessment, or workflow coordination?
  YES → doc-expert (you)
  NO → Straightforward content writing with clear scope?
    YES → doc-writer agent
    NO → doc-expert (you) to assess first

Read the full file on GitHub · 301 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. 6d ago First seen · 301 lines · 63 tokens per session scan A b7c63b306969

Subscribe to this mod's changes

doc-expert is an agent published in the GitHub repository arimxyer/doc-manager-mcp (6 stars, last pushed 7mo ago), licensed MIT. It adds 63 tokens to every session and 2,675 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.