Borrowing it
Nothing to install: this file belongs to xuzhougeng/ScientificFigureLibrary. 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/xuzhougeng/ScientificFigureLibrary/main/AGENTS.mdgit clone --depth 1 https://github.com/xuzhougeng/ScientificFigureLibraryWrote 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/xuzhougeng/scientificfigurelibrary/agents-md)<a href="https://agentmods.dev/instructions/xuzhougeng/scientificfigurelibrary/agents-md"><img src="https://agentmods.dev/badge/instructions/xuzhougeng/scientificfigurelibrary/agents-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.
<a href="https://agentmods.dev/instructions/xuzhougeng/scientificfigurelibrary/agents-md"><img src="https://agentmods.dev/badge/instructions/xuzhougeng/scientificfigurelibrary/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01271 | $0.01271 |
| Opus 5.5 | $0.00508 | $0.00508 |
| Sonnet 5.5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
ScientificFigureLibrary AGENTS.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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
适用于整个仓库。保持本文件简短，只放日常开发约束和按需阅读入口；详细设计、决策依据和任务进度放在对应文档中。
产品边界
- SFL 是本地图片—代码知识库客户端，管理可复用图片、代码及其关联，提供浏览、检索、预览、选择、导入、发布和材料化；具体研究任务的组织、执行与持续管理由宿主 Agent 负责。
- 不将跨会话绘图偏好自动应用、研究项目归档/投稿打包、论文主图/子图编排新增为 SFL 原生职责。图库自身的资产身份、版本和来源管理仍属于核心能力。
- 新需求先判断管理对象和责任归属。混合需求只在 SFL 中实现图库职责内的部分；涉及产品范围变更时参阅 产品原则，不要因功能与绘图有关就扩大职责。
- 通过 MCP 和一个核心 Skill 向外部 CLI/Desktop 提供知识库能力与候选图片列表；简化的 MCP App 仅为支持它的宿主提供可选交互。见 Agent 接入方案。
- 本地客户端采用 macOS 原生 SwiftUI、Windows / Linux 内置 Node 运行时启动本地 Web 页面；共用 TypeScript/Node 后端，另提供复用本机 Node.js 22+ 的
no-node安装包。确定方向与实现状态见 本地客户端架构。 - 本地 App 是简单的知识库应用，不内置 AI、模型调用或 Agent 任务编排；直接调用共享业务层。MCP/Skill 仅供外部工具接入，不在 App 内新增 MCP Client 或代理链路。
仓库导航
src/：图库存储、Provider 和材料化逻辑；library-service.ts管理共享业务与会话，server.ts为外部 MCP 适配，local/为本地界面连接；启动入口为src/index.ts。app/：MCP App 界面。tests/：Node 测试。scripts/：构建、目录生成、版本和打包脚本。design/brand/：图标的可编辑源文件，不随包分发。skills/：随插件分发给宿主的绘图指导。.wisp-plugin/、.codex-plugin/、.claude-plugin/、.cursor-plugin/、.pi-plugin/、.dsh-plugin/：各宿主插件配置。- 修改工具契约前阅读 PROTOCOL；修改存储、身份或 Provider 前阅读 全局图库架构。
- 安装与用户流程见 QUICKSTART 和 用户手册。历史 worktree spec 中的路径、版本和临时授权不作为当前任务的默认指令。
实现约束
- 共享后端和 Web 界面使用现有 TypeScript ESM、严格类型检查和模块划分；macOS 原生界面使用 SwiftUI。修改源文件，通过相应构建生成产物；现有
dist/由 Node/Web 构建生成。 - SFL 不执行用户绘图或下载的模板代码；执行由宿主完成，不能将材料化成功描述为绘图已验证。
- 保留用户显式选择的全局 Library、不可变 Published Release 和 Provider 限定的精确身份；不要从当前项目目录推断权威图库。
- 修改写入流程时保留既有 plan/apply、过期状态检查和重放语义；修改材料化时保留精确预览与确认契约，具体要求查阅协议。
- 测试使用隔离临时目录和配置，不读写真实用户图库或绑定状态。
- 工具契约、用户可见行为或宿主调用方式变化时，同步相关协议、手册或分发 Skill；不要把规划能力写成已实现。
常用命令与验证
使用 Node.js 22+ 和 npm；首次安装依赖运行 npm ci。命令以 package.json 为准。
| 场景 | 命令 |
|---|---|
| 定向测试 | node --test tests/<name>.test.ts |
| 完整测试（含版本同步检查） | npm test |
| 类型检查及构建 | npm run build |
| 构建及 MCP smoke | npm run test:smoke |
| 完整开发检查 | npm run check |
| Markdown 链接检查 | npm run docs:check-links -- <文件路径> |
| 发布 GitHub Release | 先 version:set 并撰写 .github/release-notes/vX.Y.Z.md，再推送 vX.Y.Z 标签；流程见 基础 CI |
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.
- yesterday Changed · +20 tokens per session 11bb5e88c546
- 1mo ago Changed · +13 tokens per session 6a391959f0b6
- 1mo ago Changed · +1 lines · +56 tokens per session 14f395b184b9
- 1mo ago Changed · +2 lines · +208 tokens per session c92169752253
- 1mo ago Changed · +1 lines · +56 tokens per session 2076f8c3e6fe
- 1mo ago First seen · 44 lines · 918 tokens per session scan A 69dbb78167bd
ScientificFigureLibrary AGENTS.md is an instructions file published in the GitHub repository xuzhougeng/ScientificFigureLibrary (135 stars, last pushed 2d ago), licensed MIT. It adds 1,271 tokens to every session, about $0.0051 per session on Opus 5.5. 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 2026-09-13.
ScientificFigureLibrary AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ScientificFigureLibrary AGENTS.mdxuzhougeng/ScientificFigureLibrary | Instructions file | 135 | 2d ago | MIT | A | 1,271 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |