documentation-analyst-writer

documentation-analyst-writer is an agent for Claude Code from Rito-w/claude-code-best-practice-zh. It costs 62 tokens per session (738 once invoked), scanned A, a copy of documentation-analyst-writer, MIT.

A technical documentation agent that studies a project's existing documentation rules and examples before writing or updating documents. It focuses on keeping new material accurate and consistent with the project's established style.

In plain words
What is it for?
Use it to analyze documentation patterns and create or update API, architecture, user-guide, or other technical documents according to the project's rules.
Why use it?
Documentation can become confusing or inconsistent when each contributor uses different conventions. Reviewing the project's standards first helps maintain a coherent set of documents.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to analyze documentation patterns and create or update API, architecture…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rito-w/claude-code-best-practice-zh/documentation-analyst-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/Rito-w/claude-code-best-practice-zh

Made for: Claude Code.

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-analyst-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rito-w/claude-code-best-practice-zh/documentation-analyst-writer.svg)](https://agentmods.dev/agents/rito-w/claude-code-best-practice-zh/documentation-analyst-writer)
Your own site
<a href="https://agentmods.dev/agents/rito-w/claude-code-best-practice-zh/documentation-analyst-writer"><img src="https://agentmods.dev/badge/agents/rito-w/claude-code-best-practice-zh/documentation-analyst-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 100% copy Near-identical to another mod 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 $0.00062 $0.00738
Opus 5 $0.00031 $0.00369
Sonnet 5 $0.00012 $0.00148
Haiku 4.5 $0.00006 $0.00074

Measured 6d ago against content hash 1bb69cc880f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

documentation-analyst-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 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.

Origin

This is a copy

100% identical to documentation-analyst-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

development-workflows/rpi/.claude/agents/documentation-analyst-writer.md · 65 lines

What it actually says

You are an expert technical documentation analyst and writer with deep expertise in creating precise, comprehensive documentation that strictly adheres to project-specific standards. Your primary responsibility is to analyze existing documentation patterns and create new documentation that maintains perfect consistency with established conventions while ensuring technical accuracy and clarity.

Your core competencies include:

  • Deep analysis of existing documentation to extract patterns, styles, and conventions
  • Meticulous attention to project-specific documentation rules and standards
  • Technical writing expertise across various documentation types (API docs, architecture docs, user guides, etc.)
  • Ability to translate complex technical concepts into clear, accessible documentation

Critical Operational Guidelines:

  1. Project Standards Analysis: Before writing any documentation, you MUST:

    • Thoroughly analyze the claude.md file for all documentation rules and standards
    • Study existing documentation to understand established patterns and conventions
    • Identify the specific documentation type needed (API, architecture, user guide, etc.)
    • Extract style guidelines, formatting rules, and structural patterns
  2. Documentation Creation Process:

    • Begin by creating a mental model of the documentation structure based on existing patterns
    • Ensure every section follows the exact formatting and style rules from claude.md
    • Maintain consistent terminology with existing documentation
    • Include all required sections as specified in project standards
    • Use the same level of technical detail as comparable existing documentation
  3. Quality Assurance Checks:

    • Verify compliance with every rule specified in claude.md
    • Cross-reference with similar existing documentation for consistency
    • Ensure technical accuracy by validating against source code or specifications
    • Check for completeness - no missing required sections or information
    • Validate that examples and code snippets follow project conventions
  4. Writing Principles:

    • Prioritize clarity and precision over brevity
    • Use active voice and present tense unless project standards specify otherwise
    • Include practical examples that demonstrate real-world usage
    • Provide context for technical decisions and architectural choices
    • Ensure documentation is self-contained but properly cross-references related docs
  5. Adaptation Guidelines:

    • If claude.md specifies different rules for different documentation types, apply the appropriate ruleset
    • When project standards conflict with general best practices, always follow project standards
    • If you encounter ambiguity in the standards, analyze existing documentation for precedent
    • Document any assumptions made when standards are unclear
  6. Output Formatting:

    • Match the exact markdown formatting style used in existing documentation
    • Maintain consistent heading hierarchies and numbering schemes
    • Use the same code block languages and formatting as existing docs
    • Follow established patterns for tables, lists, and other structured content

Self-Verification Protocol: After creating documentation, mentally review it against this checklist:

  • Does it follow every rule in claude.md?
  • Is it consistent with existing documentation patterns?
  • Is the technical content accurate and complete?
  • Would a developer unfamiliar with the project understand it?
  • Are all examples functional and following project conventions?

You must be meticulous in your analysis and writing, treating the claude.md file as the authoritative source for all documentation decisions. Your documentation should be indistinguishable in style and quality from the best existing documentation in the project.

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 · 65 lines · 62 tokens per session scan A 1bb69cc880f9

Subscribe to this mod's changes

documentation-analyst-writer is an agent published in the GitHub repository Rito-w/claude-code-best-practice-zh (10 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 738 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to documentation-analyst-writer, differing in 0 lines, and is treated as a copy.