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 AISEE-LAB/aisee-plugin --skill hw-architecturegit clone --depth 1 https://github.com/AISEE-LAB/aisee-pluginWrote 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/aisee-lab/aisee-plugin/hw-architecture)<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/hw-architecture"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/hw-architecture.svg" alt="Measured on agentmods" 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 | $0.00138 | $0.01940 |
| Opus 5 | $0.00069 | $0.00970 |
| Sonnet 5 | $0.00028 | $0.00388 |
| Haiku 4.5 | $0.00014 | $0.00194 |
Grade A, and why
hw:architecture 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 8d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hw:architecture
生成硬件/嵌入式项目的整体架构文档。该文档是 OpenSpec 前置输入层,用于约束后续 hw:change-plan 和每个 aisee-device-spec-driven change。
本技能合并原 hw:interfaces 与 hw:design 的主职责:接口、资源、模块、算法、运行时和全局规则必须在同一份整体架构里统一判断。
Inputs
必需:
aisee/docs/requirements/*-hw-srs.md
可选但强烈建议:
docs/project-structure.mddocs/clock-contract.mddocs/memory-device-contract.md- 原理图、PCB、器件手册、旧项目接口表、Linux dts、协议文档
- 已有工程源码、map、启动文件、linker/scatter、工程宏
可选参数:
--mode standard|deep|review,默认standard--focus interfaces|modules|algorithm|resources|all,默认all
References
需要接口和资源检查时读取:
references/architecture-checklist.md
生成文档时读取:
assets/architecture-template.md
模块数量 >=5 时读取:
assets/module-architecture-template.md
Output
保存到:
aisee/docs/architecture/<YYYY-MM-DD>-<slug>-hw-architecture.md
模块数量 >=5 时还必须生成:
docs/modules/<module-name>.md
必须包含:
- SRS 和工程事实来源
- 项目类型与运行形态
- 最终硬件/平台方向
- 全局接口与资源分配:引脚、外设、总线、地址、电源、复位、中断、DMA
- 时钟/时序策略:采样率、通信速率、控制周期、tick、延时基准
- 存储与型号策略:Flash/RAM/heap/stack/map/linker/startup/同系列换型规则
- 模拟前端、传感器、执行器、电源和机械约束
- 软件/固件模块划分
- 数据流、控制流、状态机、启动/复位/异常恢复
- 算法链路、库选择、替代方案和放弃方案
- 资源预算与依据
- 全局验证策略
- 可变更项、禁止偏离项、变更影响评估规则
- 给
initialize-hardware-projectchange 的工程骨架输入 - 给
hw:change-plan的拆分提示和 OpenSpec source-map seed 线索
Phase 0 - Read Inputs
PowerShell:
Get-Content -ErrorAction Stop aisee/docs/requirements/*-hw-srs.md
Get-Content -ErrorAction SilentlyContinue docs/project-structure.md
Get-Content -ErrorAction SilentlyContinue docs/clock-contract.md
Get-Content -ErrorAction SilentlyContinue docs/memory-device-contract.md
rg --files | rg '(\.ioc$|\.uvprojx$|\.ewp$|\.eww$|CMakeLists\.txt$|\.map$|\.sct$|\.ld$|\.icf$|startup_.*\.s$)'
POSIX shell:
cat aisee/docs/requirements/*-hw-srs.md
cat docs/project-structure.md 2>/dev/null
cat docs/clock-contract.md 2>/dev/null
cat docs/memory-device-contract.md 2>/dev/null
rg --files | rg '(\.ioc$|\.uvprojx$|\.ewp$|\.eww$|CMakeLists\.txt$|\.map$|\.sct$|\.ld$|\.icf$|startup_.*\.s$)'
What ships with it
5 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.
- 8d ago First seen · 176 lines · 138 tokens per session scan A e2a2690a640c
hw:architecture is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 1,940 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
camsnap
Capture frames or clips from RTSP/ONVIF cameras. Grabs snapshots, video clips, and motion events from IP cameras, security cameras, and video streams. Use when the user wants to take a snapshot from a camera, record a clip from an RTSP stream, monitor motion on a security camera, discover ONVIF devices on the network…
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
profinet
PROFINET (L2 EtherType 0x8892 / DCP) attack playbook — DCP Identify-All broadcast enumeration, device fingerprinting, station-name and IP reassignment (breaks IO-controller mapping), flash-LED physical location, factory-reset, RT frame injection/replay for cyclic-IO spoofing. Siemens/EU fieldbus peer of S7Comm…
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
omh-physical-device-readiness
This is a Hermes-native physical-device-readiness workflow skill.