awesome-claude-agents: Instructions file for Claude Code

CLAUDE.md

awesome-claude-agents CLAUDE.md is an instructions file for Claude Code from vijaythecoder/awesome-claude-agents. It costs 2,015 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code in a collection of specialized AI agents. They describe how agents are written and how a lead agent routes complex work to other agents.

In plain words
What is it for?
Use it when creating or editing agents, coordinating multi-step development work, or following the repository's required lead-agent routing process.
Why use it?
They reduce confusion about which agent should handle a task and how agents should report findings. This is especially useful because Claude Code agents cannot directly call one another.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

This is vijaythecoder/awesome-claude-agents's own configuration. It tells Claude Code how to work on awesome-claude-agents 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 awesome-claude-agents configures →

About the project

Awesome Claude Agents is an experimental team of specialized AI agents that Claude Code coordinates to work on software projects. Developers use it to build features and investigate complex coding problems with multiple agents. Its catalogue add-ons provide the instructions and workflows that define this agent team.

vijaythecoder/awesome-claude-agents · 4,387 stars · on GitHub · x.com

Reuse

Borrowing it

Nothing to install: this file belongs to vijaythecoder/awesome-claude-agents. 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/vijaythecoder/awesome-claude-agents/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vijaythecoder/awesome-claude-agents

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 awesome-claude-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vijaythecoder/awesome-claude-agents/claude-md.svg)](https://agentmods.dev/instructions/vijaythecoder/awesome-claude-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vijaythecoder/awesome-claude-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/vijaythecoder/awesome-claude-agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,015 This file is loaded in full into every session.
When invoked 2,015 The same file — it is already loaded in full.
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 $0.02015 $0.02015
Opus 5 $0.01007 $0.01007
Sonnet 5 $0.00403 $0.00403
Haiku 4.5 $0.00201 $0.00201

Measured 9d ago against content hash c2cc9e33425e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

awesome-claude-agents CLAUDE.md 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 9d 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.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is the Awesome Claude Agents repository - a collection of specialized AI agents that extend Claude Code's capabilities through intelligent orchestration and domain expertise. The agents work together as a development team, with each agent having specific expertise and delegation patterns.

Working with Agents

When creating or modifying agents:

  1. Agents are Markdown files with YAML frontmatter
  2. Most agents should omit the tools field to inherit all available tools
  3. Use XML-style examples in descriptions for intelligent invocation
  4. Agents return structured findings for main agent coordination

Orchestration Pattern for Claude Code

Since sub-agents in Claude Code cannot directly invoke other sub-agents, orchestration follows this strict pattern:

CRITICAL: Agent Routing Protocol

When handling complex tasks, you MUST:

  1. ALWAYS start with tech-lead-orchestrator for any multi-step task
  2. FOLLOW the agent routing map returned by tech-lead EXACTLY
  3. USE ONLY the agents explicitly recommended by tech-lead
  4. NEVER select agents independently - tech-lead knows which agents exist

Example: Building a Feature with Agent Routing

User: "Build a user management system"

Main Claude Agent:
1. First, I'll use the tech-lead-orchestrator to analyze and get routing
   → Tech lead returns Agent Routing Map with SPECIFIC agents
   
2. I MUST use ONLY the agents listed in the routing map:
   - If tech-lead says "use django-api-developer" → Use that EXACT agent
   - If tech-lead says "use react-component-architect" → Use that EXACT agent
   - DO NOT substitute with generic agents unless specified as fallback
   
3. Execute tasks in the order specified by tech-lead using TodoWrite

Key Orchestration Rules

  1. Tech-Lead is Routing Authority: Tech-lead determines which agents can handle each task
  2. Strict Agent Selection: Use ONLY agents from tech-lead's "Available Agents" list
  3. No Improvisation: Do NOT select agents based on your own judgment
  4. Deep Reasoning: Apply careful thought when coordinating the recommended agents
  5. Structured Handoffs: Extract and pass information between agent invocations

Read the full file on GitHub · 263 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. 9d ago First seen · 263 lines · 2,015 tokens per session scan A c2cc9e33425e

Subscribe to this mod's changes

awesome-claude-agents CLAUDE.md is an instructions file published in the GitHub repository vijaythecoder/awesome-claude-agents (4,387 stars, last pushed 10mo ago), licensed MIT. It adds 2,015 tokens to every session, about $0.0101 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens