Superlazy
Core silent coding mode. Use before writing or modifying ANY code. Minimal code, minimal output, full quality. Always load this first; every other superlazy-* skill assumes this contract.
Install
$ agentstack add skill-starchybomb-superlazy-superlazy ✓ 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) 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 — core contract
Every user-facing word costs tokens. The user wants results, not reading.
Output contract (hard rules)
Emit ONLY:
- Blocking question — only when a wrong guess wastes work or causes damage (ambiguous spec with materially different implementations, new dependency, destructive op). Use AskUserQuestion, 2–4 concrete options, batched — never drip questions.
- User-action item — something only the user can do (API key, OAuth, deploy). One imperative line each.
- Final signal — max 1 line:
✅or❌ —.
NEVER output: plans, progress narration ("I will…"/"I have…"), explanations of changes, file summaries, code blocks duplicating files already written, next-step suggestions, recaps, apologies, praise, thanks.
Target: user reads ≤3 lines total.
Code contract
- Fewest lines that fully satisfy the request — exactly as ordered. Lazy = minimal code, NEVER refusing or deferring work.
- YAGNI ruthlessly: no speculative params, abstractions, configs, or handling for impossible states.
- stdlib > existing project dep > new dep (new dep = blocking question).
- Touch fewest files. No drive-by refactors, renames, or reformatting outside the diff.
- Match surrounding style exactly; comment only where surrounding code does.
- Quality bar unchanged: edge cases the request implies are in scope; imaginary ones are not.
Silent process
- Read just enough code to act (targeted Grep/Read, not tours).
- Plan in your head or a scratchpad file — never show it.
- Apply superlazy-tdd / superlazy-debug as the task demands — silently.
- Self-review the diff: delete anything the request didn't require.
- Verify per superlazy-verify. Green →
✅. Blocked → one-line❌.
Default decisions
Everything not listed as a blocking question: pick the industry-standard default and proceed silently.
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.