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 xonovex/platform --skill asset-pipeline-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/asset-pipeline-guide)<a href="https://agentmods.dev/skills/xonovex/platform/asset-pipeline-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/asset-pipeline-guide/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/xonovex/platform/asset-pipeline-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/asset-pipeline-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00143 | $0.01509 |
| Opus 5.5 | $0.00057 | $0.00604 |
| Sonnet 5.5 | $0.00029 | $0.00302 |
| Haiku 4.5 | $0.00014 | $0.00151 |
Grade A, and why
asset-pipeline-guide 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset pipeline Guidelines
An asset pipeline turns editable authored sources into runtime-ready data and keeps the two in sync as content changes. The pipeline has two halves: a stable raw/intermediate representation that stays close to the original file, and a derived runtime representation produced by deterministic compile steps whose results are cached by content hash. How assets are modeled as typed objects with stable references is owned by data-model-guide; the memory layout of the cooked output is owned by data-oriented-design-guide; the discipline of writing reloadable C is owned by c99-opinionated-guide.
Essentials
- Two representations - Keep an editable raw/intermediate form separate from the compiled runtime form; never edit the runtime form directly, see references/raw-vs-runtime-formats.md
- Importers per format, compilers per type - Source files enter through a format importer keyed by extension; each asset type owns a deterministic compiler that cooks it to runtime data, see references/import-and-compile.md
- Settings are compile inputs - Import/compile options (mip count, compression, quantization, target platform) are part of the input, not side state, see references/import-and-compile.md
- Hash inputs to a cache key - Compute a content hash over source bytes plus settings plus the input hashes of dependencies; key the cache on it, see references/content-hash-and-cache.md
- Track dependencies, reimport the closure - Record which inputs each output consumed so a source edit invalidates exactly its dependents and nothing else, see references/dependency-tracking.md
- Hot-reload by swapping live data - Watch sources, recompile only the changed closure, and swap runtime data atomically while the app keeps running, see references/hot-reloading-content.md
What ships with it
9 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.
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.
- 2mo ago First seen · 54 lines · 143 tokens per session scan A 5006c31f9e23
asset-pipeline-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 12d ago), licensed MIT. It adds 143 tokens to every session and 1,509 once invoked, about $0.0006 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 2026-08-31.
asset-pipeline-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| asset-pipeline-guidexonovex/platform | Skill | 6 | 12d ago | MIT | A | 143 | Claude Code |
| gamedev-multiplayerericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| gamedev-physicsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 102 | Claude Code, Codex |
| hz-unity-meta-movement-sdk-retargetingmeta-quest/agentic-tools | Skill | 245 | 1mo ago | Apache-2.0 | A | 186 | Claude Code |
| swallowtailregiellis/godot-mcp-go | Skill | 71 | 29d ago | MIT | A | 0 | Claude Code, Codex |
| kastell-opskastelldev/kastell | Skill | 59 | 1mo ago | Apache-2.0 | A | 53 | Claude Code |
| hz-platform-sdkmeta-quest/agentic-tools | Skill | 245 | 1mo ago | Apache-2.0 | A | 135 | Claude Code |