# Investigate

> Alias for debug+. Invoke when encountering any bug, test failure, or unexpected behavior. Redirects to debug+ which wraps superpowers:systematic-debugging with scout agent context.

- Skill: `franklywatson/investigate` (Agent Skill)
- Install (CLI): `npx skillmds@latest add franklywatson/investigate`
- Raw SKILL.md: https://api.skillmd.com/api/skills/franklywatson/investigate/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: franklywatson (https://skillmd.com/u/franklywatson)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/franklywatson/investigate

---


<!-- rig-generated -->

# investigate — Alias for debug+

Redirects to `/debug+` which wraps `superpowers:systematic-debugging` with scout
agent context harvesting. This alias exists for backward compatibility.

## Procedure

Use `/debug+` instead. It follows the same systematic debugging process:

1. Reproduce the issue and capture output
2. Use the scout agent when code exploration is needed
3. Delegate to `superpowers:systematic-debugging`
4. Report findings with evidence

- [ ] Issue reproduced and symptom documented
- [ ] Root cause identified with evidence
- [ ] Fix applied and tests pass

## Skill Chain

Invoke `/debug+` directly for the full skill. After resolving, return to your
current phase.

## Completion

Report one of these states:

- **DONE** — Root cause identified and fix applied with passing tests.
- **DONE_WITH_CONCERNS** — Root cause identified but fix has side effects or needs review.
- **BLOCKED** — Cannot reproduce the issue or insufficient context to diagnose.
- **NEEDS_CONTEXT** — Need user input to reproduce the issue or understand expected behavior.