prototype-fast

prototype-fast is a skill for Claude Code from gamedev-skills/awesome-gamedev-agent-skills. It costs 64 tokens per session (1,441 once invoked), scanned A, original, Apache-2.0.

A time-boxed method for building a rough, playable version of one game idea or mechanic. A prototype is an experiment used to answer a question, not the finished product.

In plain words
What is it for?
Use it to test a mechanic, greybox a level, build a vertical slice or minimum viable product, and decide whether to continue, change, or discard the idea.
Why use it?
It prevents spending production time on an idea before knowing whether it is enjoyable or workable. Clear keep, kill, or refactor decisions make the next step easier.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the workflows plugin — 4 skills shipped together , and of gamedev

Good fit Use it to test a mechanic, greybox a level, build a vertical slice or minimum viable product, and decide whether to continue, change, or discard the idea.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gamedev-skills/awesome-gamedev-agent-skills --skill prototype-fast
Clone the repo
git clone --depth 1 https://github.com/gamedev-skills/awesome-gamedev-agent-skills

Made for: Claude Code.

Or install workflows, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prototype-fast

README.md
[![agentmods](https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast/github.svg)](https://agentmods.dev/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast)
Your own site
<a href="https://agentmods.dev/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prototype-fast

Your own site · 80×15
<a href="https://agentmods.dev/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/prototype-fast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 8 Aug 2026
  • Snyk pass 8 Aug 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01441
Opus 5 $0.00032 $0.00720
Sonnet 5 $0.00013 $0.00288
Haiku 4.5 $0.00006 $0.00144

Measured 9d ago against content hash 02491395c621, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prototype-fast scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/workflows/prototype-fast/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prototype Fast

Get a mechanic into a player's hands fast to learn whether it's worth building. The output of a prototype is a decision (keep / kill / refactor), not a product. Optimize for learning speed, and decide up front whether the code is throwaway or load-bearing.

When to use

  • Use when validating a single mechanic or "what if", building a vertical slice / MVP, greyboxing a level or interaction, or de-risking an idea before committing real time.
  • Use when the user says "just get something playable", "is this fun?", or "rough it in".

When not to use: a timed competition with a deadline and a submission (use game-jam); shipping or updating a real release (use steam-publish / itch-publish); building the production version of a validated feature (use the engine/genre skill directly).

Core workflow

  1. Write the one question. State the single thing the prototype must answer, e.g. "Is grappling-while-falling satisfying to control?" If you have two questions, build two prototypes. A prototype that tests everything tests nothing.
  2. Decide throwaway vs keep — before you write code. Throwaway (a spike): hard-code, no architecture, delete after. Keep: still rough, but folder/names you can grow. Most prototypes should be throwaway; pretending otherwise is how prototypes rot into the shipping codebase.
  3. Set a hard timebox (30-90 min for a mechanic; one sitting for a slice) and a visible timer. The constraint is the point — it forces you to test the core idea, not the trim.
  4. Greybox everything non-essential. Primitives for art (boxes, circles, capsules), built-in fonts, one debug sound or none. Spend zero minutes on anything the question doesn't depend on.
  5. Instrument for the question. Add on-screen debug text / gizmos that show the thing you are judging (speed, distance, timing window). You're measuring, not decorating.
  6. Playtest immediately and honestly. Play it yourself, then hand it to one other person without explaining the controls. Watch where they struggle.
  7. Make the call against your kill criteria (below). Keep → schedule the real build and rewrite, don't promote the spike. Kill → log the lesson and move on. Refactor → narrow the question and spike again.

Read the full file on GitHub · 120 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 120 lines · 64 tokens per session scan A 02491395c621

Subscribe to this mod's changes

prototype-fast is a skill published in the GitHub repository gamedev-skills/awesome-gamedev-agent-skills (952 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,441 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.