Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OpenDCAI/GameFactory-3Anpx agentmods add skills/opendcai/gamefactory-3a/audioWrote 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/audio)<a href="https://agentmods.dev/skills/opendcai/gamefactory-3a/audio"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/audio/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/audio"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/audio.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 | $0.00000 | $0.02048 |
| Opus 5.5 | $0.00000 | $0.00819 |
| Sonnet 5.5 | $0.00000 | $0.00410 |
| Haiku 4.5 | $0.00000 | $0.00205 |
Grade A, and why
audio 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.
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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio generation and QA Skill
Use this Skill when a game plan requires dialogue, voice lines, sound effects, foley, ambience, or other offline WAV assets. This is asset generation, not a runtime audio-playback contract; use the selected engine context after an asset has passed review.
Scope and output
The audio chain is:
Task dict / JSONL → GenAudioOperator → selected audio model → WAV + meta.json
- Model implementations:
<REPO_PATH>/models/gen_audio/ - Task and artifact handling:
<REPO_PATH>/operators/gen_audio/ - Runner and batch execution:
<REPO_PATH>/pipeline/assets_gen/gen_audio/ - Free smoke checks:
<REPO_PATH>/test/harness/ - Generated results:
<REPO_PATH>/test_data/outputs/<game_id>/<run_id>/assets/audio/<task_id>/
Use <REPO_PATH>/pipeline/common/paths.py for output locations. Mechanics and UI belong in
that game's run directory, not in root-level <REPO_PATH>/test_data/outputs/mechanic/ or
<REPO_PATH>/test_data/outputs/ui/ directories.
Plan before generating
For every audio task, record:
- the game moment and source (player, enemy, world, UI, cinematic);
- asset type:
dialogueorsound_effect; - duration required by the game code that will play it (fire-rate interval, animation length, loop period), plus language/voice requirements, emotional delivery, distance, perspective, and any diegetic context;
- style references, loudness/mixing intent, looping need, and acceptance criteria;
- route (download vs generate), backend choice, expected cost, and licence/provenance.
Do not ask a generator to imitate a named living performer or use reference recordings without the required rights. Never commit audio API keys or private reference recordings.
Backend selection
| Need | Preferred route | Notes |
|---|---|---|
| Character dialogue / TTS | Qwen3-TTS or Seed Audio | Choose a voice that is licensed and suitable for the game; record speaker configuration. |
| Natural / mechanical one-shots (gunshots, thunder, rain, wind, footsteps, engines, impacts, doors) | Download a licence-checked recording | A real recording beats a generated one for these; see Download natural sound effects first below. |
| Sound effects / foley / ambience that cannot be sourced | Sony Woosh-DFlow or Seed Audio | Generate a focused one-shot first; layer and mix only after QA. |
| Fast cloud dialogue or SFX | Seed Audio 1.0 | One API supports both slots and outputs an offline WAV asset. |
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 · 215 lines · 0 tokens per session scan A 3dfab50c9f61
audio is a skill published in the GitHub repository OpenDCAI/GameFactory-3A (938 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,048 tokens. 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…
scenario-blender-hair
Use when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games. Also covers the Essentials hair node assets (Interpolate, Clump, Curl, Frizz, Noise, Trim), density masks, bald spots, parting lines, strand…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
scenario-godot-animation
Use when animating characters or scenes in Godot 4.7: AnimationPlayer clips and RESET, AnimationTree state machines and blend spaces built in code, Mixamo or glTF import, loop settings, BoneMap retargeting and shared animation libraries, root motion, foot sliding, foot IK with TwoBoneIK3D or custom SkeletonModifier3D…
scenario-godot-expert
Use when an agent drives Godot 4.7 on macOS or Windows for any task: headless --script jobs, --import, --check-only, command-line exports, GUT tests, windowed screenshots, the headless editor (-e) or an MCP server into a running editor; when a run hangs or fails silently, a capture is black, Godot 3 code breaks in…
scenario-roblox-tooling
Use when setting up or repairing a Roblox team project outside Studio: Rojo or Script Sync, Wally packages, Rokit pins, luau-lsp type checking, Selene, StyLua, unit tests in Lune or the engine, GitHub Actions CI on pull requests, Open Cloud place publishing, Luau Execution or API key scopes, merging builders' Team…