Deepagents
Scraped LangChain Deep Agents docs for backends, subagents, and human-in-the-loop config.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · bd4227b
Correctly gave the real write()/edit() -> WriteResult/EditResult policy-hook API where a from-memory baseline invented a plausible-but-wrong write_file() method, but the SKILL.md body is padded with two full raw webpage scrapes (nav chrome, 'Search...⌘K' cruft included) and the suite's README oversells it as a '自研' (self-authored) skill when the file itself admits it was scraper-generated.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What Deepagents does
Bundles LangChain's official deepagents documentation (backends, subagents, human-in-the-loop, memory, middleware, CLI) as an auto-generated reference skill. Triggers when the user is building, customizing, or debugging a deepagents-based autonomous coding agent.
How to install Deepagents
git clone https://github.com/joneqian/claude-skills-suite
cd claude-skills-suite
mkdir -p ~/.claude/skills
cp -r skills/deepagents ~/.claude/skills/deepagents
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Deepagents
-
/deepagentsScraped LangChain Deep Agents docs for backends, subagents, and human-in-the-loop config.
It also activates on plain-language prompts like these:
-
show me how to configure a FilesystemBackend for my deep agent -
help me add a human in the loop approval step to my deepagents agent -
explain how subagent delegation works in the deepagents framework
Frequently asked questions
- Is the Deepagents skill free?
- Yes. The skill itself is free from joneqian/claude-skills-suite. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Deepagents work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Correctly gave the real write()/edit() -> WriteResult/EditResult policy-hook API where a from-memory baseline invented a plausible-but-wrong write_file() method, but the SKILL.md body is padded with two full raw webpage scrapes (nav chrome, 'Search...⌘K' cruft included) and the suite's README oversells it as a '自研' (self-authored) skill when the file itself admits it was scraper-generated.
- What is the Deepagents SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install Deepagents?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Deepagents with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.