deepagents-cli-deepagents-skill
Advanced tools
A LangGraph Deep Agents Skill for the LangChain Deep Agents CLI
Scaffold a production-grade Deep Agents Skill that gives LangGraph Deep Agents comprehensive, structured knowledge of the Deep Agents CLI — commands, providers, memory, sandboxes, streaming, and SDK customization.
Installation · What Gets Installed · Skill Resources · Official Documentation
The Deep Agents CLI is LangChain's terminal coding agent — a LangGraph-powered assistant with persistent memory, 20+ LLM provider integrations, sandboxed code execution, and a composable skills system. Its surface area spans interactive and non-interactive modes, a rich slash-command REPL, programmatic SDK customization, streaming output, and the Agent Client Protocol for editor integration.
This package scaffolds a Deep Agents Skill that encodes that entire surface area as structured, on-demand knowledge. When the skill is active, the agent can accurately assist with any Deep Agents CLI task — from launching a first session to building production subagent pipelines — without requiring repeated context or pasted documentation.
The skill follows the Agent Skills open standard and loads automatically via progressive disclosure when relevant.
Installs the skill into the current project's .deepagents/skills/ directory. Check it into version control to share it with your team.
npx deepagents-cli-deepagents-skill init
Installs the skill to ~/.deepagents/<agent>/skills/ so it is available across all projects for a specific agent.
npx deepagents-cli-deepagents-skill init --personal
By default, the skill installs to the default agent. To install for a named agent:
npx deepagents-cli-deepagents-skill init --personal --agent my-agent
You can also create a skill scaffold with the Deep Agents CLI and copy the files manually:
# Create the skill directory
deepagents skills create deepagents-cli
# Copy skill files into it
cp -r /path/to/deepagents-cli/* ~/.deepagents/<agent>/skills/deepagents-cli/
For programmatic use with the Deep Agents SDK, skills can be loaded via any backend:
FilesystemBackend (recommended for local development):
from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend
agent = create_deep_agent(
backend=FilesystemBackend(root_dir="/path/to/project"),
skills=["/path/to/project/.deepagents/skills/"],
)
StateBackend (default, for virtual filesystems):
from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver
# Load skill files into the virtual filesystem
skills_files = {
"/skills/deepagents-cli/SKILL.md": create_file_data(open("SKILL.md").read()),
# ... add reference files as needed
}
agent = create_deep_agent(
skills=["./skills/"],
checkpointer=MemorySaver(),
)
result = agent.invoke(
{"messages": [...], "files": skills_files},
config={"configurable": {"thread_id": "123"}}
)
| Flag | Description | Default |
|---|---|---|
--personal | Install to ~/.deepagents/<agent>/skills/ (personal scope) | false |
--agent <name> | Agent name for personal install | default |
--path <dir> | Target directory for workspace installation | Current directory |
--force | Skip confirmation when skill directory already exists | false |
--help | Show usage information | — |
--version | Show installed version | — |
To update the skill after a new release, re-run the init command. Existing files are never overwritten; only files added in the new release will be created.
.deepagents/skills/deepagents-cli/
├── SKILL.md Main skill definition and quick-start reference
└── references/
├── cli-reference.md Complete CLI commands, flags, and keyboard shortcuts
├── providers.md LLM provider configuration and config.toml schema
├── skills-system.md Skills creation, SKILL.md format, progressive disclosure
├── memory-and-persistence.md Memory system, AGENTS.md, SDK long-term memory
├── sandboxes.md Sandbox providers: Modal, Runloop, Daytona, LangSmith
├── sdk-customization.md create_deep_agent(), middleware, subagents, backends, HITL
├── streaming.md Streaming modes, subgraph streaming, frontend integration
├── acp.md Agent Client Protocol and editor integrations
└── workflows.md Automation patterns, CI/CD, troubleshooting
The skill follows the Agent Skills progressive disclosure model: SKILL.md is the primary context loaded by the agent, and the reference files are surfaced on-demand as the task requires them. This keeps the token footprint minimal while making the full surface area available.
Each reference file is a structured knowledge document scoped to a specific area of the Deep Agents CLI. All content is sourced from the official LangChain Deep Agents documentation and aligned with the documented API.
Purpose: Entry point for the skill. Contains a concise overview, quick-start examples, core concept summaries, and links to all reference files.
Value: The agent reads this file first when the skill is activated. It provides enough context to handle the most common tasks immediately and directs the agent to the appropriate reference file for deeper questions, keeping initial token usage minimal.
File: references/cli-reference.md
Source: CLI Overview
Complete reference for every command, flag, slash command, and keyboard shortcut in the Deep Agents CLI.
File: references/providers.md
Source: Model Providers
Configuration reference for all 20+ supported LLM providers.
File: references/skills-system.md
Source: Skills
Detailed guide to the Deep Agents skills system.
File: references/memory-and-persistence.md
Source: Long-term Memory
Covers both layers of the Deep Agents memory system.
File: references/sandboxes.md
Source: Sandboxes
Setup and configuration guide for all four supported sandbox providers.
File: references/sdk-customization.md
Sources: Customization, Subagents, Backends, Human-in-the-Loop, Middleware
Programmatic usage of the Deep Agents SDK via create_deep_agent().
File: references/streaming.md
Sources: Streaming Overview, Streaming Frontend
Streaming output reference for both CLI and SDK usage.
File: references/acp.md
Source: Agent Client Protocol
Reference for the Agent Client Protocol (ACP).
File: references/workflows.md
Practical reference for automation and scripted usage.
This skill is built to the Agent Skills open standard and the Deep Agents Skills specification:
| Requirement | Implementation |
|---|---|
SKILL.md with YAML frontmatter | name, description, and compatibility fields present; description written for accurate progressive disclosure matching |
| Narrow, outcome-focused scope | Skill scoped entirely to Deep Agents CLI knowledge; single domain, single responsibility |
| Co-located supporting files | references/ directory co-located with SKILL.md inside the skill directory |
| Progressive disclosure | SKILL.md is the primary context under 500 lines; reference files are loaded on-demand by topic |
| Automatic discovery | Deep Agents loads the skill automatically when the description matches the task |
| Personal and workspace scopes | --personal targets ~/.deepagents/<agent>/skills/; default targets <project>/.deepagents/skills/ |
| Never overwrites existing files | The installer skips any file that already exists at the target path |
All technical content in this skill is sourced from and cross-referenced against the official LangChain Deep Agents documentation:
Deep Agents Skills specification: https://docs.langchain.com/oss/python/deepagents/skills Agent Skills open standard: https://agentskills.io/specification
MIT — see LICENSE for details.
FAQs
Deep Agents CLI skill for LangGraph Deep Agents
The npm package deepagents-cli-deepagents-skill receives a total of 8 weekly downloads. As such, deepagents-cli-deepagents-skill popularity was classified as not popular.
We found that deepagents-cli-deepagents-skill demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Threat Research
Malicious Firefox extensions mimic Phantom, Jupiter, and Bitget wallets to steal recovery phrases and private keys, with one fetching its payload remotely.
Product
Socket Threat Intel now shows which malware campaigns were blocked or detected in your organization, with links to scans and Firewall events.
Security News
Fixes for eMudhra and Brotli are out. Getting them everywhere they’re needed means tracking down bundled libraries, runtimes, and certificate stores.