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 skills/eigenwise/atomic-agents/create-atomic-agentnpx skills add Eigenwise/atomic-agents --skill create-atomic-agentgit 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 | $0.00093 | $0.01825 |
| Opus 5 | $0.00046 | $0.00912 |
| Sonnet 5 | $0.00019 | $0.00365 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
create-atomic-agent 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an Atomic Agent
An agent is an LLM-backed transformer from one BaseIOSchema to another. Building one means: design the schemas, write the system prompt, wire the provider client, build the AgentConfig, instantiate AtomicAgent[In, Out].
For deep material (streaming, token counting, hooks, multi-agent memory), the authority is ../framework/references/agents.md plus providers.md, prompts.md, and memory.md. This skill is the action-oriented path: clarify → write → run.
When this fires vs the umbrella framework skill
- This skill: the user is creating or wiring a specific agent — "add a planner agent", "build a Q&A agent", "make a router that classifies tickets".
frameworkskill: questions about Atomic Agents in general, or the user is doing something other than authoring an agent.
Phase 1 — Clarify
Bundle into one message:
- What should the agent do? One sentence. Becomes the persona /
backgroundline. - Inputs and outputs. Use
BasicChatInputSchema/BasicChatOutputSchemafor free-form chat. Use a custom pair for anything structured (extraction, classification, planning, routing). When custom, branch to thecreate-atomic-schemaskill for the schema authoring. - Provider. OpenAI / Anthropic / Groq / Ollama / Gemini / OpenRouter / MiniMax. Default: whatever the project already uses; otherwise OpenAI.
- Conversational? Yes → wire a
ChatHistory. No (single-shot transformer) → omit it for stateless behavior. - Context providers. Anything to inject into the prompt at runtime (current time, user identity, retrieved docs)? If yes, plan to also use the
create-atomic-context-providerskill afterwards.
Skip anything already settled in context.
Phase 2 — Plan
State the plan in one short block:
- File:
<project>/agents/<agent_name>.py(or directly inmain.pyfor a tiny project — see../framework/references/project-structure.md). - Schemas: which pair, where they live.
- Provider + model + Instructor mode. Default models: OpenAI
gpt-5-mini, Anthropicclaude-haiku-4-5, Groqllama-3.3-70b-versatile, Ollamallama3.1, Geminigemini-2.5-flash. SystemPromptGeneratorcontent — three sections:background,steps,output_instructions.- History? Hooks? Context providers?
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.
- 2d ago First seen · 161 lines · 93 tokens per session scan A 278b9aaeeaa0
create-atomic-agent is a skill published in the GitHub repository Eigenwise/atomic-agents (6,218 stars, last pushed 9d ago), licensed MIT. It adds 93 tokens to every session and 1,825 once invoked, about $0.0005 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.
Other skills, from other repositories
add-harness-package
Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness- package that adapts a coding-agent runtime to HarnessV1.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
agent-setup-maintenance
Shared workflow for editing Langfuse's repo-owned agent setup under .agents/. Use when changing AGENTS files, shared skills, .agents/config.json, generated shim behavior, provider discovery paths, or install-time agent sync.
create-repo-agent
Design, implement, review, or harden Langfuse repo-owned autonomous agents. Use for LLM-powered GitHub Actions, scheduled or dispatched agents, agent-created PRs, prompts, allowlists, tokens, untrusted content, or self-updating instructions.
orchestrate
Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees…
auto
Autonomous pipeline: claim → experiment (mechanism routing folded in) → verify → iteration. Each stage is delegated to an isolated agent with its own context window and configurable model. Gates are AUTOPROCEED-governed; defaults run end-to-end without human input. Use when user says "auto pipeline", or wants the core…