Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. 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/med-paper-assistant/master/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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/med-paper-assistant/copilot-instructions)<a href="https://agentmods.dev/instructions/u9401066/med-paper-assistant/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/u9401066/med-paper-assistant/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 | $0.02515 | $0.02515 |
| Opus 5 | $0.01257 | $0.01257 |
| Sonnet 5 | $0.00503 | $0.00503 |
| Haiku 4.5 | $0.00251 | $0.00251 |
Grade A, and why
med-paper-assistant 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 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot 指令（Quick Reference）
完整指引：AGENTS.md。本檔每次對話都載入，務求精簡。
核心價值
逐步多輪演進：寫論文是人類多年累積、多輪訓練的結果。Agent + MCP 框架必須實現類似的螺旋式進步。三層架構：L1 Hook（即時品質）→ L2 Code（結構約束）→ L3 CI（長期演進）。每輪可審計，每輪更好。（CONSTITUTION §25-26）
雙模式心智模型
先讀 project.json.workflow_mode，再決定路徑：
library-wiki= Library Wiki Path：ingest → organize → analyze → synthesize → query。目標是維護可被 agent 管理的個人文獻庫 / wiki。這條路不強制 concept validation，也不套用 manuscript pipeline gates。manuscript= Manuscript Path：concept → draft → review → export。目標是產出投稿稿件。這條路才套用 novelty / concept validation、writing hooks、review loop、export gates。
如果用戶從 library/wiki 轉向寫稿，先把 workflow_mode 切到 manuscript，再要求 paper_type、concept.md、draft/review/export。
模式（操作前必查 .copilot-mode.json）
| 模式 | 可修改檔案 | 技能範圍 |
|---|---|---|
development |
全部 | 全部技能 + 靜態分析 |
normal |
projects/ docs/ |
僅研究技能 |
research |
projects/ docs/ |
僅研究技能 |
Normal/Research 下 .claude/ .github/ src/ tests/ integrations/ AGENTS.md CONSTITUTION.md pyproject.toml 皆唯讀。
用戶要改受保護檔案 → 提示切換開發模式。
關鍵規則
Path Selection: 先看 workflow_mode。建 library/wiki 時優先 workflow_mode="library-wiki"；要寫論文時才用 workflow_mode="manuscript"。
儲存文獻: compact surface 以 reference_action 管理查詢、讀取、格式化與 agent fallback；verified PubMed 儲存仍以直接的 save_reference_mcp(pmid) 永遠優先。reference_action(action="save_agent") 僅 API 不可用時 fallback。
草稿引用: get_available_citations() → patch_draft() → sync_references()。禁止直接 replace_string_in_file 改引用。
Novelty Check: 僅適用於 manuscript 路徑。犀利回饋 + 給選項（「直接寫？修正？用 CGU？」）。禁止討好式回饋或自動改 NOVELTY。
Workspace State: 新對話 → get_workspace_state()。重要操作 → sync_workspace_state()。
Memory Bank: 重要操作後更新 memory-bank/。對話結束前更新 projects/{slug}/.memory/。
法規層級
CONSTITUTION.md > .github/bylaws/*.md > .claude/skills/*/SKILL.md
跨 MCP 編排（詳見 auto-paper SKILL.md）
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.
- 8d ago First seen · 117 lines · 2,515 tokens per session scan A ab8f5f5aa9d7
med-paper-assistant copilot-instructions.md is an instructions file published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,515 tokens to every session, about $0.0126 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 2026-08-30.
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.