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 skills add Magical-Bear/BillUserManualSkills --skill super-bill-softwaregit 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/skills/magical-bear/billusermanualskills/super-bill-software)<a href="https://agentmods.dev/skills/magical-bear/billusermanualskills/super-bill-software"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/super-bill-software/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/skills/magical-bear/billusermanualskills/super-bill-software"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/super-bill-software.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 | $0.00064 | $0.03897 |
| Opus 5.5 | $0.00026 | $0.01559 |
| Sonnet 5.5 | $0.00013 | $0.00779 |
| Haiku 4.5 | $0.00006 | $0.00390 |
Grade A, and why
super-bill-software 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 1mo 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
super-bill Software
1. 调用边界
- 本 Skill 只负责软件领域分析和实现规则,不能绕过主
super-bill。 - 正式需求先用
superpowers;架构与版本选型先用Context7;涉及 UI 必须用ui-ux-pro-max-skill。 - 没有小白可读的需求/架构文档和用户批准,禁止写生产代码。
- 开发必须在非
main分支;开发完成后交给独立测试 Agent。 - 满足主 Skill「小改动快速通道」条件时,可在当前会话直接实现并自检,不派 subagent;本 Skill 第 4 节数据库强制规则、时区语义和配置外置要求不豁免。改动涉及 schema、迁移、聚合语义或 API 破坏性变更时必须退回完整流程。
2. 能力范围
- 产品需求、业务流程、后台、管理端、数据大屏和报表。
- Python 异步服务、FastAPI、API 契约、任务调度、消息处理。
- MySQL/PostgreSQL、SQLAlchemy ORM、Redis、数据建模与迁移。
- React 19 + TypeScript、Vite/Next.js、Tailwind CSS、ECharts、bun 项目管理和前后端联调。
- FastMCP
streamable-http服务、IoT 桥梁服务和 AI 应用后端。 - 高并发、高可用、链路追踪、日志、指标、告警和工程规范。
3. 技术选择原则
优先级:
用户明确要求
> 现有项目约束
> 当前官方兼容性和安全要求
> super-bill 默认偏好
默认偏好,新项目和项目改造必须遵守:
- Web/API:FastAPI + asyncio + lifespan,并使用 Pydantic v2 做输入输出校验。
- Python:uv安装,3.11+,适用时使用
asyncio.TaskGroup和结构化并发。 - 对外 HTTP:aiohttp;现有项目已统一使用 httpx 等方案时遵循现有架构。
- 定时任务:异步 APScheduler;分布式或高可靠任务按需求评估 Taskiq/Celery/队列方案。
- Redis:redis-py 异步客户端。
- MQTT:优先
aiomqtt。 - PostgreSQL 驱动:psycopg 3 异步能力。
- MySQL 驱动:现有项目兼容时优先
asyncmy;engine、连接池和 session factory 由 lifespan 管理。 - 前端:React 19 + TypeScript
strict+ Vite 7 SPA;需要 RSC/SEO 时用 Next.js 16 App Router。现有非 React 项目遵循原架构,不强行重写。完整技术栈和代码模板见assets/react-frontend.md。 - 前端包管理与脚本:bun(
bun create vite、bun add、bun test);Monorepo 用 Turborepo + bun workspace。 - 样式与组件:Tailwind CSS v4 + shadcn/ui(Base UI/Radix);中后台高密度 Table/Form/DatePicker 用 Semi Design;禁止两套主按钮体系并存。
- 前端数据与状态:TanStack Query(服务端状态)+ Zustand v5(仅 UI 状态)+ React Hook Form + Zod;请求统一走 ky 封装,禁用裸 fetch/axios。
- 路由与图标:TanStack Router(Vite)/ App Router(Next.js);lucide-react 为唯一图标源。
- AI 流式 Markdown:只用 Vercel Streamdown,传输用原生
fetch+ReadableStream,禁止EventSource,SSE 不放进queryFn;必须配 Tailwind@source扫描 streamdown 发行文件。 - 前端测试:Vitest + Testing Library + Playwright + axe 进 CI;Storybook 8 做组件文档。
- 图表:ECharts。
选择前必须用 Context7 核对当前版本 API、生命周期、弃用项和兼容性。
4. 数据库强制规则
除非用户明确指定其他方案架构,业务数据库必须遵守:
- 使用 SQLAlchemy 2.x ORM,不能默认用裸 SQL、同步 ORM 或另一套 ORM 替代。
- 使用 async engine、
async_sessionmaker和AsyncSession。 - engine 与 session factory 必须在应用 lifespan 中创建和释放。
- Redis、aiohttp ClientSession、scheduler、MQTT client 等共享资源也应由 lifespan 统一管理。
- 具体
AsyncSession必须请求级或任务级隔离,禁止全局共享同一个 session。 - 使用异步依赖或异步上下文管理器获取 session。
- 事务必须有明确 commit/rollback 边界;异常时回滚并保留可追踪日志。
- 不把 session、连接或事务跨并发任务共享。
- 服务器现有 MySQL 且满足需求时优先复用,不擅自新建另一套数据库服务。
- 开发数据库与测试数据库必须物理或逻辑隔离,禁止自动化测试写入开发库、生产库。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 298 lines · 64 tokens per session scan A c0f9622b2409
super-bill-software is a skill published in the GitHub repository Magical-Bear/BillUserManualSkills (9 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 3,897 once invoked, about $0.0003 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 2026-09-21.
Other skills, from other repositories
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
subscriptions
Set up real-time event streams with async generator subscriptions using .subscription(async function() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client…
middlewares
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstablepipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
service-oriented-architecture
Break a tRPC backend into multiple services with custom routing links that split on the first path segment (op.path.split('.')) to route to different backend service URLs. Define a faux gateway router that merges service routers for the AppRouter type without running them in the same process. Share procedure and…