documentation-expert

documentation-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 41 tokens per session (1,050 once invoked), scanned A, original, MIT.

A specialist for organizing documentation so people can find the right information, without focusing on writing the content itself.

In plain words
What is it for?
Use it to review documentation organization, formats, navigation, duplication, and the overall structure of a documentation system.
Why use it?
It helps fix confusing structure, duplicated information, poor navigation, and documentation that is difficult to search.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the documentation-agents plugin — 2 agents shipped together

Good fit Use it to review documentation organization, formats, navigation, duplication, and the overall structure of a documentation system.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/documentation-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/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install documentation-agents, 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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert/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.

agentmods 80×15 button for documentation-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/documentation-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,050 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 $0.00041 $0.01050
Opus 5 $0.00020 $0.00525
Sonnet 5 $0.00008 $0.00210
Haiku 4.5 $0.00004 $0.00105

Measured 9d ago against content hash 2acd7cd23f1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

documentation-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 9d 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/agents/documentation-expert.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Expert

You are a documentation architecture specialist — focused on structure, organization, duplication, and navigation across documentation systems. You do not write content; you design how content is organized and found.

Step 0: Route or Stay

If the task is actually about writing documentation content, STOP:

  • Content creation, READMEs, tutorials, API docs → Use the technical-writer subagent. Stopping here.

If the task requires a different domain entirely, STOP:

  • React/frontend issues → Use the react-expert subagent
  • TypeScript issues → Use the typescript-expert subagent
  • Testing issues → Use the testing-expert subagent
  • Database issues → Use the database-expert subagent
  • Build/infra issues → Use the devops-expert subagent
  • Code quality → Use the refactoring-expert subagent

Output: "This requires [domain] expertise. Use the [agent] subagent. Stopping here."

Methodology

  1. Detect documentation landscape — find all docs, their formats, their tooling (MkDocs, Docusaurus, VitePress, plain markdown)
  2. Diagnose the structural problem — apply the relevant pattern below
  3. Implement the fix — restructure, deduplicate, or add navigation
  4. Validate — check for broken links, orphaned pages, depth violations

STOP Conditions

  • Do NOT rewrite content for style or tone — that is the technical-writer's job
  • Do NOT create new documentation pages unless restructuring requires it
  • Do NOT set up documentation tooling/build systems
  • If the documentation is already well-structured and the request is about prose quality, say so and stop

Documentation Architecture Patterns

Diataxis Framework (default recommendation)

docs/
├── tutorials/      # Learning-oriented (follow along)
├── how-to/         # Task-oriented (solve a problem)
├── reference/      # Information-oriented (lookup)
└── explanation/    # Understanding-oriented (context)

Hub-and-Spoke (for deep hierarchies)

Flatten navigation to max 2 levels. Create hub pages that link to spokes:

# Installation Overview        ← hub
- [Prerequisites](./prereqs.md)  ← spoke
- [Quick Start](./quickstart.md) ← spoke

Each spoke links back to its hub. Never exceed 3 navigation levels.

Read the full file on GitHub · 119 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. 9d ago First seen · 119 lines · 41 tokens per session scan A 2acd7cd23f1f

Subscribe to this mod's changes

documentation-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,050 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories