yeaight7

Use when mining PR review comments and text diffs for reusable writing, documentation, tone, and editorial improvement patterns.

Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.

Use when completing a task or running out of context limit. Ensures the next session or human engineer has exactly what they need to resume work instantly.

Coordinate multi-system deployment steps as a review-first runbook with explicit approval before any external write or promotion action.

Review SQL for business logic correctness, semantic drift, aggregation risk, and silent definition changes.

Use to diagnose tests that pass and fail intermittently without code changes.

Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.

Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.

Full autonomous execution from idea to working code

Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.