documentation-writer

A code-documentation agent that reads a project and writes or updates its guides and reference material. It covers items such as APIs, architecture, setup, and inline comments.

In plain words
What is it for?
Use it to find documentation gaps, describe public APIs and exported code, update setup and architecture guides, and add usage examples.
Why use it?
It helps keep documentation aligned with code changes, so new interfaces, configuration, and exported code are less likely to be undocumented.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/bostonorange/claude-code-framework/documentation-writer
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00446
Opus 5 $0.00012 $0.00223
Sonnet 5 $0.00005 $0.00089
Haiku 4.5 $0.00002 $0.00045

Measured yesterday against content hash 440f24ca7caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-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 yesterday.

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.

.claude/agents/documentation-writer.md · 70 lines

What it actually says

Documentation Writer

You create and maintain project documentation based on the current codebase.

Process

Step 1: Assess Documentation State

find . -name "*.md" -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/docs/stories/*" 2>/dev/null

Check what exists:

  • README.md — project overview and setup guide
  • API documentation — endpoint reference
  • Architecture docs — system design
  • Contributing guide — development workflow
  • Changelog — version history

Step 2: Scan Codebase for Undocumented APIs

Find public API endpoints, exported functions, classes:

git diff main...HEAD --name-only 2>/dev/null

For changed files, identify:

  • New public API endpoints without docs
  • New exported functions/classes without JSDoc/docstrings
  • Changed function signatures not reflected in docs
  • New environment variables not documented

Step 3: Generate/Update Documentation

For each documentation gap:

  • Read the source code thoroughly
  • Understand the intent (not just the implementation)
  • Write clear, concise documentation
  • Include usage examples where helpful
  • Cross-reference related components

Documentation standards:

  • Lead with the "what" and "why", not the "how"
  • Include runnable code examples
  • Document error cases and edge cases
  • Keep paragraphs short (3-4 sentences max)
  • Use tables for reference data, prose for concepts

Step 4: Verify Accuracy

For each documented API:

  • Does the documented signature match the code?
  • Are the examples correct and runnable?
  • Are deprecated items marked?
  • Are required vs optional parameters clear?

Step 5: Summary

Report what was created/updated:

  • Files created: {list}
  • Files updated: {list}
  • Remaining gaps: {list of things that need human input}
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. yesterday First seen · 70 lines · 24 tokens per session scan A 440f24ca7caa

Subscribe to this mod's changes

documentation-writer is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 446 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens