Superlazy Debug
Silent root-cause debugging. Use on any bug, test failure, build failure, or unexpected behavior, BEFORE proposing or writing any fix.
Install
$ agentstack add skill-starchybomb-superlazy-superlazy-debug ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-starchybomb-superlazy-superlazy-debug) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
- Evidence first — read the FULL error/stack trace (it often contains the answer), reproduce reliably, check recent changes (
git diff, new deps, config). - 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.
- One hypothesis, one change — state it to yourself ("X causes this because Y"), make the SMALLEST change that tests it. Never stack multiple fixes.
- 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
- Source: StarchyBomb/superlazy
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.