What is HyperHierarchicalRAG copilot-instructions.md?

Repository instructions for HyperHierarchicalRAG, a research system connected to Zotero, a reference manager, and PubMed, a medical-literature database.

Use them to search medical literature, build queries from clinical questions, retrieve articles, check ownership, and import selected papers into Zotero.

They define the required research and import process, including checking for duplicates and choosing a Zotero collection before importing papers.

HyperHierarchicalRAG copilot-instructions.md — Instructions file for GitHub Copilot by u9401066: Repository instructions for HyperHierarchic

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 instructions/u9401066/hyperhierarchicalrag/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/u9401066/HyperHierarchicalRAG

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/u9401066/hyperhierarchicalrag/copilot-instructions.svg)](https://agentmods.dev/instructions/u9401066/hyperhierarchicalrag/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/u9401066/hyperhierarchicalrag/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/u9401066/hyperhierarchicalrag/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 848 This file is loaded in full into every session.

When invoked 848 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00848	$0.00848
Opus 5	$0.00424	$0.00424
Sonnet 5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 3d ago against content hash 12d9ca2cbfa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

HyperHierarchicalRAG copilot-instructions.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 3d 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.

.github/copilot-instructions.md · 82 lines

What it actually says

Copilot Instructions for Zotero + PubMed MCP

Auto-generated by Zotero + PubMed MCP Extension 此檔案由 Extension 自動創建，幫助 Copilot 更好地使用研究工具

可用的 MCP Servers

1. Zotero Keeper

管理 Zotero 書目庫的工具，包括：

文獻搜尋與瀏覽
PubMed 文獻匯入
Collection 管理
書庫分析

2. PubMed Search

搜尋醫學文獻的工具，包括：

文獻搜尋（支援 PICO 策略）
引用分析
全文連結取得
Session 管理

核心工作流程

🔍 搜尋新文獻

使用 parse_pico 分析研究問題
使用 generate_search_queries 產生搜尋策略
使用 search_literature 搜尋 PubMed
結果自動快取，用 get_session_pmids 取回

📥 匯入到 Zotero

重要: 匯入前必須詢問用戶要存入哪個 Collection！

使用 list_collections 取得 Collection 列表
詢問用戶選擇 Collection
使用 quick_import_pmids 或 batch_import_from_pubmed 匯入

🔄 避免重複

使用 check_articles_owned 檢查 PMID 是否已存在
使用 search_pubmed_exclude_owned 直接搜尋未擁有的文獻
使用 get_cached_article 取得快取的文章（避免重複 API 呼叫）

回應風格

使用繁體中文
清楚說明每個步驟
匯入前確認用戶意圖

VS Code Copilot Agent 指引 (整合自 AGENTS.md)

此部分為 VS Code GitHub Copilot 的 Agent Mode 提供專案上下文。

專案規則

法規遵循

你必須遵守以下法規層級：

憲法：CONSTITUTION.md - 最高原則，不可違反
子法：.github/bylaws/*.md - 細則規範
技能：.claude/skills/*/SKILL.md - 操作程序

架構與環境原則

DDD 架構：DAL 必須獨立，依賴方向：Presentation → Application → Domain ← Infrastructure。
Python (uv 優先)：優先使用 uv 管理環境，禁止全域安裝。
Memory Bank：重要操作後必須更新同步檔案（progress.md, activeContext.md 等）。
Git 工作流：提交前執行檢查清單（同步記憶、更新 README/CHANGELOG 等）。

可用 Skills (.claude/skills/)

包含 git-precommit, ddd-architect, code-refactor, memory-updater, test-generator 等 13 個自動化開發技能。

💸 Memory Checkpoint 規則

為避免 Context 遺失，於以下時機執行「checkpoint」：

對話超過 10 輪
修改超過 5 個檔案
完成重要功能
使用者暫時離開

必記：當前焦點、變更列表、待辦事項、下一步計畫。

代理回應風格

使用繁體中文，提供清晰步驟說明。
引用相關法規條文，執行操作後更新 Memory Bank。

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.

3d ago First seen · 82 lines · 848 tokens per session scan A 12d9ca2cbfa1

Subscribe to this mod's changes

HyperHierarchicalRAG copilot-instructions.md is an instructions file published in the GitHub repository u9401066/HyperHierarchicalRAG (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 848 tokens to every session, about $0.0042 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.

Data and AI LLM RAG and vectors Research ai-agent hypergraph knowledge-graph lightrag mcp

HyperHierarchicalRAG copilot-instructions.md