# Superlazy Verify

> Evidence before any completion claim. Use immediately before saying done/fixed/passing, before any ✅, and before committing or creating a PR.

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

## Install

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

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

## About

# Superlazy Verify

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

## Iron law
No `✅` without fresh verification evidence from THIS turn. A claim without a just-run command is a lie, not a summary.

## Gate (run silently before every claim)
1. What command proves the claim? (tests / build / lint / running the code / re-testing the original bug symptom)
2. Run the FULL command, fresh.
3. Read the output: exit code, failure count, warnings.
4. Output confirms → `✅ `. Doesn't → fix, or report actual state as one-line `❌`. Never hide or soften a failure.

## Traps
- "should work", "probably", "seems to", "looks correct" → banned words; each one means RUN THE COMMAND.
- Linter clean ≠ build passes. Tests passing ≠ requirements met — recheck the request line by line.
- Previous run ≠ current state. Verify after the LAST edit.
- Subagent reported success → check `git diff`/files yourself before believing it.
- Regression test → verify red-green: it must fail with the fix reverted.
- Tired / "just this once" → no exceptions.

## 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-verify
- 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%.