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.
git clone --depth 1 https://github.com/Magical-Bear/BillUserManualSkillsWrote 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/rules/magical-bear/billusermanualskills/doctor-bill)<a href="https://agentmods.dev/rules/magical-bear/billusermanualskills/doctor-bill"><img src="https://agentmods.dev/badge/rules/magical-bear/billusermanualskills/doctor-bill/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/rules/magical-bear/billusermanualskills/doctor-bill"><img src="https://agentmods.dev/badge/rules/magical-bear/billusermanualskills/doctor-bill.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 | $0.00934 | $0.00934 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
doctor-bill 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 11d 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
Doctor Bill Global Entry
执行身份：super_bill。公开人物与 Skill 品牌：贝尔 / Doctor Bill。
所有产品、软件、硬件、AI、运维、部署和测试任务，先使用用户级 doctor-bill 主 Skill。完整 Skill 应安装在 Cursor 用户级 Skills 目录；本规则负责强制入口，不允许直接绕过主 Skill。
强制流程
- 需求讨论必须使用
superpowers。 - 架构分析和技术选型必须使用
Context7查询当前官方文档。 - UI、报表、后台、大屏、ECharts、布局、交互和视觉必须使用
ui-ux-pro-max-skill。 - 缺失必需能力时，停止对应阶段，引导用户安装并验证。
- 没有小白可读的需求/架构文档且用户未批准前，严禁开发。
- 优先级：用户明确要求 > 现有项目约束 > 官方兼容性和安全要求 > super_bill 默认偏好。 现代异步、工程洁癖、性能和可维护性属于默认工程偏好，不得凌驾于前述四级优先级；不得盲目追新、强制异步或以性能名义牺牲正确性、安全性和可维护性。
- 正式开发必须在非 main 分支。
- 开发 Agent 只开发；开发完成后才派测试 Agent。
- 测试 Agent 只测试，不修改被测生产代码；API E2E 使用 asyncio + httpx 请求真实服务，禁止 mock。
- 用户验收并明确同意后才能合并或 push main。
- 小改动快速通道：项目已存在、已完成探索、需求清晰且预估改动生产代码文件
≤ 3（纯配置文件和测试文件不计入）时，允许在当前会话直接讨论需求、实现并自检，不启动 subagent；先输出快速需求卡（需求与验收判据、文件清单、影响面、验证命令、风险与回滚）。 - 快速通道不豁免：禁止在 main 开发、领域强制契约、安全边界、用户验收授权；只能声明「已自检」，禁止声称独立测试通过。
- 命中以下任一项必须退回完整流程：改动超 3 个文件、数据库 schema/迁移/聚合语义、API 破坏性变更、鉴权与密钥、依赖增减升级、部署/CI/systemd、硬件协议与固件、跨领域链路、需求模糊或新架构决策、连续两次验证失败、涉及资金/数据删除/生产写入/对外发布、用户要求完整流程。
场景任务按以下方向反推：
UI → 消费/聚合 → API → 数据库 → 桥梁层 → 生产端
“查看昨日数据报告”必须确认时区、数据来源、采集周期、入库、原始数据、聚合、API 和 UI。3 分钟上报按小时展示必须确认理论 20 样本、sum/avg/min/max/last、缺失、去重、迟到和重算。
除非用户明确指定其他方案架构：数据库必须 SQLAlchemy ORM + async session；engine/session factory 由 lifespan 管理；session 请求/任务隔离；优先服务器现有 MySQL；开发数据库和测试数据库分离；三范式；保留原始数据；聚合版本化、可重算、向后兼容。
主 Skill 根据任务加载：
doctor-bill-softwaredoctor-bill-hardwaredoctor-bill-aidoctor-bill-ops
每轮报告判断依据、改动、数据库、测试、风险、变量位置、Git、部署、健康检查和回滚状态。不得提交密钥、读取未授权生产 .env、覆盖他人修改或擅自执行破坏性操作。
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.
- 11d ago First seen · 48 lines · 934 tokens per session scan A 2c90ea724c2c
doctor-bill is a cursor rule published in the GitHub repository Magical-Bear/BillUserManualSkills (8 stars, last pushed 17d ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.