deep-debugging

> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # Deep Debugging For bugs where `bugfix-quick` fails. Apply scientific method, not vibes. **Escalation path:** `bugfix-quick` (< 15 min, clear cause) → `deep-debugging` (scientific method) **Uses:** `tree-of-thoughts` skill for hypothesis trees, `chain-of-verification` for claim validation --- ## When to Use vs. bugfix-quick | Signal | Use | |--------|-----| | Stack trace points to clear line | bugfix-quick | | Reproduces 100% of the time | bugfix-quick | | Happens in known edge case | bugfix-quick | | Intermittent / flaky | **deep-debugging** | | Multiple plausible causes | **deep-debugging** | | "Works on my machine" class | **deep-debugging** | | Timing / race conditions | **deep-debugging** | | Production-only, can't repro locally | **deep-debugging** | --- ## The Protocol ### Step 1 — Reproduce reliably Cannot debug what you can't reproduce. Goals: - Minimum reproduction case (strip all non-essential code) - Document trigger conditions (env, timing, order of operations) - If intermittent: repeat N times, calculate failure rate **If can't reproduce: STOP.** You can't debug. Alternative: add observability (logging, metrics, traces) to production to catch the next occurrence. D...