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 metaspartan/cybara --skill game-asset-pipelinegit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/game-asset-pipeline)<a href="https://agentmods.dev/skills/metaspartan/cybara/game-asset-pipeline"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/game-asset-pipeline/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/metaspartan/cybara/game-asset-pipeline"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/game-asset-pipeline.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 | $0.00051 | $0.00379 |
| Opus 5 | $0.00026 | $0.00189 |
| Sonnet 5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
game-asset-pipeline 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 9d 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.
What it actually says
Game asset pipeline
Inspect the contract
Identify the source format, source-control policy, engine import settings, runtime format, units, axes, pivots, naming, material model, texture budgets, animation conventions, collision strategy, and target platforms.
Use the separate blender-mcp skill when Blender is connected and source scene edits are required.
Pipeline rules
- Preserve editable source assets separately from optimized runtime output.
- Keep units, orientation, pivots, skeleton naming, and animation root motion consistent.
- Reuse materials and texture sets where practical.
- Choose texture compression and resolution for the target platform and visible screen size.
- Define collision proxies and levels of detail intentionally.
- Keep importer settings reproducible and committed when the engine supports that.
- Avoid lossy conversion chains and repeated re-encoding.
- Do not text-edit binary asset files.
Verification
- Validate the source asset and export logs.
- Reimport through the engine's normal path from a clean state.
- Check missing references, scale, pivot, normals, tangents, UVs, materials, rig, animation, collision, and bounds.
- Inspect the asset in representative lighting and gameplay distance.
- Measure runtime memory, load time, draw calls, geometry, texture residency, and build-size impact.
- Exercise a packaged or exported build because editor previews can hide runtime import differences.
Completion criteria
Report source and runtime formats, importer changes, validation scene, target platform, visual evidence, before and after size or memory, and any destructive source conversion that was intentionally avoided.
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.
- 9d ago First seen · 37 lines · 51 tokens per session scan A 8ed88ea7b9b1
game-asset-pipeline is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 379 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 2026-09-03.
Other skills, from other repositories
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.
threejs-animation
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.