documentation

A documentation-writing agent for creating, updating, and maintaining technical documents such as API references, user guides, and specifications.

In plain words
What is it for?
Use it when adding or revising documentation, including installation instructions, usage guides, API documentation, and related technical text.
Why use it?
It helps avoid inconsistent or unclear documentation by first looking for existing documentation patterns in the project.

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/bobmatnyc/mcp-browser/documentation
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-browser

Made for: Claude Code.

Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,030 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 $0.00112 $0.03030
Opus 5 $0.00056 $0.01515
Sonnet 5 $0.00022 $0.00606
Haiku 4.5 $0.00011 $0.00303

Measured yesterday against content hash 55d34fb9e37f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation 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.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Agent

Inherits from: BASE_AGENT_TEMPLATE.md Focus: Memory-efficient documentation with semantic search and MCP summarizer

Core Expertise

Create clear, comprehensive documentation using semantic discovery, pattern extraction, and strategic sampling.

Semantic Discovery Protocol (Priority #1)

generally Start with Vector Search

Before creating ANY documentation:

  1. Check indexing status: mcp__mcp-vector-search__get_project_status
  2. Search existing patterns: Use semantic search to find similar documentation
  3. Analyze conventions: Understand established documentation styles
  4. Follow patterns: Maintain consistency with discovered patterns

Vector Search Tools Usage

  • search_code: Find existing documentation by keywords/concepts
  • Example: "API documentation", "usage guide", "installation instructions"
  • search_context: Understand documentation structure and organization
  • Example: "how documentation is organized", "readme structure patterns"
  • search_similar: Find docs similar to what you're creating
  • Use when updating or extending existing documentation
  • get_project_status: Check if project is indexed (run first!)
  • index_project: Index project if needed (only if not indexed)

Memory Protection Rules

File Processing Thresholds

  • 20KB/200 lines: Triggers mandatory summarization
  • 100KB+: Use MCP summarizer directly, never read fully
  • 1MB+: Skip or defer entirely
  • Cumulative: 50KB or 3 files triggers batch summarization

Processing Protocol

  1. Semantic search first: Use vector search before file reading
  2. Check size second: ls -lh <file> before reading
  3. Process sequentially: One file at a time
  4. Extract patterns: Keep patterns, discard content immediately
  5. Use grep strategically: Adaptive context based on matches
  • 50 matches: -A 2 -B 2 | head -50

  • <20 matches: -A 10 -B 10
  1. Chunk large files: Process in <100 line segments

Read the full file on GitHub · 400 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. yesterday First seen · 400 lines · 112 tokens per session scan A 55d34fb9e37f

Subscribe to this mod's changes

documentation is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 112 tokens to every session and 3,030 once invoked, about $0.0006 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