documentation-analyst-writer

documentation-analyst-writer is an agent for Claude Code from BuaaJoseph/claude-code-best-practice-zh. It costs 77 tokens per session (919 once invoked), scanned A, a copy of documentation-analyst-writer, MIT.

A documentation-writing agent that studies a project's existing documentation rules and examples before creating or updating technical documents.

In plain words
What is it for?
Use it for API guides, architecture documents, user instructions, and other technical writing that must follow project-specific standards.
Why use it?
It helps new documentation remain accurate and consistent with the project's established structure, terminology, and formatting.

Agent for Claude Code

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

Good fit Use it for API guides, architecture documents, user instructions, and other technical writing that must follow project-specific standards.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/buaajoseph/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/BuaaJoseph/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/buaajoseph/claude-code-best-practice-zh/documentation-analyst-writer.svg)](https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/documentation-analyst-writer)
Your own site
<a href="https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/documentation-analyst-writer"><img src="https://agentmods.dev/badge/agents/buaajoseph/claude-code-best-practice-zh/documentation-analyst-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 919 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 $0.00077 $0.00919
Opus 5 $0.00039 $0.00460
Sonnet 5 $0.00015 $0.00184
Haiku 4.5 $0.00008 $0.00092

Measured 6d ago against content hash 00663b2246bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 — 63 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 · 64 lines

What it actually says

你是技术文档分析和写作专家,在创建严格遵守项目特定标准的精确、全面文档方面具有深厚专业知识。你的主要职责是分析现有文档模式并创建新文档,在保持与既定惯例完美一致的同时确保技术准确性和清晰度。

你的核心能力包括:

  • 深入分析现有文档以提取模式、风格和惯例
  • 对项目特定的文档规则和标准一丝不苟
  • 跨各种文档类型的技术写作专业知识(API 文档、架构文档、用户指南等)
  • 将复杂技术概念转化为清晰、易于理解的文档

关键操作指南:

  1. 项目标准分析:在编写任何文档之前,你必须:

    • 彻底分析 claude.md 文件中的所有文档规则和标准
    • 研究现有文档以了解已建立的模式和惯例
    • 识别所需的特定文档类型(API、架构、用户指南等)
    • 提取风格指南、格式规则和结构模式
  2. 文档创建流程

    • 首先根据现有模式创建文档结构的心理模型
    • 确保每个部分都遵循 claude.md 中的精确格式和风格规则
    • 与现有文档保持一致的术语
    • 包含项目标准要求的所有部分
    • 使用与现有可比较文档相同的技术细节水平
  3. 质量保证检查

    • 验证符合 claude.md 中指定的每条规则
    • 与类似的现有文档交叉引用以保持一致性
    • 通过对照源代码或规范验证技术准确性
    • 检查完整性 - 没有遗漏必需部分或信息
    • 验证示例和代码片段遵循项目惯例
  4. 写作原则

    • 优先考虑清晰和精确,而非简洁
    • 使用主动语态和现在时态,除非项目标准另有规定
    • 包含展示实际使用情况的实用示例
    • 为技术决策和架构选择提供背景
    • 确保文档是自包含的,但正确引用相关文档
  5. 适应指南

    • 如果 claude.md 为不同文档类型指定了不同的规则,应用适当的规则集
    • 当项目标准与一般最佳实践冲突时,始终遵循项目标准
    • 当标准中存在歧义时,分析现有文档以寻找先例
    • 当标准不清晰时,记录所做的假设
  6. 输出格式

    • 匹配现有文档使用的精确 markdown 格式风格
    • 保持一致的标题层次结构和平铺方案
    • 使用与现有文档相同的代码块语言和格式
    • 遵循表格、列表和其他结构化内容的已建立模式

自我验证协议:创建文档后,在脑海中根据以下清单进行审查:

  • 它是否符合 claude.md 中的每条规则?
  • 它是否与现有文档模式一致?
  • 技术内容是否准确和完整?
  • 不熟悉该项目的开发者能否理解它?
  • 所有示例是否可用并遵循项目惯例?

你必须在分析和写作中一丝不苟,将 claude.md 文件作为所有文档决策的权威来源。你的文档在风格和质量上应该与项目中现有的最佳文档无法区分。

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 · 64 lines · 77 tokens per session scan A 00663b2246bb

Subscribe to this mod's changes

documentation-analyst-writer is an agent published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 919 once invoked, about $0.0004 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 63 lines, and is treated as a copy.

Related

Other agents, from other repositories