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 CodePhobiia/claude-roblox-game-studio --skill asset-auditgit clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studioWrote 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/codephobiia/claude-roblox-game-studio/asset-audit)<a href="https://agentmods.dev/skills/codephobiia/claude-roblox-game-studio/asset-audit"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/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/codephobiia/claude-roblox-game-studio/asset-audit"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/asset-audit.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 | $0.00030 | $0.00787 |
| Opus 5 | $0.00015 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
asset-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/asset-audit — Asset Review
Delegate to: art-director (with technical-artist for optimization review)
Steps
1. Scan Asset Directories
find assets/ -type f | sort
Categorize by type: images, audio, models, data.
2. Naming Convention Check
Standard: lowercase-kebab-case.ext
Good: wooden-crate.fbx, sword-swing-01.mp3, ui-button-bg.png
Bad: Wooden Crate.fbx, swordswing1.mp3, UI_Button_BG.png
# Find files with spaces (violation)
find assets/ -type f -name "* *"
# Find files with uppercase (violation — except extensions)
find assets/ -type f | grep -v "/[a-z0-9-]*\.[a-zA-Z0-9]*$"
3. File Size Check
Flag large files:
- Images > 1MB (warning), > 5MB (critical)
- Audio > 1MB short SFX (warning), > 10MB music (normal)
- Models > 5MB (warning), > 20MB (critical)
find assets/images -type f -size +1M
find assets/audio -type f -size +10M
find assets/models -type f -size +5M
4. Unused Asset Detection
Check which assets are referenced in code:
# For each asset, grep for its name in src/
for asset in $(find assets/ -type f -name "*.png" -o -name "*.jpg"); do
name=$(basename "$asset")
if ! grep -r "$name" src/ > /dev/null; then
echo "POTENTIALLY UNUSED: $asset"
fi
done
Note: Some assets may be referenced by ID (Roblox asset ID), not by filename. Manual verification needed.
5. Organization Check
- All images in
assets/images/ - All audio in
assets/audio/ - All models in
assets/models/ - All data (JSON) in
assets/data/ - Sub-categorized if > 20 files in a folder (e.g.,
assets/images/ui/,assets/images/icons/)
6. Roblox Limit Check
- Mesh triangles: Flag models > 10,000 tris (need DCC tool inspection)
- Texture resolution: Flag images > 1024×1024
- Audio duration: Flag audio > 60 seconds that isn't music
7. Generate Report
# Asset Audit
## Summary
- Total assets: X
- Images: X
- Audio: X
- Models: X
- Data files: X
## Violations
### Naming (must fix)
- [path] — violates kebab-case
### Oversized (should fix)
- [path] — [size] exceeds [limit]
### Potentially Unused (investigate)
- [path] — no references found in src/
### Organization (nice to have)
- [suggestion]
## Statistics
- Largest asset: [path, size]
- Most referenced: [path, count]
- Total asset size: XX MB
## Recommendations
1. [Specific cleanup action]
2. [Optimization opportunity]
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.
- 10d ago First seen · 105 lines · 30 tokens per session scan A 1f7594baef13
asset-audit is a skill published in the GitHub repository CodePhobiia/claude-roblox-game-studio (9 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 787 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.