What is html-game-parallel-builder?

A workflow for building TypeScript games that run in a web browser, using separate code modules and multiple coding agents working in parallel. It also covers previewing the game locally and preparing it for GitHub Pages or a single-file export.

Use it for game features and fixes, batched testing, local web serving, single-file builds, and GitHub Pages deployment from the provided TypeScript setup.

It helps teams finish a playable game within a tight time limit while checking that separately written parts still work together. Smoke tests and type checks help catch integration problems early.

html-game-parallel-builder — Skill for Claude Code and Codex by vossla

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 vosslab/vosslab-skills --skill html-game-parallel-builder

Clone the repo

git clone --depth 1 https://github.com/vosslab/vosslab-skills

Made for: Claude Code, Codex.

Or install vosslab-skills, the plugin that ships this one along with the rest of its 42 skills, 14 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vosslab/vosslab-skills/html-game-parallel-builder.svg)](https://agentmods.dev/skills/vosslab/vosslab-skills/html-game-parallel-builder)

Your own site

<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/html-game-parallel-builder"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/html-game-parallel-builder.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,166 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.03166
Opus 5	$0.00025	$0.01583
Sonnet 5	$0.00010	$0.00633
Haiku 4.5	$0.00005	$0.00317

Measured 6d ago against content hash b6e24bd1ad6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

html-game-parallel-builder 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 6d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (templates/build_github_pages.sh, templates/check_codebase.sh, templates/devel/setup_playwright.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/management/html-game-parallel-builder/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Game Parallel Build

Overview

This skill exists to cut wall-clock time. It builds a TypeScript browser game from modular src/ files using parallel coding subagents with batched integration checkpoints, so an entire playable game (or major fix) can ship inside a live podcast, classroom demo, or livestream window. The audience watches the game come up at http://localhost:<port>/ from run_web_server.sh during the show; that local preview is the immediate live target. GitHub Pages and the optional single-file export are post-show release paths, not the artifact the audience watches you build.

Without the wall-time constraint this skill would not exist -- a serial agent with TDD produces cleaner output for the same total cost. The whole point is to hit the deadline.

The skill hits the deadline AT the quality bar, not at the cost of it. Every rule that looks like rigor (typed cross-module contracts, smoke tests between batches, exact tsc --noEmit output in subagent reports, pause-and-invoke for type design) is there because it saves time at the end: 30 seconds of contract discipline per agent prevents 30 minutes of integration debugging in a 14-module pile at the boundary. Cutting any of these rules to "save time" moves the same time into integration debt and blows the window.

Mechanism: parallel coding subagents coordinated by an orchestrator around shared contracts and batched integration checkpoints. The orchestrator does NOT write game code (except Batch 1 foundation). It gathers requirements, writes type contracts, dispatches coding agents in parallel, runs smoke tests, and fixes integration issues. Type design lives in typescript-engineer; this skill does not restate any TypeScript rules.

Required upstream skills

Invoke these; do not hand-roll their work here.

typescript-engineer (this repo) owns all type design. Route to typescript-engineer/references/game-type-patterns.md for branded ids, save-file boundary, GameEvent unions, ECS shapes, and as const satisfies config tables; typescript-engineer/references/modular-type-design.md for feature-area ownership; typescript-engineer/references/strict-mode-flags.md for strict posture.
delegate-manager-to-subagents owns manager dispatch: read-only manager review, subagent ownership boundaries, evidence-first handoff. Invoke before dispatching any coding subagent.
parallel-plan owns the up-front decision of how many lanes to split into and when one agent should hand off rather than carry everything. Invoke once before Batch 1; revisit if a batch becomes lopsided.

Read the full file on GitHub · 277 lines

Files

What ships with it

28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 277 lines · 50 tokens per session scan A b6e24bd1ad6f

Subscribe to this mod's changes

html-game-parallel-builder is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 3,166 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 2026-08-31.

Frontend Game development

worker-visualizer

A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…

nexu-io/open-design · 123 tokens

react-three-fiber

React Three Fiber 3D renderer for json-render. Use when working with @json-render/react-three-fiber, building 3D scenes from JSON specs, rendering meshes/lights/models/environments, or integrating Three.js with json-render catalogs.

vercel-labs/json-render · 54 tokens

matterjs

Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and constraints, and scroll/interaction-friendly canvas scenes.

MengTo/Skills · 39 tokens

vgpu

Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, and performance work.

vercel-labs/vgpu · 51 tokens

threejs-game-director

Entrypoint for building, upgrading, and finishing Three.js browser games. Routes work across the sibling threejs- skills for gameplay, graphics, UI, 3D/image/audio asset generation, debugging, and release. Use for build-a-game, upgrade, polish, premium, AAA, high-fidelity, showcase, from-scratch, endless runner…

majidmanzarpour/threejs-game-skills · 86 tokens

build-game-map-editor

Build, extend, or audit production-linked browser map editors for Three.js and isometric games. Use when Codex needs to create a private director view, derive a versioned editor document from authored placements, add outliner, layer, selection, drag, snap, inspector, or camera controls, expose enemy aggro, leash, or…

MengTo/Skills · 111 tokens