launch-sub-agent — Claude Code skill: what it does, how to install
Dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification.
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a claude-codeWhat launch-sub-agent does
The skill sets up an orchestrator pattern. Instead of polluting the primary conversation with deep troubleshooting steps, it delegates execution to a separate sub-agent. Each worker starts in a clean context window.
Execution runs across four phases. First, it breaks down the task using Zero-shot Chain-of-Thought reasoning to gauge complexity and output volume. It assigns Opus for complex architectural choices, Sonnet for lengthy non-complex outputs, and Haiku for fast lookups. If domain profiles exist in plugins like sdd, it injects that persona directly into the sub-agent prompt.
Every worker prompt finishes with a strict self-critique loop requiring five verification questions before finishing. If specialized role definitions are missing, the skill falls back to a general sub-agent. That gives you immediate context isolation, but specialized domain guidance depends on the plugins configured in your project.
What it helps with
- isolate task execution to prevent primary context bloat
- select Opus, Sonnet, or Haiku based on task complexity
- attach specialized agent personas to focused sub-tasks
- enforce systematic self-critique before task completion
Example prompts for the agent
- Use launch-sub-agent to design the database architecture in an isolated session
- Run launch-sub-agent to research third-party auth libraries
- Delegate unit test generation to a sub-agent using launch-sub-agent
How to install launch-sub-agent
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a claude-code2Manually: put the files in place
~/.claude/skills/launch-sub-agent/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/launch-sub-agent/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a codex2Manually: put the files in place
.agents/skills/launch-sub-agent/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a cursor2Manually: put the files in place
.cursor/skills/launch-sub-agent/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit launch-sub-agent2Manually: put the files in place
.github/skills/launch-sub-agent/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/launch-sub-agentManually: put the files in place
.devin/skills/launch-sub-agent/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about launch-sub-agent
How to install launch-sub-agent in Claude Code?
Run npx skills add NeoLabHQ/context-engineering-kit --skill launch-sub-agent -a claude-code. The file is saved to ~/.claude/skills/launch-sub-agent/SKILL.md.
What does launch-sub-agent do?
It evaluates task complexity, picks the fitting model from Haiku to Opus, and dispatches an isolated sub-agent that must complete self-critique questions before delivery.
How does specialized agent matching work?
The skill looks for configured roles like sdd:developer or sdd:software-architect. If no matching profile exists in your setup, it falls back to a general agent without specialization.
