# 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.

- **Type:** Skill
- **Install:** `agentstack add skill-starchybomb-superlazy-superlazy-review`
- **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-review

## Install

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

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

## 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
1. Read ALL items. Any unclear → clarify ALL unclear items first in one batched question. Never implement a partial understanding.
2. 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.
3. Implement in order: blocking → simple → complex. Test each fix.
4. 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](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-review
- 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%.