asset-audit

asset-audit is a skill for Claude Code, Codex from striderZA/OpenCodeGameStudios. It costs 38 tokens per session (1,721 once invoked), scanned A, original, MIT.

A game-asset checking tool that reviews files against project rules for names, formats, sizes, references, and pipeline requirements.

In plain words
What is it for?
It audits art, audio, visual effects, shaders, and data files against project documentation and naming standards.
Why use it?
It finds missing, unused, or non-compliant assets before they cause problems in the game or asset pipeline.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/striderza/opencodegamestudios/asset-audit
Any agent
npx skills add striderZA/OpenCodeGameStudios --skill asset-audit
Clone the repo
git clone --depth 1 https://github.com/striderZA/OpenCodeGameStudios

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for asset-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/striderza/opencodegamestudios/asset-audit.svg)](https://agentmods.dev/skills/striderza/opencodegamestudios/asset-audit)
Your own site
<a href="https://agentmods.dev/skills/striderza/opencodegamestudios/asset-audit"><img src="https://agentmods.dev/badge/skills/striderza/opencodegamestudios/asset-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01721
Opus 5 $0.00019 $0.00860
Sonnet 5 $0.00008 $0.00344
Haiku 4.5 $0.00004 $0.00172

Measured yesterday against content hash 9f767aa4c0cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.agents/modules/art/skills/asset-audit/SKILL.md · 185 lines

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 standards
  • design/gdd/asset-manifest.md — expected asset list if it exists
  • .agents/rules/data-files.md — data file standards
  • AGENTS.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

Read the full file on GitHub · 185 lines

Changes

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.

  1. yesterday First seen · 185 lines · 38 tokens per session scan A 9f767aa4c0cc

Subscribe to this mod's changes

asset-audit is a skill published in the GitHub repository striderZA/OpenCodeGameStudios (83 stars, last pushed 24d ago), licensed MIT. It adds 38 tokens to every session and 1,721 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 2026-09-03.