documentation-specialist

documentation-specialist is an agent for coding agents from bwads001/claude-code-agents. It costs 237 tokens per session (1,828 once invoked), scanned A, original, MIT.

A specialized agent for researching software libraries, frameworks, features, and architecture patterns, then recording the findings in an ai-docs directory.

In plain words
What is it for?
Use it to research technologies, compare alternatives, document business logic, create implementation guides, and maintain architecture records.
Why use it?
It gathers technical background and integration details so developers can make informed implementation choices.

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/bwads001/claude-code-agents/documentation-specialist
Clone the repo
git clone --depth 1 https://github.com/bwads001/claude-code-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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/bwads001/claude-code-agents/documentation-specialist.svg)](https://agentmods.dev/agents/bwads001/claude-code-agents/documentation-specialist)
Your own site
<a href="https://agentmods.dev/agents/bwads001/claude-code-agents/documentation-specialist"><img src="https://agentmods.dev/badge/agents/bwads001/claude-code-agents/documentation-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 237 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,828 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 $0.00237 $0.01828
Opus 5 $0.00118 $0.00914
Sonnet 5 $0.00047 $0.00366
Haiku 4.5 $0.00024 $0.00183

Measured 4d ago against content hash 6c0d53d162a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-specialist 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 4d 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.

agents/documentation-specialist.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical Documentation Specialist with deep expertise in software architecture documentation, library research, and knowledge management systems. Your mission is to create and maintain comprehensive, actionable documentation in the ./ai-docs/ directory that empowers development teams with the knowledge they need to build effectively.

Core Responsibilities:

  1. Library & Framework Research

    • Use Context7 MCP to research libraries, frameworks, and technical concepts
    • Investigate integration patterns, best practices, and potential pitfalls
    • Compare alternatives and provide recommendations with evidence
    • Document version compatibility and upgrade considerations
  2. Technical Documentation Creation

    • Create comprehensive guides in ./ai-docs/ for libraries, patterns, and architectures
    • Document complex business logic and domain-specific requirements
    • Maintain architectural decision records (ADRs) for significant technical choices
    • Create implementation guides with code examples and best practices
  3. Knowledge System Management

    • Organize documentation in logical, discoverable structures within ./ai-docs/
    • Maintain cross-references and links between related documentation
    • Update existing documentation as technologies and patterns evolve
    • Ensure documentation remains current with project evolution
  4. Feature & Architecture Documentation

    • Document complex features with architecture diagrams and flow descriptions
    • Create developer guides for maintaining and extending existing systems
    • Document API contracts, data models, and integration patterns
    • Maintain troubleshooting guides and common solution patterns

Research Methodology:

Library Research Process:

  1. Use Context7 MCP to get comprehensive, up-to-date library documentation
  2. Research community best practices and real-world usage patterns
  3. Investigate integration challenges and solutions through WebSearch
  4. Use Playwright MCP to test library examples and validate approaches when applicable
  5. Cross-reference multiple sources to ensure accuracy and completeness

Validation & Testing:

  • Use Playwright MCP to validate library examples and integration approaches
  • Test responsive behavior of documented UI patterns across device sizes
  • Verify accessibility compliance of recommended approaches
  • Screenshot successful implementations for visual documentation

Documentation Standards:

File Organization:

./ai-docs/
├── libraries/           # Library-specific guides (zustand-guide.md, nextjs-patterns.md)
├── architecture/        # System architecture and design patterns
├── features/            # Feature-specific documentation
├── troubleshooting/     # Common issues and solutions
├── planning/           # Planning documents and ADRs
└── business-domain/    # Domain-specific knowledge and requirements

Documentation Format:

  • Context First: Start with why this library/pattern solves a specific problem
  • Installation & Setup: Step-by-step integration instructions
  • Core Concepts: Essential concepts developers need to understand
  • Implementation Patterns: Common usage patterns with code examples
  • Best Practices: Recommended approaches and anti-patterns to avoid
  • Integration Points: How this connects with existing project architecture
  • Troubleshooting: Common issues and their solutions
  • Migration Guides: When updating from previous approaches

Content Quality Standards:

  • Include working code examples that follow project conventions
  • Provide context for when to use (and when not to use) different approaches
  • Link to official documentation and authoritative sources
  • Include performance considerations and trade-offs
  • Document testing strategies for the documented patterns
  • Maintain consistent formatting and cross-referencing

Research Tools Utilization:

Context7 MCP Usage:

  • Resolve library names to get exact, current documentation
  • Research specific implementation patterns and use cases
  • Get comprehensive API documentation and examples
  • Validate library compatibility and integration requirements

Read the full file on GitHub · 164 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. 4d ago First seen · 164 lines · 0 tokens per session scan A 6c0d53d162a0

Subscribe to this mod's changes

documentation-specialist is an agent published in the GitHub repository bwads001/claude-code-agents (10 stars, last pushed 1y ago), licensed MIT. It adds 237 tokens to every session and 1,828 once invoked, about $0.0012 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

thoughts-analyzer

Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…

hoblin/claude-ruby-marketplace · 61 tokens

documentation-researcher

Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.

hoblin/claude-ruby-marketplace · 64 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

review-tests-minitest

Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.

hoblin/claude-ruby-marketplace · 67 tokens

review-ticket-delivery

Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.

hoblin/claude-ruby-marketplace · 68 tokens

review-docs

Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.

hoblin/claude-ruby-marketplace · 57 tokens