scribe-query
by w31r4
Query and analyze AI agent behavior traces using scribe's CLI query primitives (scribe q). Use this skill whenever you need to: inspect what an AI agent (Claude Code, Codex, Cursor) sent or received in its API calls; search through system prompts, tool definitions, or conversation history; understand the parent-child hierarchy of agent and subagent requests; compare how prompts evolve across turns; or debug why an agent behaved a certain way. Trigger this skill when the user mentions scribe, trace analysis, agent behavior inspection, prompt archaeology, request trees, or wants to understand what happened in a coding agent session. Also trigger when the user says things like "what did Claude send", "show me the system prompt", "how many subagents spawned", "what tools were available", or "what changed between turns".