Agent skill

Kantor Agent

by humaedihume in humaedihume/kantor-agent

Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini.

MITAuto-check passedGame Development

Install Kantor Agent

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kantor-agent .claude/skills/kantor-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .claude/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/kantor-agent .agents/skills/kantor-agent && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .agents/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/kantor-agent .cursor/skills/kantor-agent && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .cursor/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/humaedihume/kantor-agent.git --path skills/kantor-agent

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/kantor-agent .gemini/skills/kantor-agent && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .gemini/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/kantor-agent .github/skills/kantor-agent && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .github/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add humaedihume/kantor-agent --skill kantor-agent -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install humaedihume/kantor-agent kantor-agent --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/humaedihume/kantor-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/kantor-agent .opencode/skills/kantor-agent && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "kantor-agent" agent skill from https://github.com/humaedihume/kantor-agent/tree/main/skills/kantor-agent into .opencode/skills/kantor-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kantor-agent", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: kantor-agent
GitHub stars: 101
Token cost: ~1k tokens
SKILL.md length: 394 words
Files: 37
Skills in repo: 1
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini.

Works in 4 steps: Pilih perintah dari argumen (tanpa… → Skrip bersifat idempoten: bila server… → Laporkan singkat (Bahasa Indonesia): URL… → …
Tasks that involve Subagents
SKILL.md covers Langkah, Cara membaca kantornya (untuk… and Aturan
Runs JavaScript, PHP and Shell scripts from its folder; calls bash and node

What it does

Kantor Agent is an agent skill from humaedihume/kantor-agent. Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini. Ketua (sesi utama) bekerja di mejanya; 4 anggota tim (Budi, Sari, Agus, Rina) santai di lounge lalu duduk bekerja setiap kali Claude memanggil subagent (jenis apa pun); bila tim penuh, freelancer datang lewat pintu. Semua dari transkrip nyata ~/.claude/projects, read-only, tanpa menulis file ke project. Node ≥ 18 (atau PHP ≥ 8.1). Pakai saat user ingin…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 41 other files (for example `runtime/bin/kantor.sh` and `runtime/defaults.json`).

It sits in Game Development, covering Subagents, Penetration testing and 3D graphics and WebGL. It works with PHP and Three.js. The repository describes itself as: Kantor Agent: kantor 3D tanpa konfigurasi yang menampilkan Claude Code & subagent-nya bekerja (plugin Claude Code). The licence is MIT.

When your agent uses it

Tasks that involve Subagents
Tasks that involve Penetration testing
Tasks that involve 3D graphics and WebGL

Example prompts

“Kantor Agent”
“/kantor-agent”

Requirements

Node.js
A Bash shell

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Pilih perintah dari argumen (tanpa argumen = start)
Skrip bersifat idempoten: bila server sudah berjalan untuk project ini ia hanya mencetak URL; port sibuk → otomatis
Laporkan singkat (Bahasa Indonesia): URL lokal (baris URL :), runtime, cara menghentikan
Tawarkan URL publik dalam satu kalimat (jangan dijalankan tanpa persetujuan eksplisit): "Ingin dibuka dari ponsel

What it can do on your machine

Read from SKILL.md and the folder at commit ad92a7a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (JavaScript, PHP and Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- bash
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kantor Agent loads about 1k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 394 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~153
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from humaedihume/kantor-agent at commit ad92a7a, republished under its MIT licence (© humaedihume). 394 words, ~1,039 tokens.

Download SKILL.mdSave it as .claude/skills/kantor-agent/SKILL.md (or your agent's skills folder). This skill also uses 36 other files; get the full folder from GitHub.

name: kantor-agent
description: Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini. Ketua (sesi utama) bekerja di mejanya; 4 anggota tim (Budi, Sari, Agus, Rina) santai di lounge lalu duduk bekerja setiap kali Claude memanggil subagent (jenis apa pun); bila tim penuh, freelancer datang lewat pintu. Semua dari transkrip nyata ~/.claude/projects, read-only, tanpa menulis file ke project. Node ≥ 18 (atau PHP ≥ 8.1). Pakai saat user ingin melihat/menyalakan/mematikan kantor agent, dashboard subagent, atau URL publiknya.
argument-hint: [start|stop|status|publik|tutup-publik] [--node|--php] [--port N]

Runtime siap pakai ada di ${CLAUDE_SKILL_DIR}/runtime/ — tidak ada yang disalin ke project. Semua perintah memakai bash "${CLAUDE_SKILL_DIR}/runtime/bin/kantor.sh" <perintah> dan dijalankan di root project saat ini (folder tempat Claude Code dibuka), karena transkrip dicari berdasarkan path folder itu.

