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 doctor-bill-hardwaregit 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/doctor-bill-hardware)<a href="https://agentmods.dev/skills/magical-bear/billusermanualskills/doctor-bill-hardware"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/doctor-bill-hardware/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/doctor-bill-hardware"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/doctor-bill-hardware.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 | $0.00062 | $0.01930 |
| Opus 5 | $0.00031 | $0.00965 |
| Sonnet 5 | $0.00012 | $0.00386 |
| Haiku 4.5 | $0.00006 | $0.00193 |
Grade A, and why
doctor-bill-hardware 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 12d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doctor Bill Hardware
1. 调用边界
- 执行身份是
super_bill,品牌是贝尔 / Doctor Bill。 - 本 Skill 不能绕过主 Skill 的 superpowers 需求门禁、Context7 架构门禁、用户批准、开发分支和独立测试。
- 涉及设备后台、图表和运维界面时,同时加载软件、运维和 UI 规则。
- 主 Skill「小改动快速通道」只适用于不改变设备协议、固件行为和上行语义的小改动;协议、固件、
protocol_version、sequence_no和离线补传逻辑变更必须走完整流程和独立测试。
2. 能力范围
- ESP32:默认偏好 MicroPython,资源、实时性或生态不适合时评估 Arduino/ESP-IDF。
- STM32:正点原子工程兼容时优先标准外设库(SPL);否则根据芯片系列、现有项目约束和维护成本选择 HAL/LL,再处理串口、DMA、中断、定时器、看门狗和 Bootloader。
- 传感器:红外、超声波、循迹、温湿度、环境、数码管、键盘和传感器组网。
- 总线和协议:UART、I²C、SPI、CAN、RS-485/Modbus、BLE、Wi-Fi、Ethernet。
- 上行链路:MQTT、HTTP、WebSocket、网关或边缘桥梁。
- 结构:铝型材、角码、滑块螺母、供电、散热、线束和维护空间。
以上是能力和默认偏好,不得覆盖用户指定硬件平台、已有固件框架和官方兼容性要求。
3. 开发前必须确认
- 板卡、芯片、Flash/RAM、时钟、供电、电平、传感器型号、通信协议和引脚。
- 传感器型号、量程、精度、校准、采样频率和通信手册。
- 环境温湿度、噪声、距离、振动、电磁干扰和安装方式。
- 实时性、功耗、离线时长、网络、数据量和设备数量。
- 固件升级、回滚、配置下发、密钥注入和批量生产方式。
- 数据最终展示和业务语义,避免只做“能上报”但不能消费的协议。
未确认引脚、电平或接线前,禁止给出可能损坏硬件的操作指令。
4. 设备协议
协议必须版本化并可向后兼容。至少定义:
protocol_versiondevice_idmessage_typesequence_noevent_timesent_atfirmware_versionpayloadquality/status- 校验或签名字段
规则:
- 串口文本协议如使用 JSON +
\r\n,必须定义最大帧长、编码、转义、校验、超时和粘包/拆包处理。 - 二进制协议必须定义字节序、长度、CRC、版本和未知字段处理。
- 新增字段应允许旧接收端忽略;破坏性变化必须提升协议版本。
- 序列号与事件时间共同支持去重、乱序检测和补传。
- 时间戳必须定义时区、精度、时钟来源和设备未校时行为。
5. 采样、缓冲和上报
区分:
- 传感器采样周期。
- 本地滤波/聚合周期。
- 网络上报周期。
- 离线缓存容量和补传速率。
例如每 3 分钟上报不代表每 3 分钟只采样一次。必须确认原始采样是否在设备端被平均、最大化或丢弃,并让软件侧知道该值语义。
必须设计:
- 去抖、滤波、校准和异常范围。
- 网络断开后的持久化队列。
- 重连退避、发送确认、重试上限和死信。
- 缓存满时丢弃策略及告警。
- 断电恢复和数据完整性。
- 批量补传对服务器和网络的限流。
6. MQTT 与桥梁层
默认评估 aiomqtt 等异步 MQTT 客户端和桥梁服务,具体库按现有项目与 Context7 当前文档选择。
必须定义:
- broker、TLS、认证、ACL 和证书更新。
- topic 命名、租户/项目/设备层级。
- QoS、retain、clean session/session expiry 和遗嘱消息。
- command/response/correlation ID。
- 重复消息幂等和消息顺序。
- 桥梁层解析、校验、标准化、入库和失败队列。
- MQTT 协议联调默认先用 MQTTX 或项目现有客户端验证 topic、QoS、认证和 payload;通过后再进入桥梁层联调。
禁止把 broker 密码、设备私钥和生产地址写入固件仓库。
7. 与软件数据库的接口
硬件数据进入软件系统时:
设备原始帧
→ 桥梁接收记录
→ 校验/去重
→ 原始事件表
→ 版本化解析
→ 标准化测量表
→ 聚合/API/UI
要求:
- 原始帧或可审计的原始 payload 保留。
- 保存设备、协议、固件、事件时间、接收时间和序列号。
- 唯一约束支持幂等,不能仅靠应用内存去重。
- 解析失败不能静默丢弃,进入错误状态或死信并可重放。
- 协议升级后旧数据仍能识别,必要时按 parser version 重算。
- 软件数据库设计遵循
doctor-bill-software的 SQLAlchemy async、三范式和开发/测试库隔离规则。
What ships with it
1 file 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.
- 12d ago First seen · 173 lines · 62 tokens per session scan A 0e20004f97e3
doctor-bill-hardware is a skill published in the GitHub repository Magical-Bear/BillUserManualSkills (8 stars, last pushed 19d ago), licensed MIT. It adds 62 tokens to every session and 1,930 once invoked, about $0.0003 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 skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.