Deep Agents is an extensible agent harness that provides an out-of-the-box agent for long, multi-step tasks, with features such as planning, sub-agents, filesystem access, context management, memory, and human approval of tool calls. It is used by developers building agents with different language models, and its catalogue entries extend the harness with reusable skills, MCP servers, and instructions.
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/langchain-ai/deepagents/skill-creatornpx skills add langchain-ai/deepagents --skill skill-creatorgit clone --depth 1 https://github.com/langchain-ai/deepagentsWrote 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.
[](https://agentmods.dev/skills/langchain-ai/deepagents/skill-creator)<a href="https://agentmods.dev/skills/langchain-ai/deepagents/skill-creator"><img src="https://agentmods.dev/badge/skills/langchain-ai/deepagents/skill-creator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00159 | $0.04138 |
| Opus 5 | $0.00079 | $0.02069 |
| Sonnet 5 | $0.00032 | $0.00828 |
| Haiku 4.5 | $0.00016 | $0.00414 |
Grade A, and why
skill-creator 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 5d 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.
This is a copy
89% identical to skill-creator — 141 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Skill Location for Deepagents
The deepagents CLI loads skills from five sources, listed here from lowest to highest precedence:
| # | Directory | Scope | Notes |
|---|---|---|---|
| 0 | <package>/built_in_skills/ |
Built-in | Ships with deepagents CLI |
| 1 | $DEEPAGENTS_HOME/<agent>/skills/ |
User (deepagents alias) | Default for deepagents skills create |
| 2 | ~/.agents/skills/ |
User | Shared across agent tools |
| 3 | .deepagents/skills/ |
Project (deepagents alias) | Default for deepagents skills create --project |
| 4 | .agents/skills/ |
Project | Shared across agent tools |
<agent> is the agent configuration name (default: agent). When two directories contain a skill with the same name, the higher-precedence version wins — project skills override user skills, and any user or project skill overrides built-in skills.
Example directory layout:
$DEEPAGENTS_HOME/agent/skills/ # user skills (lowest precedence)
├── skill-name-1/
│ └── SKILL.md
└── ...
<project-root>/.deepagents/skills/ # project skills (higher precedence)
├── skill-name-2/
│ └── SKILL.md
└── ...
Core Principles
Concise is Key
The context window is a public good. Skills share the context window with everything else the agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: The agent is already very capable. Only add context the agent doesn't already have. Challenge each piece of information: "Does the agent really need this explanation?" and "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Set Appropriate Degrees of Freedom
Match the level of specificity to the task's fragility and variability:
High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 384 lines · 159 tokens per session scan A 5da11304716c
skill-creator is a skill published in the GitHub repository langchain-ai/deepagents (28,893 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 4,138 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to skill-creator, differing in 141 lines, and is treated as a copy.
Other skills, from other repositories
code-reviewer
当用户要求进行代码审查、Code Review、查找 Bug、安全风险、性能问题或代码质量问题时使用。.
emoji-translator
当用户明确要求把自然语言翻译成 Emoji、把 Emoji 解释成文字，或要求“表情翻译/emoji 翻译”时使用。.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.
forge-platform
Use when designing, building, debugging, or explaining Forge workflows, nodes, state, routing, middleware, tools, or knowledge - especially custom/complex shapes beyond the canned builders, AND for anything about deep agents, sub-agents, or supervisor patterns (how sub-agents are wired on the canvas), or…
recover-from-failure
How to recover when a tool call fails — diagnose, not blindly retry.
workspace-conventions
Reminders about how Dawn's workspace tools behave and what the path-jail allows.