researchlisted

# Research Command Read-only external knowledge gathering. Walk the 5-tier source ladder; cite every claim to a primary source; flag training-data-only assertions explicitly. Do NOT write, edit, or commit files. ## When to Apply / NOT **Apply:** - Library/framework/SDK/API docs — signatures, config options, migration - Version-specific behavior — changelogs, deprecations, breaking changes - Vendor announcements, RFCs, public web technical content - Any named library, framework, SDK, API, CLI tool, or cloud service **NOT apply:** - Questions about a local repo's code — use a codebase exploration workflow instead - Autonomous goal-directed research loops (multi-step, agent-driven) - Implementation or file editing ## Process 1. **Identify subject** — extract the library, framework, SDK, API, CLI, or topic from the user's message. Capture version if stated (e.g., `pydantic@2.7`). If version unstated, resolve latest stable at Tier 1. 2. **Resolve identifier** — look up the canonical name and version from the library's official documentation surface. If no dedicated doc tool is available, use the subject name as the search query and proceed. 3. **Walk the source ladder** — start at Tier 1; proceed to the next tier only on hard failure (source unavailable, no results, clearly non-authoritative hit). State which tier was skipped and why. 4. **Cross-reference** — every factual claim must cite at least one primary source URL. Assertions derived solely from training data must carr