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.
npx skills add OpenDCAI/GameFactory-3A --skill game-cg-directorgit clone --depth 1 https://github.com/OpenDCAI/GameFactory-3AWrote 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.
[](https://agentmods.dev/skills/opendcai/gamefactory-3a/game-cg-director)<a href="https://agentmods.dev/skills/opendcai/gamefactory-3a/game-cg-director"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/game-cg-director/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.
<a href="https://agentmods.dev/skills/opendcai/gamefactory-3a/game-cg-director"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/game-cg-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.01861 |
| Opus 5 | $0.00048 | $0.00931 |
| Sonnet 5 | $0.00019 | $0.00372 |
| Haiku 4.5 | $0.00010 | $0.00186 |
Grade A, and why
game-cg-director 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 11d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game CG Director
Build one validated directing envelope per generated clip. For 3AGameFactory, write it directly as a Harness task row; for standalone use, return the envelope file. Never call a video-generation API or write generated media.
Establish caller context
Require the caller to provide:
- an approved game plan, CG requirement, or standalone CG intent;
- the clip purpose:
opening,cutscene,ultimate, orpromo; - one intended output clip per requested task, with acceptance criteria;
- optional material paths and the declared role of each material;
- the selected model (
h3orseedance), or permission to use the default; - optional duration, aspect ratio, seed, and stable
task_id.
When 3AGameFactory invokes this Skill as a child capability, also require the
selected game_id and use its standard authoring workspace:
test_data/test_samples/<game_id>/cg_video/
├── requirement.txt
├── ref_images/ # optional source material
├── ref_videos/ # optional source material
├── ref_audio/ # optional source material
└── cg_tasks.jsonl # written directly by this Skill
Do not choose the generated-artifact directory here. The parent Skill and
<REPO_PATH>/pipeline/common/paths.py own run_id and final output paths.
For a multi-clip sequence, create and validate one envelope per independently generated clip. Keep task IDs unique and preserve continuity anchors between envelopes. Do not represent several independently generated clips as one task.
Establish input evidence
- Inventory intent, settings, material paths, and each declared material role before choosing a mode. Preserve supplied paths and roles verbatim.
- Inspect accessible materials. Use only observed facts or explicit user descriptions, and keep those sources distinct in working context.
- Treat inaccessible material as opaque: preserve its path, never infer content from names or story context, and ask for one short description only when the requested motion or endpoint depends on an unknown fact.
- For T2VA or content not fixed by a reference, add only compatible concrete detail needed for scene coherence, composition, continuity, timing, or sound; never present it as a reference fact.
- Do not claim opaque media was inspected or add an evidence record to the output JSON.
What ships with it
16 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.
- common/camera.md 2.7 KB
- common/principles.md 3.0 KB
- common/sound.md 910 B
- common/style-mapping.md 2.4 KB
- models/h3.md 4.0 KB
- models/seedance.md 4.0 KB
- modes/fl2va.md 908 B
- modes/i2va.md 1.2 KB
- modes/ref2va.md 1.1 KB
- modes/t2va.md 770 B
- schemas/output.schema.json 4.6 KB
- scripts/validate_output.py 23 KB runs code
- templates/cutscene.md 945 B
- templates/opening.md 719 B
- templates/promo.md 1.4 KB
- templates/ultimate.md 1.3 KB
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.
- 11d ago First seen · 175 lines · 95 tokens per session scan A 11c1f7f84e4f
game-cg-director is a skill published in the GitHub repository OpenDCAI/GameFactory-3A (624 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,861 once invoked, about $0.0005 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.
Other skills, from other repositories
alpha-scene-gen
Generates AI 3D models through the Alpha3D MCP connector and imports them directly into the user's currently open Blender scene, scaled and placed to build out a described environment, prop set, or character roster. Use this skill whenever the user wants to populate, build, dress, furnish, or fill a Blender scene with…
meshy-3d-generation
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…
meshy-openclaw
Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture…
blender-director
Use when starting any Blender asset task, planning a production pipeline, coordinating multiple disciplines, or matching a reference photo/concept art. Invoke for game-ready assets, hard surface, environment, character, creature, export, or any multi-skill Blender workflow.
environment-artist
AAA environment art for modular kits, buildings, terrain, vegetation, architecture, and scene composition. Use for game-optimized environments, storytelling through space, and modular asset pipelines in Blender via MCP.
hard-surface
AAA hard surface modeling for sci-fi, industrial, military, vehicles, weapons, robotics, and mechanical props. Use for boolean/bevel workflows, panel lines, greebles, chamfers, and manufacturing-accurate surfaces in Blender via MCP.