A staged workflow for rebuilding an object or character from a reference image as a procedural Three.js model, meaning a 3D model generated by code. It includes checks for the image, visual analysis, specifications, and animation readiness.

Use it for browser-based 3D props, game objects, character busts, and objects that need animation or destruction behavior.

It provides a structured way to decide whether a single image contains enough information for a useful 3D reconstruction. It also prevents missing inputs from being replaced with an unsupported generic model.

img2threejs — Skill for Claude Code and Codex by zhuanggenhua

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 zhuanggenhua/BoardGame --skill img2threejs

Clone the repo

git clone --depth 1 https://github.com/zhuanggenhua/BoardGame

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/img2threejs/github.svg)](https://agentmods.dev/skills/zhuanggenhua/boardgame/img2threejs)

Your own site

<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/img2threejs"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/img2threejs/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/zhuanggenhua/boardgame/img2threejs"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/img2threejs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,193 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

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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.02193
Opus 5	$0.00032	$0.01097
Sonnet 5	$0.00013	$0.00439
Haiku 4.5	$0.00006	$0.00219

Measured 12d ago against content hash 00b8b2bd71a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

img2threejs 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 12d ago.

The scan reads SKILL.md. This mod also ships 31 executable files (forge/_shared/artifact_cache.py, forge/_shared/color_metrics.py, forge/_shared/feature_acceptance_policy.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.

.spec/skills/img2threejs/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

img2threejs

角色

把参考图中的对象重建为 code-only procedural Three.js 模型。它不是摄影测量、mesh 抽取、素材包下载或手写近似原型。BoardGame 项目里的准入和落点先看 ../img2threejs-readiness/SKILL.md 与 ../img2threejs-reconstruction/SKILL.md；本文件只定义官方 pipeline 本体。

使用条件

适用：

用户提供对象 / 角色参考图，要求 Three.js 程序化重建。
要输出 sculpt spec、结构拆解、动画就绪模型或项目内临时原型。
要和官方 showcase 或已有 img2threejs 产物对齐。

最低输入：

可读参考图路径、截图、URL 或附件。
目标用途：浏览器实时 prop、游戏对象、角色 bust、可动画 / 可破坏对象等；未指定时默认实时浏览器 prop。
若是 CS2 路线，必须有权威分类记录或明确要求用户 / vision provider 补分类；启发式识别不能单独选择 adapter。

缺输入时停下说明缺什么，不用泛主题模型补位。

核心流程

脚本从 skill 根目录运行，Python 3.10+ stdlib 即可。脚本负责 gate 和状态，视觉判断由 agent 完成。

状态入口：先运行 python3 forge/next.py <spec>，确认当前解锁 pass、下一条命令和未满足标准。
读图与适配性：按 grimoire/intake/validation_rubric.md 判断图是否适合 3D 重建；再用 forge/stage1_intake/probe_image.py <image> 只读元数据。
图面观察：先按 grimoire/intake/image_analysis.md 做 macro -> meso -> micro 分解，列部件、材料、拓扑、身份特征和单视角缺失。
本地知识检索：需要领域 anatomy、PBR、wear、runtime 或 physics 规格时，运行 pre-spec assessment 的 local spec search；CS2 走 cs2 collection，其它对象走 core_3d。
Pre-spec assessment：forge/stage2_spec/new_pre_spec_assessment.py "Name" --image <img> --out assessment.json，写对象类别、复杂度、qualityContract、detailInventory。
Detail inventory：中等以上复杂对象必须跑 forge/stage1_intake/build_detail_inventory.py，每个细节都映射到 component localFeatures 或 material localOverrides。
Spec：forge/stage2_spec/new_sculpt_spec.py "Name" --image <img> --assessment assessment.json --out object-sculpt-spec.json，写 component hierarchy、materials、lighting、pivots、sockets、action anchors。
严格校验：forge/stage2_spec/validate_sculpt_spec.py object-sculpt-spec.json --strict-quality；浅 spec 不准 codegen。
锁 pass 构建：只改当前解锁 pass，使用 forge/stage3_build/orchestrate_passes.py 和 forge/stage3_build/generate_threejs_factory.py。
渲染截图：在浏览器 / 项目 preview 中渲染当前 pass，截当前 review viewpoint。
对比审查：forge/stage4_review/make_comparison_sheet.py 生成参考图 + render 对比图；agent 必须逐图判断。
记录结论：forge/stage4_review/append_review.py ... --action continue|refine-spec|refine-code|request-input|stop --in-place。

Read the full file on GitHub · 119 lines

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.

12d ago First seen · 119 lines · 63 tokens per session scan A 00b8b2bd71a0

Subscribe to this mod's changes

img2threejs is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,193 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 2026-08-30.

Creative and media Game development

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 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

img2threejs

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

img2threejs

角色

使用条件

核心流程

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

gameobject-component-destroy

unity-version-split

godot-signals-groups

motion

unity-addressables

threejs-exposure-color-grading