Argumen user: $ARGUMENTS

Langkah

Pilih perintah dari argumen (tanpa argumen = start):
- start / kosong → bash "${CLAUDE_SKILL_DIR}/runtime/bin/kantor.sh" start (teruskan --node, --php, --port N bila ada).
- stop → … kantor.sh stop · status → … kantor.sh status · restart → … kantor.sh restart.
- publik / tunnel / --publik → jalankan start dulu, lalu … kantor.sh tunnel (butuh cloudflared).
- tutup-publik / tunnel-stop → … kantor.sh tunnel-stop.
Skrip bersifat idempoten: bila server sudah berjalan untuk project ini ia hanya mencetak URL; port sibuk → otomatis pindah ke port bebas berikutnya; Node ≥ 18 dipakai bila ada, selain itu PHP ≥ 8.1. Bila keduanya tidak ada, sampaikan pesan error skrip apa adanya (cara memasang Node/PHP) lalu berhenti.
Laporkan singkat (Bahasa Indonesia): URL lokal (baris URL :), runtime, cara menghentikan (/kantor-agent stop atau perintah Hentikan yang dicetak). Bila skrip mencetak Catatan : belum ada transkrip…, jelaskan bahwa kantor terisi setelah Claude Code dipakai di folder ini (semua karakter santai sampai ada aktivitas).
Tawarkan URL publik dalam satu kalimat (jangan dijalankan tanpa persetujuan eksplisit): "Ingin dibuka dari ponsel di luar jaringan? Jalankan /kantor-agent publik." Saat user memintanya, setelah tunnel berhasil sampaikan peringatannya: siapa pun yang tahu link bisa melihat aktivitas agent (read-only, diredaksi), bagikan hanya ke orang tepercaya, dan matikan dengan /kantor-agent tutup-publik.

Show full SKILL.md (168 more words)Show less

Cara membaca kantornya (untuk menjawab pertanyaan user)

Ketua (default "Joko") = sesi utama Claude Code terbaru yang aktif; lebih dari satu sesi aktif → catatan "+N sesi lain".
Tim (Budi, Sari, Agus, Rina) = subagent. Subagent baru → anggota bebas pertama (urutan tetap) berjalan ke mejanya; selesai/dihentikan/limit → "Beres!" lalu kembali santai. Penugasan dihitung ulang dari data yang sama sehingga stabil.
Freelancer = subagent saat keempat anggota tim sibuk: masuk lewat pintu, duduk di meja cadangan (maks 4 meja, sisanya kartu "+N"), pulang lewat pintu setelah selesai.
Nama/judul/port bisa ditimpa lewat <project>/.claude/kantor-agent.json (opsional, lihat README): {"title": "…", "port": 8788, "names": {"ketua": "…", "team": ["…","…","…","…"], "freelancers": ["…"]}, "autostart": false}.

Aturan

Read-only terhadap project dan transkrip; jangan membuat atau mengubah file di project kecuali user meminta .claude/kantor-agent.json. Cache/PID/log ada di ~/.cache/kantor-agent/<slug-project>/.
Jangan pernah membuka tunnel publik tanpa persetujuan user; jangan menyalin isi transkrip ke balasan.
Autostart (hook SessionStart plugin) mati secara bawaan. Aktifkan hanya bila user meminta: "autostart": true di .claude/kantor-agent.json (atau env KANTOR_AUTOSTART=1).
Verifikasi opsional: node "${CLAUDE_SKILL_DIR}/runtime/bin/check.mjs" <url-dasar>; bila Node dan PHP ada: node "${CLAUDE_SKILL_DIR}/runtime/bin/parity.mjs" --project="$PWD" (harus "PARITY OK").

Files

SKILL.md and 36 other files in skills/kantor-agent of humaedihume/kantor-agent.

