assetcache-mcp: Instructions file for Claude Code

CLAUDE.md

assetcache-mcp CLAUDE.md is an instructions file for Claude Code from v0o0v/assetcache-mcp. It costs 2,914 tokens per session, scanned A, original, MIT.

A project guide for Claude Code, an AI coding tool, that explains how to work in a specific software repository.

In plain words
What is it for?
It helps Claude Code understand the repository, read the right design and handoff files, and follow the project's required workflow.
Why use it?
It gives the coding agent the project context, current status, and rules it must follow before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is v0o0v/assetcache-mcp's own configuration. It tells Claude Code how to work on assetcache-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything assetcache-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to v0o0v/assetcache-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/v0o0v/assetcache-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/v0o0v/assetcache-mcp

Made for: Claude Code.

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 assetcache-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/v0o0v/assetcache-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/v0o0v/assetcache-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/v0o0v/assetcache-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/v0o0v/assetcache-mcp/claude-md/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.

agentmods 80×15 button for assetcache-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/v0o0v/assetcache-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/v0o0v/assetcache-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,914 This file is loaded in full into every session.
When invoked 2,914 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02914 $0.02914
Opus 5 $0.01457 $0.01457
Sonnet 5 $0.00583 $0.00583
Haiku 4.5 $0.00291 $0.00291

Measured 8d ago against content hash 25b816bc3754, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

assetcache-mcp CLAUDE.md 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 8d 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.

CLAUDE.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

이 파일은 Claude Code(혹은 다른 Claude 도구)가 이 저장소에서 작업할 때 항상 먼저 읽어야 하는 프로젝트 가이드다. 새 세션을 시작하면 가장 먼저 이 파일을 읽고, 그 다음 DESIGN.md, HANDOFF.md, milestones/ 를 본다.

1. 프로젝트 한 줄 소개

AssetCacheMCP (assetcache-mcp) — Unity 게임 개발 중 Claude Code가 보유 에셋(2D 스프라이트, 스프라이트 시트, 사운드)을 자연어로 요청하면 가장 적합한 후보를 돌려주는 MCP 서버 + 윈도우즈 트레이 상주 앱.

핵심 아이디어

  • 사용자가 library/<pack>/... 형태로 에셋 팩을 드롭하면 자동 인덱싱.
  • Ollama로 도는 Gemma 4(gemma4:e4b)가 이미지·오디오를 직접 보고 의미 라벨을 만든다.
  • 한 프로젝트에서 한 번 채택한 팩을 이후 검색에서 우선시해 통일성을 유지.
  • Unity Asset Store 로컬 캐시(.unitypackage)도 자동 임포트.
  • PyPI 1차 배포pipx install assetcache-mcp / uv tool install assetcache-mcp (Windows + Mac + Linux 동시 지원). 단일 .exe 는 2차 옵션.

자세한 아키텍처는 DESIGN.md.

2. 진행 현황 (요약)

구간 상태 위치
M0 ~ M11.7 ✅ 완료 (모두 main 머지) 상세 PR/회귀/산출물 → milestones/HISTORY.md
현재 main M11.7 (PR #27 04c205e squash, v0.2.3~v0.2.6 publish 누적 보류) mood OPTIONAL + category 별 mood 차단 (A1 + A2). LIVE: crown mood 2→0 토큰 (A2 완벽), 시트 mood 10→5 토큰 (58% 감소). 회귀 1601 passed + 1 skipped + 63 deselected. 옵트인 6/6 PASSED. MCP 20 도구
다음 후보 M11.8 (📋 spec/plan 작성됨) mood 시드 neutral/minimalist is_enabled=0 마이그 (v0.2.7 candidate). M11.7 LIVE 의 catch-all 'neutral' 시트 4/5 잔존 해소. ⚠️ palette.neutral 은 절대 유지 (M11.6 tone group 핵심). spec: m11-8, plan: M11_8_plan.md

전체 마일스톤 정렬 + future 후보 (M12~M18) 는 milestones/ROADMAP.md.
한 줄 인계 스냅샷은 HANDOFF.md.

3. 사용자 환경

  • OS: Windows 10
  • Python: python.org 정식 Python 3.12 (C:\Users\v0o0v\AppData\Local\Programs\Python\Python312\). Microsoft Store Python 금지%APPDATA% 가상화로 경로가 불일치한다.
  • venv 위치: %USERPROFILE%\.venvs\gah\. Cowork 작업 폴더(D:\ClaudeCowork\...) 내부에 venv를 만들면 권한 충돌이 난다.
  • PowerShell: 기본 5.1 가정. PowerShell 7+은 사용자가 별도 설치한 경우만.

Read the full file on GitHub · 164 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. 8d ago First seen · 164 lines · 2,914 tokens per session scan A 25b816bc3754

Subscribe to this mod's changes

assetcache-mcp CLAUDE.md is an instructions file published in the GitHub repository v0o0v/assetcache-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,914 tokens to every session, about $0.0146 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens