hybrid-prototype

hybrid-prototype is a skill for Claude Code, Codex from striderZA/OpenCodeGameStudios. It costs 35 tokens per session (1,221 once invoked), scanned A, original, MIT.

A fast workflow for building a playable game prototype during the discovery phase. It focuses on one clearly stated gameplay question and uses only the minimum work needed to answer it.

In plain words
What is it for?
Use it to test focused questions about controls, combat, movement, input delay, or resource systems over a short development period.
Why use it?
It lets a team decide whether a mechanic works before spending time on formal design documents, architecture, or a larger production plan.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/striderza/opencodegamestudios/hybrid-prototype
Any agent
npx skills add striderZA/OpenCodeGameStudios --skill hybrid-prototype
Clone the repo
git clone --depth 1 https://github.com/striderZA/OpenCodeGameStudios

Made for: Claude Code, Codex.

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 hybrid-prototype

README.md
[![agentmods](https://agentmods.dev/badge/skills/striderza/opencodegamestudios/hybrid-prototype.svg)](https://agentmods.dev/skills/striderza/opencodegamestudios/hybrid-prototype)
Your own site
<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/hybrid-prototype"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/hybrid-prototype.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,221 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01221
Opus 5 $0.00017 $0.00611
Sonnet 5 $0.00007 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured yesterday against content hash 8c2345d90e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hybrid-prototype 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 yesterday.

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.

.agents/modules/prototyping/skills/hybrid-prototype/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

This skill implements the Discovery Phase fast lane as described in docs/framework/hybrid-workflow.md. It is intentionally lightweight: no formal GDD, no architecture, no epic breakdown. Just build it, play it, decide.

Time budget: 1-3 days. Agents involved: creative-director, game-designer, prototyper, godot-specialist (or engine equivalent).


Phase 1: Concept & Question (5 minutes)

Read the concept description from the argument. State the one core question this prototype must answer. If the concept is vague, ask the user to clarify before proceeding.

Examples of good questions:

  • "Does the combat feel responsive with 200ms input lag?"
  • "Is resource scarcity actually fun, or just frustrating?"
  • "Does the movement mechanic support the intended platforming challenges?"

Bad question: "Is this game fun?" (Too broad. Narrow it down.)

Ask the user: "The core question for this prototype is: [question]. Proceed?"


Phase 2: Plan (15 minutes)

Define the minimum viable prototype in 3-5 bullet points:

  • What is the absolute minimum code to answer the question?
  • What can be hardcoded / placeholder / skipped?
  • What is the success criteria? (e.g., "Player can complete 3 jumps in a row without dying")

Present the plan to the user and ask for confirmation.


Phase 3: Build (1-2 days)

Ask: "May I create the prototype directory at prototypes/[concept-name]/ and begin implementation?"

If yes, create the directory. Every file must begin with:

// PROTOTYPE - NOT FOR PRODUCTION
// Question: [Core question being tested]
// Date: [Current date]

Rules for prototype code:

  • Hardcode values freely
  • Use placeholder assets (colored squares, simple shapes)
  • Skip error handling
  • Use the simplest approach that works
  • Copy code rather than importing from production
  • NEVER import from src/ — prototypes are isolated

Run the prototype as you build. Test continuously. Fix blockers, but don't polish.

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 35 tokens per session scan A 8c2345d90e46

Subscribe to this mod's changes

hybrid-prototype is a skill published in the GitHub repository striderZA/OpenCodeGameStudios (83 stars, last pushed 24d ago), licensed MIT. It adds 35 tokens to every session and 1,221 once invoked, about $0.0002 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.