why - Investigate the rationale behind code and design decisions
Investigates design rationale, tradeoffs, constraints, regressions, and historical context across code and available evidence sources.
Tags
Updated: 2026-10-08Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Discover available MCPs
- Anchor code history
- Query evidence categories in parallel
- Synthesize cited findings
- Calibrate confidence explicitly
- Surface contradictions and gaps
Inputs
- User question
- Target code
- Repository history
- Available MCP servers
- Cursor environment
Outputs
- Cited investigation report
- Evidence coverage map
- Confidence-calibrated findings
- Documented evidence gaps
- Reported alternative hypotheses
Requirements
- Git repository access
- gh CLI access
- Available MCP integrations
- Parallel subagent support
- Investigator model support
- Reference files