# debug-mode

> Evidence-driven debugging loop with mandatory instrumentation + fix approvals, run_id-tagged logs, default 3-pass verification for flaky issues, and guaranteed cleanup of debug-only instrumentation.

- Author: willyu1007
- Repository: willyu1007/Skill_Template
- Version: 20260207130336
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-07
- Source: https://github.com/willyu1007/Skill_Template
- Web: https://mule.run/skillshub/@@willyu1007/Skill_Template~debug-mode:20260207130336

---

---
name: debug-mode
description: Evidence-driven debugging loop with mandatory instrumentation + fix approvals, run_id-tagged logs, default 3-pass verification for flaky issues, and guaranteed cleanup of debug-only instrumentation.
metadata:
  short-description: Run a disciplined debug loop (hypothesize -> instrument -> reproduce -> analyze -> fix -> verify -> cleanup) with explicit user approvals.
  version: 1
category: workflows/llm
ssot_path: .ai/skills/workflows/llm/debug-mode
---

# debug-mode (entry)

Canonical source: `.ai/skills/workflows/llm/debug-mode/`

Open `.ai/skills/workflows/llm/debug-mode/SKILL.md` and any supporting files referenced there (for example `reference.md`, `examples.md`, `scripts/`, `templates/`).

> **Note**: The frontmatter above is identical to the canonical source except for `ssot_path` and `category` which are added for navigation. After opening the source file, skip re-reading the description to avoid redundant token usage.