spawn-investigator
Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.
Profile →npx skills add majiayu000/claude-skill-registry --skill spawn-investigator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Spawn Investigator Launch an isolated investigation subagent to answer a codebase question without polluting the main conversation context. ## Why This Exists Reading many files to answer a question fills up the main context window. By spawning an Explore-type subagent, the investigation happens in a separate context. Only the concise answer comes back, keeping the main context clean for actual work. ## Usage - `/spawn-investigator <question>` — User-invoked investigation - Claude can also auto-invoke this when it recognizes a question requiring broad codebase exploration ## Procedure ### Step 1: Formulate the Question Parse `$ARGUMENTS` into a clear, specific investigation question. If the question is vague, refine it: - BAD: "How does auth work?" - GOOD: "What authentication middleware is used, where is it configured, and what are the auth routes?" ### Step 2: Spawn the Subagent Use the Task tool with these parameters: ``` subagent_type: Explore description: "Investigate: [short summary]" prompt: | Investigate this question about the codebase: **Question:** [the question] Instructions: - Search broadly first (Glob for file patterns, Grep for keywords) - Read the most relevant f
- Why This Exists
- Usage
- Procedure
- Step 1: Formulate the Question
- Step 2: Spawn the Subagent
- Step 3: Report Back
- When to Auto-Invoke
What does the spawn-investigator skill do?
Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill spawn-investigator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.