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 Meowa-AI/meowa-skills --skill game-assetsgit clone --depth 1 https://github.com/Meowa-AI/meowa-skillsWrote 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/meowa-ai/meowa-skills/game-assets)<a href="https://agentmods.dev/skills/meowa-ai/meowa-skills/game-assets"><img src="https://agentmods.dev/badge/skills/meowa-ai/meowa-skills/game-assets/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/meowa-ai/meowa-skills/game-assets"><img src="https://agentmods.dev/badge/skills/meowa-ai/meowa-skills/game-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00111 | $0.07586 |
| Opus 5.5 | $0.00044 | $0.03034 |
| Sonnet 5.5 | $0.00022 | $0.01517 |
| Haiku 4.5 | $0.00011 | $0.00759 |
Grade A, and why
game-assets 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 today.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meowa Game Assets
For playable TypeScript/Three.js games, use the developer-only beta Game development workbench. It supports a separate owned game library, idea-based creation without automatic execution, development tasks, activity replay, cancellation, private previews, owned image imports, saved source export, and explicit publishing/unpublishing when enabled. Publish only when the user requests public access.
For coordinate-based map expansion, use image-expander-run; for editable expansion prompts, use image-expander-prompt; for selected final tile exports, use image-expander-export. See maps, tiles, and textures for matching canvas parameters and neighbor coordinates.
Plan a game or create game-ready visual and audio assets. For game concepts, systems, balance, market research, or structured design documents, use the Game Designer module. For assets, establish the final asset contract first, choose the smallest suitable capability, and combine modules only when the downstream command accepts the upstream output.
Load tutorials/frame-animation/ only when the current task requires creating or processing frame animation. These tutorials are extensive; do not preload them for static character/image generation or other asset tasks. Use the relevant capability references for those tasks, and load only the tutorial sections needed for the current animation stage.
For frame-animation tasks, Character design covers design preparation for Pixel and HD; Animation production covers poses, action-specific canvases, first/last frames, generation, editing, and review. Before delivering a character's animation set, read Cross-action anchor review and alignment: review transitions, correct padding offsets with one fixed translation per clip when needed, and preserve intended motion. For Agent-driven V2 generation, follow background and high-frame-rate selection: prefer high frame rate for green-screen animation or promotional output without removal; prefer it off when removal is needed without a green screen. These recommendations do not change CLI defaults.
For the complete Pixel frame-animation workflow, read Pixel frame animation: character design → direct pixel generation or HD-to-pixel conversion → pixel review → animation production. It compares templates, custom-size generation, general generation plus pixelation, and large canvases. HD design preparation is optional; choose by style, dimensions, and actual reviewed results.
For post-processing that adapts reviewed animations to gameplay — speeding up, trimming wind-up and recovery frames, reversing clips, dropping problem frames, or preparing combo actions such as throws handed off to code projectiles and synchronized partner attacks — read Frame-animation post-processing. Load it after an animation passes review, or before generation when a throw or combo needs prepared first/last frames.
When animations go into a game or interactive demo, read Frame animation in games for metadata, anchors and root motion, state transitions, hit detection, hit feedback, effect responsibilities, multi-character sync, pixel rendering, and in-game review.
For Image2.5 free native background removal, see Transparent asset tips.
For HD frame animation V2, --auto-scale-to-input (default off, no extra credits) restores the final animation to the input dimensions with smooth scaling and retains the original animation as a second output. With background removal, only the final transparent animation is resized.
What ships with it
30 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.
- agents/openai.yaml 251 B
- assets/map-tile-layout-demo.html 66 KB
- meowart_api.md 18 KB
- meowart_api.py 507 KB runs code
- references/animation-and-video.md 27 KB
- references/audio.md 6.6 KB
- references/capability-routing.md 12 KB
- references/game-design.md 4.8 KB
- references/game-development.md 7.9 KB
- references/local-tools.md 2.9 KB
- references/maps-tiles-and-textures.md 38 KB
- references/pixel-and-hd-assets.md 23 KB
- references/running-and-outputs.md 7.5 KB
- references/ui-and-image-editing.md 27 KB
- release.json 174 B
- scripts/_png.py 6.4 KB runs code
- scripts/build-map-preview.py 4.8 KB runs code
- scripts/map-preview-server.py 24 KB runs code
- scripts/map-tile-layout.js 8.7 KB runs code
- scripts/split-components.py 11 KB runs code
- tutorials/frame-animation-postprocess/combo-assembly.md 4.1 KB
- tutorials/frame-animation-postprocess/README.md 1.5 KB
- tutorials/frame-animation-postprocess/speed-and-trim.md 2.6 KB
- tutorials/frame-animation/animation-alignment.md 6.3 KB
- tutorials/frame-animation/animation-export.md 2.9 KB
- tutorials/frame-animation/animation-production.md 29 KB
- tutorials/frame-animation/character-design.md 6.6 KB
- tutorials/frame-animation/pixel.md 13 KB
- tutorials/game-integration/frame-animation.md 7.0 KB
- web_parameter_contract.json 73 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.
- today Changed · +2 lines 1c347fa0efdf
- 3d ago Changed · +4 lines 6b58227bf653
- 5d ago Changed · +6 lines 4aa0ad18b352
- 6d ago Changed 024c792eb044
- 7d ago Changed 282bb39f963c
- 8d ago Changed · +2 lines 43afb0e3131e
- 10d ago Changed · +2 lines · +12 tokens per session 72ce644a25d7
- 13d ago Changed · +3 lines d1c1f9c9570d
- 14d ago Changed 7402804a7937
- 15d ago First seen · 230 lines · 99 tokens per session scan A 8b20606c55bc
game-assets is a skill published in the GitHub repository Meowa-AI/meowa-skills (53 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 7,586 once invoked, about $0.0004 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 2026-08-30.
game-assets compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| game-assetsMeowa-AI/meowa-skills | Skill | 53 | yesterday | MIT | A | 111 | Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |