A general workflow for building and checking Three.js browser games. Three.js is a JavaScript library for displaying interactive 3D graphics in a web page, and this workflow routes tasks to more specific game skills.

Use it for Three.js or React Three Fiber games, then route gameplay, graphics, interface, asset-generation, debugging, or release-check tasks to the appropriate specialist.

It helps keep game work focused on the relevant area instead of loading every specialist for a small change. It also provides a delivery process for planning, fixing, and verifying interactive browser work.

threejs — Skill for Codex by valkor-ai/loom

About the project

Loom is a delivery harness that guides coding agents through defining, planning, implementing, checking, repairing, previewing, and handing off software changes. It is used with Claude Code, Codex, OpenCode, and other coding agents when work must be continued or inspected across sessions. The catalogue skills, hooks, commands, instructions, and plugin extend or operate this workflow.

valkor-ai/loom · 1,251 stars · on GitHub

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 valkor-ai/loom --skill threejs

Clone the repo

git clone --depth 1 https://github.com/valkor-ai/loom

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/valkor-ai/loom/threejs/github.svg)](https://agentmods.dev/skills/valkor-ai/loom/threejs)

Your own site

<a href="https://agentmods.dev/skills/valkor-ai/loom/threejs"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/valkor-ai/loom/threejs"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/threejs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 462 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	$0.00067	$0.00462
Opus 5.5	$0.00027	$0.00185
Sonnet 5.5	$0.00013	$0.00092
Haiku 4.5	$0.00007	$0.00046

Measured 1mo ago against content hash 9f44d141fc80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

threejs 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 1mo ago.

The scan reads SKILL.md. This mod also ships 25 executable files (threejs-3d-generator/scripts/threejs_3d_asset.py, threejs-audio-generator/scripts/threejs_audio_asset.py, threejs-game-director/scripts/check_evidence.py, …), 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.

plugins/shared/loom/skills/threejs/SKILL.md · 49 lines

What it actually says

Three.js Skills for Loom

Loom owns delivery state, task planning, repair, and handoff. Start non-trivial work through @loom plan; treat the specialist skills below as technical and verification guidance, not as an alternative workflow.

Choose the smallest skill

Work	Skill
Game design, core loop, input, camera, physics, or game feel	`threejs-gameplay-systems`
Models, materials, shaders, lighting, or render quality	`threejs-aaa-graphics-builder`
HUDs, menus, overlays, touch controls, or responsive game UI	`threejs-game-ui-designer`
Blank canvas, runtime errors, asset loading, input, or performance	`threejs-debug-profiler`
Playtesting, screenshots, canvas diagnostics, or release checks	`threejs-qa-release`
Explicit 3D, image, or audio asset generation	`threejs-3d-generator`, `threejs-image-generator`, or `threejs-audio-generator`

Do not load every specialist for a small fix. Browser games with visual or interactive acceptance criteria should finish with the relevant browser evidence recorded in the Loom task result.

Delivery loop

For a new game or a substantial change, begin in the project root:

@loom plan Build a Three.js game with a playable movement loop and verified browser controls
@loom continue

Run the project's build and focused behavior checks first. Use canvas inspection, screenshots, or playtests only when they are relevant to the task. When a specialist skill recommends a workflow that conflicts with a Loom MCP request, follow the MCP request.

Third-party material

The specialist skill directories were imported from an MIT-licensed upstream skill pack. Its license is retained in UPSTREAM_LICENSE.

Files

What ships with it

60 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.

1mo ago First seen · 49 lines · 67 tokens per session scan A 9f44d141fc80

Subscribe to this mod's changes

threejs is a skill published in the GitHub repository valkor-ai/loom (1,251 stars, last pushed 3d ago), licensed Apache-2.0. It adds 67 tokens to every session and 462 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-15.

Frontend Game development

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Donchitos/Claude-Code-Game-Studios · 20 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

motion

Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.

OpenDCAI/GameFactory-3A · 0 tokens

threejs