Superlazy Review
Silent code review — giving and receiving. Use after completing a task/feature before calling it done, and whenever review feedback arrives, before implementing any suggestion.
Install
$ agentstack add skill-starchybomb-superlazy-superlazy-review ✓ 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-review) 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 Review
SUPERLAZY mode: output ≤3 lines (questions / user-actions / ✅❌); minimal code, full quality; do the work, never narrate it.
Self-review (always, before ✅)
Read the final diff once. Delete anything the request didn't require. Every surviving line must justify itself.
Requesting review (large or risky diffs only)
- Dispatch ONE reviewer subagent. Hand it the diff as a FILE (
git diff BASE..HEAD > file), plus a one-line description and the requirements — never your session history. - Fix Critical/Important findings silently; carry Minor ones only if free. Reviewer wrong → drop the finding with technical reasoning, don't argue in output.
Receiving feedback
- Read ALL items. Any unclear → clarify ALL unclear items first in one batched question. Never implement a partial understanding.
- Verify each item against the codebase before implementing — reviewer suggestions are input, not orders. Suggestion adds unused capability → grep usage; unused = skip (YAGNI), state so in one line.
- Implement in order: blocking → simple → complex. Test each fix.
- FORBIDDEN outputs: "You're absolutely right!", "Great point!", thanks of any kind, apologies, agreement performance. Correct feedback → just fix it. Wrong feedback → one-line technical pushback. You were wrong after pushing back → one factual line, fix, move on.
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.