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 striderZA/OpenCodeGameStudios --skill asset-auditgit 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/asset-audit)<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/asset-audit"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/asset-audit/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/striderza/opencodegamestudios/asset-audit"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/asset-audit.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 | $0.00038 | $0.01721 |
| Opus 5.5 | $0.00015 | $0.00688 |
| Sonnet 5.5 | $0.00008 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
asset-audit 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1: Read Standards
Read the art bible or asset standards from the relevant design docs:
design/art/art-bible.md— visual and naming standardsdesign/gdd/asset-manifest.md— expected asset list if it exists.agents/rules/data-files.md— data file standardsAGENTS.md— project naming conventions
If no art bible exists, note: "No art bible found. Auditing against general game industry conventions." and proceed.
Phase 2: Scan Asset Directories
Use Glob to index all asset files in the target scope. Scan these directories:
Glob pattern="assets/art/**/*.{png,jpg,svg,psd,tres,tscn}" (art)
Glob pattern="assets/audio/**/*.{ogg,mp3,wav,flac}" (audio)
Glob pattern="assets/vfx/**/*.{tscn,tres,gdshader}" (VFX)
Glob pattern="assets/shaders/**/*.{gdshader,tres}" (shaders)
Glob pattern="assets/data/**/*.{json,yaml,csv,tres}" (data)
If the argument specifies a category (e.g., art), limit to that directory.
For each file found, use Bash stat (or Node.js fs.statSync equivalent via Execute) to record file size.
Phase 3: Run Compliance Checks
3a: Naming Conventions
Check each file against the expected naming pattern:
- Art:
[category]_[name]_[variant]_[size].{png,jpg}(e.g.,char_player_idle_256.png) - Audio:
[category]_[context]_[name]_[variant].{ogg,mp3}(e.g.,sfx_combat_sword_hit_01.ogg) - Shaders:
[type]_[category]_[name].gdshader(e.g.,spatial_env_water.gdshader) - All files must use lowercase with underscores, no spaces
- No special characters in filenames (hyphens acceptable in specific conventions)
Flag violations with the file path and the specific rule broken.
3b: File Size Budgets
Check file sizes against budget thresholds using Bash:
Bash: find assets/art -name "*.png" -exec stat --format="%s %n" {} \;
| Category | Budget per file | Budget total |
|---|---|---|
| Textures (UI) | < 512 KB | < 5 MB |
| Textures (3D models) | < 4 MB | < 100 MB |
| Audio (SFX) | < 256 KB | < 20 MB |
| Audio (music) | < 10 MB | < 100 MB |
| Shaders | < 10 KB | < 200 KB |
| Data files | < 1 MB | < 10 MB |
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 · 185 lines · 38 tokens per session scan A 9f767aa4c0cc
asset-audit is a skill published in the GitHub repository striderZA/OpenCodeGameStudios (99 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 1,721 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
bug-report
Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.
ai-behavior-patterns
Design maintainable AI behavior structures for decision-making, navigation, combat, and systemic interaction.
godot-performance
Profile Godot runtime, scene, rendering, and resource behavior based on representative builds and content.
godot-signals-patterns
Use signals for decoupling without creating hidden event webs, ownership confusion, or lifecycle bugs.
bug-triage
Classify bugs by player impact, reproducibility, severity, and milestone risk so the team fixes the right things first.
crash-triage
Handle crashes as high-severity defects with reproducibility, symbol quality, clustering, and release impact in mind.