One skill. Four platforms. The complete deepagents CLI reference and usage guide,
packaged as an Agent Skill for every major coding agent.
The deepagents CLI skill gives your coding agent comprehensive knowledge of the deepagents terminal assistant -- including session configuration, provider setup, memory management, skill authoring, sandbox execution, and workflow automation. Each variant below is the same skill adapted for a specific agent platform's filesystem conventions and invocation patterns.
This isn't just a documentation reference. When your coding agent has this skill loaded, it can actively help you work with deepagents -- not just answer questions about it.
- Learn by building. Ask your agent to walk you through deepagents concepts, then have it set up a session, configure providers, or scaffold a skill -- all from within your current editor.
- Author custom agents. The skill includes the full SDK reference for
create_deep_agent(), middleware, subagents, and backends. Your agent can help you design and implement specialized deepagents workflows tailored to your stack. - Extend deepagents itself. Clone the deepagents repo, install this skill, and let your coding agent help you customize the framework -- adding tools, modifying behavior, or building production pipelines.
The skill covers everything from first launch to programmatic customization, so your agent grows with you.
|
For the LangGraph deepagents framework. Supports named agent instances via the
|
|
For Claude Code, Claude Desktop, and claude.ai. Install via CLI or download the zip directly for Claude Desktop upload.
|
|
For OpenAI Codex. Filesystem-based skill loading with support for the
|
|
For Factory.ai Droid. This is the original, authoritative version of the skill.
|
Every variant ships with the same comprehensive reference set:
| Document | Coverage |
|---|---|
| CLI Reference | Commands, flags, configuration options |
| Providers | LLM provider setup -- OpenAI, Anthropic, Google, AWS Bedrock, local models |
| Skills System | Authoring, installing, and managing agent skills |
| Memory and Persistence | Conversation memory, AGENTS.md context files, state management |
| Sandboxes | Docker and cloud sandbox configuration for safe code execution |
| SDK Customization | Python SDK for building custom agents, tools, and integrations |
| Streaming | Real-time token streaming, event hooks, output handling |
| Agent Communication Protocol | Inter-agent messaging and coordination via ACP |
| Workflows | Multi-step automation, CI/CD patterns, scripted agent pipelines |
- Agent Skills Specification -- The open standard these skills follow
- deepagents CLI Documentation -- Official deepagents docs
- deepagents GitHub -- Source repository