# Superlazy Tdd

> Silent test-driven development. Use when implementing any feature or bugfix in a project that has a test setup, before writing implementation code.

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

## Install

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

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

## About

# Superlazy TDD

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

## Iron law
Project has test infra → no production code without a failing test first. No test infra → run the code once to verify instead; never add a test framework uninvited.

## Silent cycle
1. **RED** — write ONE minimal test for the behavior: clear name, real code (mocks only if unavoidable), one assertion focus. Wished-for API is allowed.
2. **Verify RED** — run it. Must FAIL for the right reason (feature missing, not typo/error). Passes immediately = it tests nothing; fix the test.
3. **GREEN** — simplest code that passes. No extra features, options, or "improvements" beyond the test.
4. **Verify GREEN** — run test + suite. All pass, output clean. Test fails → fix code, not test.
5. **REFACTOR** — only if it deletes lines or duplication. Stay green.
6. Repeat per behavior. Bug fix = failing test reproducing the bug first, always.

## Cut points (lazy but honest)
- One test per behavior the request implies — not per imaginary edge case.
- Code written before its test? Delete it, restart from the test. Don't "keep as reference".
- Hard to test = design too complicated → simplify the interface, don't pile up mocks.
- Never claim tested without having run the command this session (see superlazy-verify).

## 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-tdd
- 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%.