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.
npx agentmods add instructions/eigenwise/atomic-agents/agents-mdgit clone --depth 1 https://github.com/Eigenwise/atomic-agentsWhat 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 | $0.03278 | $0.03278 |
| Opus 5 | $0.01639 | $0.01639 |
| Sonnet 5 | $0.00656 | $0.00656 |
| Haiku 4.5 | $0.00328 | $0.00328 |
Grade B, and why
atomic-agents AGENTS.md scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Skill convention: frontmatter `name` + `description` (optional `allowed-tools`); one skill per dir at `.claude/skills/<name>/SKILL.md` How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atomic Agents Monorepo
What is this Repository?
atomic-monorepo is the development repository for Atomic Agents, a lightweight and modular Python framework for building Agentic AI applications. The framework is built around the principle of atomicity - creating single-purpose, reusable, and composable components for AI pipelines.
Core Philosophy
Atomic Agents bridges the gap between flexibility and reliability in production AI applications by providing:
- Predictable AI Behavior: Controlled, schema-driven agent construction vs. autonomous but unpredictable multi-agent systems
- Modular Development: Build AI applications using familiar software engineering principles (LEGO-like composability)
- Type Safety: Consistent input/output contracts through Pydantic schemas
- Developer Control: Full visibility and control over AI behavior with no hidden abstractions
Built on top of Instructor (for structured LLM outputs) and Pydantic (for data validation).
Monorepo Structure
This repository contains four main packages/projects:
atomic-monorepo/
├── atomic-agents/ # Core framework library (main package)
├── atomic-assembler/ # CLI tool for managing components
├── atomic-examples/ # Example projects and use cases
├── atomic-forge/ # Collection of downloadable tools
├── docs/ # Sphinx documentation
├── guides/ # Development guides
├── .github/workflows/ # CI/CD pipelines
├── pyproject.toml # Project configuration
└── README.md # Main documentation
Package Details
1. atomic-agents/ - Core Framework
Published as: atomic-agents on PyPI (version lives in the root pyproject.toml)
Purpose: Main Python package containing all core framework components
Key Components:
agents/- AtomicAgent class and agent configurationbase/- Base abstractions (BaseIOSchema, BaseTool, BaseToolConfig)context/- ChatHistory, SystemPromptGenerator, dynamic context providersconnectors/- External integrations (MCP support)utils/- Shared utilities (token counting, formatting)
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.
- yesterday First seen · 415 lines · 3,278 tokens per session scan B 2d7538b6b60b
atomic-agents AGENTS.md is an instructions file published in the GitHub repository Eigenwise/atomic-agents (6,213 stars, last pushed 8d ago), licensed MIT. It adds 3,278 tokens to every session, about $0.0164 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
llm AGENTS.md
Instructions for simonw/llm, covering agents.md, setting up a development environment and building the documentation.
AutoGPT copilot-instructions.md
Copilot instructions for Significant-Gravitas/AutoGPT, covering github copilot instructions for autogpt, repository overview, build and validation instructions, essential setup commands and runtime requirements.
AutoGPT AGENTS.md
AGENTS.md instructions for Significant-Gravitas/AutoGPT, covering autogpt platform contribution guide, directory overview, code style, frontend guidelines and testing.
AutoGPT CLAUDE.md
Claude Code instructions for Significant-Gravitas/AutoGPT, a project described as: AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
langfuse AGENTS.md
AGENTS.md instructions for langfuse/langfuse, a project described as: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23.
langfuse CLAUDE.md
Claude Code instructions for langfuse/langfuse, a project described as: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23.