Borrowing it
Nothing to install: this file belongs to u9401066/asset-aware-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.
curl -O https://raw.githubusercontent.com/u9401066/asset-aware-mcp/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/u9401066/asset-aware-mcpWrote 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/instructions/u9401066/asset-aware-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/u9401066/asset-aware-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/u9401066/asset-aware-mcp/copilot-instructions.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 5.1 | $0.04327 | $0.04327 |
| Opus 5 | $0.02164 | $0.02164 |
| Sonnet 5 | $0.00865 | $0.00865 |
| Haiku 4.5 | $0.00433 | $0.00433 |
Grade B, and why
asset-aware-mcp copilot-instructions.md scanned grade B with 1 finding 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- MCP 設定會保守 merge：Copilot `.vscode/mcp.json`、Cline `cline_mcp_settings.json`、Codex `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot 自定義指令
📌 此檔案為 VS Code GitHub Copilot Agent Mode 與 Claude Code 的統一指引。
專案概述
MCP Server — Asset-Aware MCP
| 項目 | 說明 |
|---|---|
| 語言 | Python 3.10+ |
| 框架 | 官方 MCP Python SDK 2 MCPServer、LightRAG、PyMuPDF；active optional engines 為 Docling / PyMuPDF4LLM |
| 策略 | 文件→可重用 agent assets；ETL_ENGINE active paths 為 pymupdf（快速預設）/ pymupdf4llm（版面感知）/ docling，MinerU/Marker adapter 目前 security hold |
🎯 核心目標：完整、快速地把文件轉換成「圖、文、表」等 agent 友善的資產，並保留精確來源定位（page / bbox / line span）供引用。
核心功能
- 📄 PDF ETL — 多引擎文件拆解成 agent 資產（圖片、表格、章節、公式），
ETL_ENGINE可插拔 - 🩺 PDF Preflight — 攝入前唯讀、process-isolated page classification / OCR / engine routing
- 📦 Agent Asset Export — deterministic text/table/figure + provenance bundle，可直接形成 Foam subtree
- 🧩 Segmentation Export — 統一 segmentation schema（reading order + line span）
- 📊 A2T — Anything to Table 表格建立
- 🧭 Section Navigation — 動態層級章節導航（5 Tools）
- 🔍 Knowledge Graph — 跨文獻知識圖譜（LightRAG）
- 🖼️ Vision AI — 圖片分析（base64 返回）
- 🔤 OCR Preprocessing — 掃描 PDF 按需前處理
LLM 後端
- 預設: Ollama (本地) — CPU
granite4.1:3b；GPU hintgranite4.1:8b；nomic-embed-text僅在啟用 LightRAG/KG 時需要 - 備選: OpenAI (需 API Key)
PDF → 資產引擎選擇 🚦
透過環境變數 ETL_ENGINE 選擇拆解引擎；結構化引擎懶加載，未安裝時自動降級為 PyMuPDF。
| 引擎 | 安裝 extra | 何時使用 | 授權 |
|---|---|---|---|
pymupdf（預設） |
內建 | 快速、數位 PDF、無模型 | AGPL |
pymupdf4llm |
[pdf-plus] |
低風險升級：版面感知 reading order + 表格 markdown | AGPL |
docling |
[docling] |
高精度：layout+表格+公式+圖表理解，附輕量 GraniteDocling VLM | MIT |
mineru |
security hold（extra 空） | adapter 保留；MinerU 3.4.4 pin transformers<5，而 fixes 需要 >=5.5 |
Apache-2.0 衍生 |
marker |
security hold（extra 空） | marker-pdf 1.10.2 pin Pillow<11 與安全基線衝突 | — |
- Active Docling / PyMuPDF4LLM extras 已驗證可解析
Pillow>=12.2.0；不得用 audit ignore 繞過 held backend 的不可解 graph。 - 結構化 adapters（docling/mineru/marker）實作共通
StructuredPDFExtractorProtocol，輸出MarkerParseResult，共用_ingest_single_with_marker資產管線；held backend 未安裝時降級 PyMuPDF。 - 對應 adapter：
src/infrastructure/{pymupdf4llm,docling,mineru}_adapter.py；工廠：extractor_factory.py。
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.
- 7d ago First seen · 330 lines · 4,327 tokens per session scan B 50ed20000a2b
asset-aware-mcp copilot-instructions.md is an instructions file published in the GitHub repository u9401066/asset-aware-mcp (0 stars, last pushed 20d ago), licensed Apache-2.0. It adds 4,327 tokens to every session, about $0.0216 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.