# Mastermind Prototype

> Build a fast, throwaway spike to learn — validate a risky assumption or an unclear approach quickly, then rebuild it properly. Use when the right design is genuinely unknown and reality will teach you faster than planning. Explicitly throwaway — the spike does not ship.

- **Type:** Skill
- **Install:** `agentstack add skill-mehrad-dm-mastermind-mastermind-prototype`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mehrad-dm](https://agentstack.voostack.com/s/mehrad-dm)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mehrad-dm](https://github.com/mehrad-dm)
- **Source:** https://github.com/mehrad-dm/mastermind/tree/master/skills/mastermind-prototype
- **Website:** https://mastermind.mehrad.me

## Install

```sh
agentstack add skill-mehrad-dm-mastermind-mastermind-prototype
```

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

## About

# MasterMind — Prototype

Tight feedback loops beat big plans when the path is unclear (`~/.mastermind/engineering/core/agent-loop.md`, `mindset.md` →
design it twice). A spike buys knowledge cheaply — as long as you don't mistake it for the product.

## Method

1. **Name the question** — the ONE risky unknown this spike will answer ("can the Worker stream a >20 MB
   file?", "does this library handle X?"). If there's no question, you don't need a prototype.
2. **Build the smallest thing that answers it** — hard-code, skip error handling, skip tests, skip
   polish. Speed over quality; it's throwaway.
3. **Extract the learning** — what did reality teach? Write down the answer and any surprises.
4. **Throw it away and rebuild to standard** — the real version gets the full loop (design, rigor,
   tests, review). **Do not ship the spike.**

## Rules
Time-box it. Keep it isolated (a scratch branch/dir) so it can't leak into production. The deliverable is
the *learning*, not the code.

## Output
The answer to the question + the surprises, and a clear "now build it properly" recommendation (or a
"don't build it — here's why").

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mehrad-dm](https://github.com/mehrad-dm)
- **Source:** [mehrad-dm/mastermind](https://github.com/mehrad-dm/mastermind)
- **License:** MIT
- **Homepage:** https://mastermind.mehrad.me

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-mehrad-dm-mastermind-mastermind-prototype
- Seller: https://agentstack.voostack.com/s/mehrad-dm
- 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%.