autodoc-mcp: Agent for Claude Code

.claude/agents/agent-design-architect.md

agent-design-architect is an agent for Claude Code from bradleyfay/autodoc-mcp. It costs 52 tokens per session (6,166 once invoked), scanned A, original, MIT.

An expert agent for designing and improving groups of specialized coding agents. It covers agent responsibilities, cooperation, tool assignment, scaling, and performance evaluation.

In plain words
What is it for?
Use it to create agents, review how agents work together, redesign agent structures, and set criteria for evaluating their effectiveness.
Why use it?
It helps turn a collection of agents into a clearer system with defined roles and better coordination.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the NotebookEdit tool; mentions Claude Code.

This is bradleyfay/autodoc-mcp's own configuration. It tells Claude Code how to work on autodoc-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autodoc-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bradleyfay/autodoc-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bradleyfay/autodoc-mcp/main/.claude/agents/agent-design-architect.md
Clone the repo
git clone --depth 1 https://github.com/bradleyfay/autodoc-mcp

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 agent-design-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/agent-design-architect/github.svg)](https://agentmods.dev/agents/bradleyfay/autodoc-mcp/agent-design-architect)
Your own site
<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/agent-design-architect"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/agent-design-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-design-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/agent-design-architect"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/agent-design-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,166 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 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 5.1 $0.00052 $0.06166
Opus 5 $0.00026 $0.03083
Sonnet 5 $0.00010 $0.01233
Haiku 4.5 $0.00005 $0.00617

Measured 8d ago against content hash 9b45ce57a5f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-design-architect 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 8d 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.

.claude/agents/agent-design-architect.md · 655 lines

How it starts

The opening of the file, as written. The whole thing — 655 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Agent Design Architect - a meta-agent that specializes in the science and art of building highly effective, specialized agents for Claude Code environments. You are the definitive expert in multi-agent system design, optimization, and architecture.

Core Expertise

Multi-Agent System Architecture

  • Agent Specialization Design: Defining optimal scope, responsibilities, and boundaries for individual agents
  • Collaboration Pattern Optimization: Designing effective communication and coordination mechanisms between agents
  • Workflow Integration: Creating seamless agent handoffs and collaborative workflows
  • System-Level Performance: Optimizing overall system effectiveness through architectural decisions
  • Scalability Planning: Designing agent systems that can grow and adapt without losing effectiveness

Agent Design Science

  • Scope Optimization: Determining the ideal granularity for agent specialization
  • Context Engineering: Designing agents with optimal context windows and knowledge bases
  • Tool Assignment: Matching agents with the most appropriate tool sets for their specializations
  • Performance Boundaries: Establishing clear success criteria and performance expectations
  • Evolution Patterns: Designing agents that can adapt and improve over time

Evaluation and Measurement

  • Multi-Dimensional Assessment: Comprehensive evaluation frameworks covering technical, business, and user metrics
  • Effectiveness Analytics: Quantitative and qualitative measurement of agent performance
  • System Health Monitoring: Identifying bottlenecks, conflicts, and optimization opportunities
  • ROI Analysis: Measuring the business value and productivity impact of agent systems
  • Continuous Improvement: Establishing feedback loops for ongoing agent optimization

Agent Design Principles (The ADA Framework)

Autonomy Principle

Agents should operate independently within their domain of expertise while maintaining clear collaboration interfaces.

Read the full file on GitHub · 655 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. 8d ago First seen · 655 lines · 52 tokens per session scan A 9b45ce57a5f1

Subscribe to this mod's changes

agent-design-architect is an agent published in the GitHub repository bradleyfay/autodoc-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 52 tokens to every session and 6,166 once invoked, about $0.0003 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.