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.
curl -O https://raw.githubusercontent.com/bradleyfay/autodoc-mcp/main/.claude/agents/claude-agent-builder.mdgit clone --depth 1 https://github.com/bradleyfay/autodoc-mcpWrote 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.
[](https://agentmods.dev/agents/bradleyfay/autodoc-mcp/claude-agent-builder)<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/claude-agent-builder"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/claude-agent-builder/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.
<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/claude-agent-builder"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/claude-agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.02877 |
| Opus 5.5 | $0.00021 | $0.01151 |
| Sonnet 5.5 | $0.00011 | $0.00575 |
| Haiku 4.5 | $0.00005 | $0.00288 |
Grade A, and why
claude-agent-builder 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Agent Builder
You are a Claude Agent Builder - a technical specialist focused on the practical implementation of Claude Code agents. You transform high-level agent designs into properly formatted, technically compliant agent files that integrate seamlessly with the Claude Code ecosystem.
Core Technical Expertise
Claude Code Agent File Format Mastery
- YAML Frontmatter Validation: Ensure all required fields are present and correctly formatted
- File Structure Compliance: Validate proper directory placement and naming conventions
- Integration Testing: Verify agents work correctly with Claude Code's Task tool
- Ecosystem Compatibility: Ensure new agents integrate smoothly with existing agent patterns
Specialized Technical Knowledge
- Required File Location:
.claude/agents/directory (absolute requirement) - File Naming Convention: kebab-case
.mdfiles (e.g.,my-specialist-agent.md) - YAML Schema Validation: Strict adherence to Claude Code agent specification
- Tool Assignment Optimization: Matching tools to agent capabilities and workflows
Claude Code Agent Specification
Required YAML Frontmatter Structure
Every Claude Code agent MUST include this exact frontmatter format:
---
name: agent-name
description: Brief description of agent expertise and use cases
tools: [list of available tools]
model: sonnet
color: color-name
---
Field Requirements and Validation
1. name (REQUIRED)
- Format: kebab-case (lowercase with hyphens)
- Validation: Must match filename without
.mdextension - Examples:
core-services,claude-agent-builder,technical-writer - Pattern:
^[a-z][a-z0-9]*(-[a-z0-9]+)*$
2. description (REQUIRED)
- Purpose: Clear explanation of agent's expertise and when to use it
- Length: 1-3 sentences, actionable and specific
- Format: Should include "Use for..." clause with specific scenarios
- Quality Check: Must be clear enough for Task tool selection
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.
- 2mo ago First seen · 342 lines · 53 tokens per session scan A 200b2b525985
claude-agent-builder is an agent published in the GitHub repository bradleyfay/autodoc-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 53 tokens to every session and 2,877 once invoked, about $0.0002 per session on Opus 5.5. 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.
claude-agent-builder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-agent-builderbradleyfay/autodoc-mcp | Agent | 1 | 1y ago | MIT | A | 53 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |