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.
npx agentmods add instructions/u9401066/nsforge-mcp/copilot-instructionsgit clone --depth 1 https://github.com/u9401066/nsforge-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/nsforge-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/u9401066/nsforge-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/u9401066/nsforge-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 | $0.03511 | $0.03511 |
| Opus 5 | $0.01755 | $0.01755 |
| Sonnet 5 | $0.00702 | $0.00702 |
| Haiku 4.5 | $0.00351 | $0.00351 |
Grade A, and why
nsforge-mcp 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 4d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot 自定義指令
此文件為 VS Code GitHub Copilot 的 Agent Mode 提供專案上下文。
開發哲學 💡
「想要寫文件的時候,就更新 Memory Bank 吧!」
「想要零散測試的時候,就寫測試檔案進 tests/ 資料夾吧!」
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
架構原則
- 採用 DDD (Domain-Driven Design)
- DAL (Data Access Layer) 必須獨立
- 依賴方向:
Presentation → Application → Domain ← Infrastructure
詳見:.github/bylaws/ddd-architecture.md
Python 環境(uv 優先)
- 優先使用 uv 管理套件和虛擬環境
- 新專案必須建立
pyproject.toml+uv.lock - 禁止全域安裝套件
# 初始化環境
uv venv
uv sync --all-extras
# 安裝依賴
uv add package-name
uv add --dev pytest ruff
詳見:.github/bylaws/python-environment.md
Memory Bank 同步
每次重要操作必須更新 Memory Bank:
| 操作 | 更新文件 |
|---|---|
| 完成任務 | progress.md (Done) |
| 開始任務 | progress.md (Doing), activeContext.md |
| 重大決策 | decisionLog.md |
| 架構變更 | architect.md |
詳見:.github/bylaws/memory-bank.md
Git 工作流
提交前必須執行檢查清單:
- ✅ Memory Bank 同步(必要)
- 📖 README 更新(如需要)
- 📋 CHANGELOG 更新(如需要)
- 🗺️ ROADMAP 標記(如需要)
- ✅
uv run python scripts/check.py(12 gates,含mcpcontract gate)
詳見:.github/bylaws/git-workflow.md
可用 Skills
位於 .claude/skills/ 目錄:
🔥 NSForge 專用 Skills(MCP 工具組合)
| Skill | 說明 | 觸發詞 |
|---|---|---|
| nsforge-derivation-workflow | 完整推導工作流 | 推導, derive, 組合公式 |
| nsforge-formula-management | 公式庫管理 | 找公式, 列出, 更新公式 |
| nsforge-formula-search | 外部公式搜尋 | Wikidata, BioModels, 物理常數, PK模型 |
| nsforge-verification-suite | 驗證工具組合 | 驗證, 維度, check |
| nsforge-code-generation | 程式碼/報告生成 | 生成程式碼, LaTeX, 報告 |
| nsforge-quick-calculate | 快速計算(無需會話) | 計算, 簡化, 求解 |
| nsforge-usolver-collab | 🆕 USolver 協作 | 優化, 最佳化, 劑量優化 |
詳細說明見
docs/nsforge-skills-guide.md
MCP 2.1 協議規則(NSForge 0.3.0)
- Runtime 使用
MCPServer、MCP Python SDK 2.1.1、protocol revision2026-07-28。 - Catalog 共 91 tools;預設 82,music 9 個需
NSFORGE_ENABLE_MUSIC=1。 - 既有工具名稱、input/output schema 與 response payload 是相容性契約;不可為了 MCP 2 metadata 改壞它們。
- 每個工具必須保有 explicit structured output、title、icon、標準 annotations 與 namespaced
org.nsforge/*_meta。application error 要保留既有 JSON body 並設 protocolisError。 - Discovery 可讀
nsforge://manifest、nsforge://health、nsforge://north-star、nsforge://derivations/{result_id},以及forge_verified_derivationprompt。 task_run/task_explore會透過 MCPContext回報開始與完成進度;不要把 progress 誤寫成 MCP Tasks extension。- stdio 為預設;Streamable HTTP 只在明確 opt-in 時啟用。非 loopback 需 allow flag 與真正的外部 authentication/TLS;allow flag 本身不是安全邊界。
- MCP 2 sync handlers 可在 worker threads 執行;session/repository 的共享可變狀態與檔案寫入必須維持 thread-safe/atomic。
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.
- 4d ago First seen · 294 lines · 3,511 tokens per session scan A 545c4d1abbd6
nsforge-mcp copilot-instructions.md is an instructions file published in the GitHub repository u9401066/nsforge-mcp (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,511 tokens to every session, about $0.0176 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.
Other instructions, from other repositories
vera CLAUDE.md
Claude Code instructions for aallan/vera, covering claude.md — project orientation for claude code, virtual environment, key commands, project layout and writing vera code.
vera AGENTS.md
AGENTS.md instructions for aallan/vera, covering agents.md — instructions for ai agents, for agents writing vera code, conformance programs as reference, workflow and commands.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.
sagemath-mcp AGENTS.md
Instructions for XBP-Europe/sagemath-mcp, covering agent playbook, environment & setup, fast commands, where code goes and testing expectations.
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.