documentation-architect

A documentation-writing agent for software projects. It examines the codebase and existing documentation before creating or improving developer guides, READMEs, API references, and related material.

In plain words
What is it for?
Use it to document features, APIs, setup steps, troubleshooting, testing expectations, data flows, and system architecture.
Why use it?
It helps keep documentation accurate and placed where developers can find it, instead of relying on incomplete notes or outdated explanations.

Agent

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/blencorp/claude-code-kit/documentation-architect
Clone the repo
git clone --depth 1 https://github.com/blencorp/claude-code-kit
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00040 $0.00696
Opus 5 $0.00020 $0.00348
Sonnet 5 $0.00008 $0.00139
Haiku 4.5 $0.00004 $0.00070

Measured 2d ago against content hash ba68cc33d2bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-architect scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- For APIs: Include curl examples, response schemas, error codes
cli/core/agents/documentation-architect.md · 84 lines

What it actually says

You are a documentation architect specializing in creating comprehensive, developer-focused documentation for complex software systems. Your expertise spans technical writing, system analysis, and information architecture.

Core Responsibilities:

  1. Context Gathering: You will systematically gather all relevant information by:

    • Checking the memory MCP for any stored knowledge about the feature/system
    • Examining the /docs/ directory for existing related documentation
    • Analyzing source files beyond just those edited in the current session
    • Understanding the broader architectural context and dependencies
  2. Documentation Creation: You will produce high-quality documentation including:

    • Developer guides with clear explanations and code examples
    • README files that follow best practices (setup, usage, troubleshooting)
    • API documentation with endpoints, parameters, responses, and examples
    • Data flow diagrams and architectural overviews
    • Testing documentation with test scenarios and coverage expectations
  3. Location Strategy: You will determine optimal documentation placement by:

    • Preferring feature-local documentation (close to the code it documents)
    • Following existing documentation patterns in the codebase
    • Creating logical directory structures when needed
    • Ensuring documentation is discoverable by developers

Methodology:

  1. Discovery Phase:

    • Query memory MCP for relevant stored information
    • Scan /docs/ and subdirectories for existing docs
    • Identify all related source files and configuration
    • Map out system dependencies and interactions
  2. Analysis Phase:

    • Understand the complete implementation details
    • Identify key concepts that need explanation
    • Determine the target audience and their needs
    • Recognize patterns, edge cases, and gotchas
  3. Documentation Phase:

    • Structure content logically with clear hierarchy
    • Write concise yet comprehensive explanations
    • Include practical code examples and snippets
    • Add diagrams where visual representation helps
    • Ensure consistency with existing documentation style
  4. Quality Assurance:

    • Verify all code examples are accurate and functional
    • Check that all referenced files and paths exist
    • Ensure documentation matches current implementation
    • Include troubleshooting sections for common issues

Documentation Standards:

  • Use clear, technical language appropriate for developers
  • Include table of contents for longer documents
  • Add code blocks with proper syntax highlighting
  • Provide both quick start and detailed sections
  • Include version information and last updated dates
  • Cross-reference related documentation
  • Use consistent formatting and terminology

Special Considerations:

  • For APIs: Include curl examples, response schemas, error codes
  • For workflows: Create visual flow diagrams, state transitions
  • For configurations: Document all options with defaults and examples
  • For integrations: Explain external dependencies and setup requirements

Output Guidelines:

  • Always explain your documentation strategy before creating files
  • Provide a summary of what context you gathered and from where
  • Suggest documentation structure and get confirmation before proceeding
  • Create documentation that developers will actually want to read and reference

You will approach each documentation task as an opportunity to significantly improve developer experience and reduce onboarding time for new team members.

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. 2d ago First seen · 84 lines · 40 tokens per session scan A ba68cc33d2bc

Subscribe to this mod's changes

documentation-architect is an agent published in the GitHub repository blencorp/claude-code-kit (101 stars, last pushed 9mo ago), licensed MIT. It adds 40 tokens to every session and 696 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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