SKILL.md
runtime/bin/check.mjs
runtime/bin/kantor.sh
runtime/bin/parity.mjs
runtime/bin/serve-node.mjs
runtime/defaults.json
runtime/lib/node/config.mjs
runtime/lib/node/http.mjs
runtime/lib/node/office.mjs
runtime/lib/node/transcripts.mjs
runtime/lib/node/util.mjs
runtime/lib/php/Config.php
runtime/lib/php/Http.php
runtime/lib/php/Office.php
runtime/lib/php/Transcripts.php
runtime/lib/php/Util.php
… and 21 more

Open the folder on GitHubat commit ad92a7a

Compare with similar skills

Kantor Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kantor Agent compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Kantor Agent this skillhumaedihume/kantor-agent	101	—	~1k	Automated safety check: Pass	MIT	10 days ago
Urban Design AI Submissionopen-city-ai/haidian	417	—	~9.4k	Automated safety check: Pass	None	1 mo ago
Image to Three.js Modelimg2threejs/img2threejs	18k	1 repos	~8.2k	Automated safety check: Pass	Apache-2.0	yesterday
Web CloneJane-xiaoer/claude-skill-web-clone	1k	1 repos	~2.7k	Automated safety check: Pass	MIT	3 mo ago
Threejs Game Directormajidmanzarpour/threejs-game-skills	2.5k	—	~2.2k	Automated safety check: Pass	MIT	11 days ago
Threejs Gameplay Systemsvalkor-ai/loom	1.2k	1 repos	~1.4k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Urban Design AI Submission
open-city-ai/haidian
A skill your agent uses when an AI agent wants to participate in the Haidian Centennial Jing-Zhang AI Innovation Belt open call, follow changing materials and community discussion, generate or…
417 GitHub stars~9.4k tokensUpdated 1 mo ago
Game DevelopmentAuto-check passed
Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
18k GitHub starsUsed in 1 repo~8.2k tokens
Game DevelopmentAuto-check passed
Web Clone
Jane-xiaoer/claude-skill-web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说复刻网站、克隆网站、clone website、抄个站、仿站、照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 /…
1k GitHub starsUsed in 1 repo~2.7k tokens
Game DevelopmentAuto-check passed
Threejs Game Director
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
2.5k GitHub stars~2.2k tokensUpdated 11 days ago
Game DevelopmentAuto-check passed
Threejs Gameplay Systems
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
1.2k GitHub starsUsed in 1 repo~1.4k tokens
Game DevelopmentAuto-check passed
Threejs World Generation
calesthio/OpenMontage
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.
66k GitHub stars~2k tokensUpdated 5 days ago
Game DevelopmentAuto-check passed

Works with

Questions about Kantor Agent

What does Kantor Agent do?

Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini. Kantor Agent is an agent skill from humaedihume/kantor-agent.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini.

When should I use Kantor Agent?

Kantor Agent fits situations like: tasks that involve Subagents; tasks that involve Penetration testing; tasks that involve 3D graphics and WebGL.

How do I install Kantor Agent in Claude Code?

Run `npx skills add humaedihume/kantor-agent --skill kantor-agent -a claude-code`. Or copy the skill folder (skills/kantor-agent in humaedihume/kantor-agent) into .claude/skills/kantor-agent in your project. Claude Code loads it when a task matches its description.

How do I install Kantor Agent in Codex?

Run `npx skills add humaedihume/kantor-agent --skill kantor-agent -a codex`. Or copy the skill folder (skills/kantor-agent in humaedihume/kantor-agent) into .agents/skills/kantor-agent in your project. Codex loads it when a task matches its description.

Can I use Kantor Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add humaedihume/kantor-agent --skill kantor-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kantor-agent, .gemini/skills/kantor-agent, .github/skills/kantor-agent and .opencode/skills/kantor-agent in your project.

What does Kantor Agent need to run?

Going by SKILL.md and its folder, Kantor Agent needs JavaScript, PHP and a shell for the scripts in its folder and the command-line tools its instructions call (bash and node). Our summary lists: Node.js; A Bash shell.

Does Kantor Agent access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Kantor Agent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kantor Agent use?

Kantor Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kantor Agent use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Kantor Agent?

Skills that share tags, products or a category with Kantor Agent: Urban Design AI Submission (open-city-ai/haidian, 417 stars), Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars) and Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kantor Agent?

humaedihume (a GitHub user) maintains it in humaedihume/kantor-agent, which has 101 GitHub stars. The repository was last updated on September 29, 2026.

Source: humaedihume/kantor-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Kantor Agent

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Langkah

Cara membaca kantornya (untuk menjawab pertanyaan user)

Aturan

Files

Compare with similar skills

Similar skills

Urban Design AI Submission

Image to Three.js Model

Web Clone

Threejs Game Director

Threejs Gameplay Systems

Threejs World Generation

Related

Questions about Kantor Agent