What is Agents Directory?

A directory structure for Claude Code sub-agents, with separate definitions for development, testing, architecture, operations, documentation, analysis, and data work.

Use it to organise or create specialised agents for backend, frontend, API, security, deployment, testing, code review, documentation, and related tasks.

It gives agents clear roles, capabilities, and tool restrictions instead of keeping every task in one general-purpose agent.

How EarthmanWeb/claude-flow-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to EarthmanWeb/claude-flow-plugin. 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/EarthmanWeb/claude-flow-plugin/main/.claude/agents/README.md

Clone the repo

git clone --depth 1 https://github.com/EarthmanWeb/claude-flow-plugin

Made for: Claude Code.

Or install claude-flow, the plugin that ships this one along with the rest of its 47 commands, 7 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/earthmanweb/claude-flow-plugin/readme/github.svg)](https://agentmods.dev/agents/earthmanweb/claude-flow-plugin/readme)

Your own site

<a href="https://agentmods.dev/agents/earthmanweb/claude-flow-plugin/readme"><img src="https://agentmods.dev/badge/agents/earthmanweb/claude-flow-plugin/readme/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/earthmanweb/claude-flow-plugin/readme"><img src="https://agentmods.dev/badge/agents/earthmanweb/claude-flow-plugin/readme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 690 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.00690
Opus 5.5	$0.00007	$0.00276
Sonnet 5.5	$0.00003	$0.00138
Haiku 4.5	$0.00002	$0.00069

Measured 1mo ago against content hash 73d42cceae3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Agents Directory 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 1mo 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.

Origin

This is a copy

100% identical to Agents Directory — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/README.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Agents Directory Structure

This directory contains sub-agent definitions organized by type and purpose. Each agent has specific capabilities, tool restrictions, and naming conventions that trigger automatic delegation.

Directory Structure

.claude/agents/
├── README.md                    # This file
├── _templates/                  # Agent templates
│   ├── base-agent.yaml
│   └── agent-types.md
├── development/                 # Development agents
│   ├── backend/
│   ├── frontend/
│   ├── fullstack/
│   └── api/
├── testing/                     # Testing agents
│   ├── unit/
│   ├── integration/
│   ├── e2e/
│   └── performance/
├── architecture/                # Architecture agents
│   ├── system-design/
│   ├── database/
│   ├── cloud/
│   └── security/
├── devops/                      # DevOps agents
│   ├── ci-cd/
│   ├── infrastructure/
│   ├── monitoring/
│   └── deployment/
├── documentation/               # Documentation agents
│   ├── api-docs/
│   ├── user-guides/
│   ├── technical/
│   └── readme/
├── analysis/                    # Analysis agents
│   ├── code-review/
│   ├── performance/
│   ├── security/
│   └── refactoring/
├── data/                        # Data agents
│   ├── etl/
│   ├── analytics/
│   ├── ml/
│   └── visualization/
└── specialized/                 # Specialized agents
    ├── mobile/
    ├── embedded/
    ├── blockchain/
    └── ai-ml/

Naming Conventions

Agent files follow this naming pattern: [type]-[specialization]-[capability].agent.yaml

Examples:

dev-backend-api.agent.yaml
test-unit-jest.agent.yaml
arch-cloud-aws.agent.yaml
docs-api-openapi.agent.yaml

Automatic Delegation Triggers

Claude Code automatically delegates to agents based on:

Keywords in user request: "test", "deploy", "document", "review"
File patterns: *.test.js → testing agent, *.tf → infrastructure agent
Task complexity: Multi-step tasks spawn coordinator agents
Domain detection: Database queries → data agent, API endpoints → backend agent

Read the full file on GitHub · 89 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.

1mo ago First seen · 89 lines · 17 tokens per session scan A 73d42cceae3a

Subscribe to this mod's changes

Agents Directory is an agent published in the GitHub repository EarthmanWeb/claude-flow-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 690 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to Agents Directory, differing in 0 lines, and is treated as a copy.

Building agents agents

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

PHP MCP Expert

Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.

github/awesome-copilot · 20 tokens

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

claude-flow-plugin: Agent for Claude Code