# Superlazy Debug

> Silent root-cause debugging. Use on any bug, test failure, build failure, or unexpected behavior, BEFORE proposing or writing any fix.

- **Type:** Skill
- **Install:** `agentstack add skill-starchybomb-superlazy-superlazy-debug`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [StarchyBomb](https://agentstack.voostack.com/s/starchybomb)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** https://github.com/StarchyBomb/superlazy/tree/main/skills/superlazy-debug

## Install

```sh
agentstack add skill-starchybomb-superlazy-superlazy-debug
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Superlazy Debug

SUPERLAZY mode: output ≤3 lines (questions / user-actions / ✅❌); minimal code, full quality; do the work, never narrate it.

## Iron law
No fix without root cause. Symptom patches are failure — and cost more tokens later.

## Silent process
1. **Evidence first** — read the FULL error/stack trace (it often contains the answer), reproduce reliably, check recent changes (`git diff`, new deps, config).
2. **Trace to origin** — bad value deep in the stack? Trace backward: who produced it, who called that, until the source. Fix at the source, never where it crashed. Multi-component systems: log data at each boundary once, find the failing layer, then dig there.
3. **One hypothesis, one change** — state it to yourself ("X causes this because Y"), make the SMALLEST change that tests it. Never stack multiple fixes.
4. **Fix via test** — write a failing test reproducing the bug (superlazy-tdd), implement the single root-cause fix, verify test + suite green. No "while I'm here" extras.

## Stop conditions
- Fix didn't work → back to step 1 with the new evidence. Don't pile fix #2 on top.
- 3 failed fixes, or the fix keeps growing in unexpected places → the architecture is wrong, not the hypothesis. STOP; ask the user one batched blocking question with your architectural finding.
- Truly environmental/flaky after full investigation → add the appropriate retry/timeout/logging and note it in the ✅ line. (95% of "no root cause" is incomplete investigation — be sure.)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** [StarchyBomb/superlazy](https://github.com/StarchyBomb/superlazy)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-starchybomb-superlazy-superlazy-debug
- Seller: https://agentstack.voostack.com/s/starchybomb
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.