Borrowing it
Nothing to install: this file belongs to JonathanQUANLEE/JobKoi-AI. 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/JonathanQUANLEE/JobKoi-AI/main/GEMINI.mdgit clone --depth 1 https://github.com/JonathanQUANLEE/JobKoi-AIWrote 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/jonathanquanlee/jobkoi-ai/gemini-md)<a href="https://agentmods.dev/instructions/jonathanquanlee/jobkoi-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/jonathanquanlee/jobkoi-ai/gemini-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/jonathanquanlee/jobkoi-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/jonathanquanlee/jobkoi-ai/gemini-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 | $0.00854 | $0.00854 |
| Opus 5.5 | $0.00342 | $0.00342 |
| Sonnet 5.5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
JobKoi-AI GEMINI.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.
What it actually says
Bosszhipin-job-bot 架构与开发铁律 (Architectural Guidelines)
本项目前端采用 Tauri + React + TypeScript + TailwindCSS 构建。所有开发与 AI Agent 协助开发必须无条件遵循以下架构铁律:
一、主视图职责铁律(Dashboard Layout Router)
- Dashboard.tsx 仅作为布局路由外壳 (Layout Router):
- 控制代码行数在 200 行左右。
- 仅负责顶层框架组装(
Sidebar+DashboardHeader+main内容区 +SettingsDrawer/SettingsModal)以及各 Tab 面板的按需挂载。 - 严禁 在
Dashboard.tsx中编写具体的业务逻辑、复杂的表单处理、DOM 3D 物理变换或底层通信。
二、功能演化与扩展铁律(Anti-Monolith Rules)
- 新功能面板归位法则:
- 任何新增的页面级功能(如求职统计大盘、面试邀约、会话管理等),必须在
src/views/或src/components/建立独立的组件文件(如XxxPanel.tsx或XxxView.tsx)。 - 在
Dashboard.tsx中仅允许通过单行条件渲染挂载(如{activeNav === "xxx" && <XxxView {...props} />})。
- 任何新增的页面级功能(如求职统计大盘、面试邀约、会话管理等),必须在
- 状态与网络通信 Hook 归位法则:
- 任何复杂的前端状态聚合、后端 IPC 接口调用或轮询逻辑,必须封装至独立的 Custom Hook(如
src/hooks/useXxx.ts)。 - 严禁在页面外壳中直接堆砌无序的
useState与useEffect。
- 任何复杂的前端状态聚合、后端 IPC 接口调用或轮询逻辑,必须封装至独立的 Custom Hook(如
- 视图小部件下沉法则:
- 纯展示型卡片、状态指示器、按钮组,必须拆分为独立的小组件(如
ReviewCard.tsx、DashboardHeader.tsx)。
- 纯展示型卡片、状态指示器、按钮组,必须拆分为独立的小组件(如
三、用户体验与视觉完整性铁律
- 3D 万花筒滚轮动力学完整性:
- 工作台必须保持 OptionWheel 物理动力学(Cylindrical 3D Wheel Physics),通过
stepY = Math.max(600, vh * 0.8)与pastProg >= 0.8严格防止卡片透视重叠与鬼影。
- 工作台必须保持 OptionWheel 物理动力学(Cylindrical 3D Wheel Physics),通过
- 多语言与普通用户文案视角:
- 避免直接暴露过度技术化的内部风控词汇,以普通求职者友好的方式呈现。
- 界面中英文切换必须保持 100% 彻底。
四、代码提交与验证铁律
- 每次模块拆分或功能迭代后,必须依次执行:
npx tsc --noEmit(TypeScript 类型检查通过,零报错)npm run test -- --run(单元测试与回归测试全部通过)npm run build(生产构建成功)
- Git 提交信息遵循 Conventional Commits 规范,严禁包含任何
Co-authored-by尾注。
五、发版铁律
- 任何涉及「打安装包 / 发版本 / 自动更新」的任务,**先通读根目录 《发布与自动更新SOP.md》**再动手:版本号 7 处同步、双通道发布流程、 latest.json 生成、发布后验证清单、数据安全红线(私钥管理、卸载钩子、 sanitize 边界)全在里面,照做即可,不要即兴发挥。
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 · 40 lines · 854 tokens per session scan A 68682b550110
JobKoi-AI GEMINI.md is an instructions file published in the GitHub repository JonathanQUANLEE/JobKoi-AI (29 stars, last pushed 21d ago), licensed MIT. It adds 854 tokens to every session, about $0.0034 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 2026-11-07.
JobKoi-AI GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| JobKoi-AI GEMINI.mdJonathanQUANLEE/JobKoi-AI | Instructions file | 29 | 21d ago | MIT | A | 854 | Gemini CLI |
| 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 | 5,649 | 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 |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |