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 agentmods add skills/striderza/opencodegamestudios/art-generatenpx skills add striderZA/OpenCodeGameStudios --skill art-generategit clone --depth 1 https://github.com/striderZA/OpenCodeGameStudiosWrote 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/striderza/opencodegamestudios/art-generate)<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/art-generate"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/art-generate.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.02645 |
| Opus 5 | $0.00028 | $0.01323 |
| Sonnet 5 | $0.00011 | $0.00529 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
art-generate 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 yesterday.
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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If no argument is provided, read design/assets/asset-manifest.md:
- If it exists: find the first target with any asset at
Status: Neededand usequestion:- Prompt: "The next unspecced target is [target]. Generate placeholder art for it?"
- Options:
[A] Yes — generate for [target]/[B] Pick a different target/[C] Stop here
- If no manifest: fail with:
"No asset manifest found. Run
/asset-spec [target]first — I need asset specs to generate art from."
Phase 0: Parse Target
Resolve the target:
- If argument matches
system:<name>→ spec atdesign/assets/specs/[name]-assets.md - If argument matches
level:<name>→ spec atdesign/assets/specs/[name]-assets.md - If argument matches
character:<name>→ spec atdesign/assets/specs/[name]-assets.md - If argument is a path → read that file directly
- If argument is a path to a .md file → treat as spec file
Fail if the spec file does not exist:
"No asset spec found at
[path]. Run/asset-spec [target]first."
Phase 1: Gather Context
Read all source material before generating anything.
Required reads:
- Asset spec: Read the resolved spec file. Extract all
ASSET-NNNentries. For each, extract: Category, Dimensions, Format, Naming, Visual Description. - Art bible: Read
design/art/art-bible.md— fail if missing:"No art bible found. Run
/art-biblefirst — I need the palette and shape language to generate art." Extract: Color System (Section 2), Shape Language (Section 3), Asset Standards (Section 8 — dimension tiers). - Asset manifest: Read
design/assets/asset-manifest.md— note which assets already have placeholders. Filter to assets withStatus: Needed.
Present context summary:
art-generate: [Target Type] — [Target Name]
- Spec: [path] — [N] assets identified
- Art bible: found — [N] palette colors, shape language: [style]
- Assets to generate: [N] (filtered from [N] total — [N] already have placeholders)
- Output: assets/source/[target]/ and assets/sprites/[target]/
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.
- yesterday First seen · 322 lines · 57 tokens per session scan A c85faead6bc2
art-generate is a skill published in the GitHub repository striderZA/OpenCodeGameStudios (84 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 2,645 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
generated-raster-asset-pipeline
Define acceptance, validation, and runtime integration rules for raster assets generated with image models before they become real project content.
lighting-lod-pipeline
Define lighting policy, light budgets, LOD chains, and culling rules so 3D scenes look intentional and hit frame budgets.
2d-animation-pipeline
Define authoring, import, and state machine rules for frame-by-frame and skeletal 2D animations.
sprite-pipeline
Define import, slicing, atlas packing, and naming rules for 2D sprite assets.
ui-animation-pipeline
Define transition, feedback, and state-driven animation rules for UI elements.
tilemap-pipeline
Define tileset creation, auto-tile rules, collision shapes, and tilemap configuration for 2D levels.