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 Jinchen-Yang/diansai-skill --skill setup-envgit clone --depth 1 https://github.com/Jinchen-Yang/diansai-skillWrote 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/jinchen-yang/diansai-skill/setup-env)<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/setup-env"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/setup-env.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 | $0.00090 | $0.01006 |
| Opus 5 | $0.00045 | $0.00503 |
| Sonnet 5 | $0.00018 | $0.00201 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
setup-env 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.
What it actually says
setup-env —— 环境/工具链全包(流水线 ③)
lane: lead 产出,三 lane 消费 · needs: 无(读 solution + KB)
目标:每个 lane 拿到一份"装什么 / 哪个版本 / 哪下 / 怎么验证"的清单,3 台机器照同一份 manifest,环境可复现,避免"我这能编译你那不行"。
步骤
- 取方案:读
design/solution.md确定主控(MSPM0 / STM32)与视觉(K230 / 无)。没有 solution 就问用户:主控选哪个、用不用 K230。工具链由此驱动:- MSPM0 → CCS Theia + MSPM0 SDK + SysConfig + Arm GCC/TI clang + XDS110 驱动。
- STM32 → STM32CubeMX/CubeIDE 或 Keil + HAL/LL + ST-Link 驱动。
- K230 → CanMV IDE + K230 固件镜像 + MicroPython。
- 查 KB 环境清单(用 Read):
kb/10-典型赛题实战Playbook与Checklist.md的"赛前软件环境"小节、kb/09-开源资源与备赛经验.md、kb/07-K230视觉与主控通信.md(CanMV/镜像)。对齐已验证的工具与版本。 - 生成
env/manifest.yaml(机器可读,schema 见下),按三 lane 分组,每项锁版本 + 下载源 + 自检命令,含烧录/调试工具(XDS110/ST-Link 驱动、VOFA+ 上位机、串口助手、逻辑分析仪)。 - 生成
env/{host,control,vision}.md:每 lane 一份人类可读安装指南(安装顺序、坑、自检通过判据)。host 指向requirements.txt+tools/bootstrap.sh。 - 更新
STATUS.md:各 lane 段贴各自 env 文档链接。
env/manifest.yaml schema
version:
lanes:
host: # 跑 skill 工具的机器(lead)
- {name: , kind: runtime|pkg|tool, version: , source: , verify: , notes: }
control: # 控制 lane(固件)
- {name: CCS Theia, kind: ide, version: , source: , verify: , notes: }
- {name: MSPM0 SDK, kind: sdk, version: , source: , verify: }
- {name: SysConfig, kind: tool, ...}
- {name: XDS110 驱动, kind: tool, ...}
- {name: VOFA+, kind: tool, ...} # 调参上位机(JustFloat)
vision: # 算法 lane(K230)
- {name: CanMV IDE, kind: ide, ...}
- {name: K230 镜像, kind: firmware, version: , source: , verify: }
注意
- 锁版本:能写确切版本就写确切版本;写不准的标
version: "待核实"并放进自检步骤让用户填回——别瞎编版本号。 - 工具的官方下载源优先(TI / ST / 嘉楠官方),KB
kb/资源链接总表.md里有现成链接可引。 verify给一条能跑的自检(如arm-none-eabi-gcc --version、CanMV 串口能进 REPL),让队友确认装对了。- 本 skill 只到"清单+版本+自检+(后续 firmware-scaffold 生成对应工程)",不替用户在他本机执行安装动作。
- 生成对应工具链的工程(SysConfig/CubeMX)属
firmware-scaffold(Build Pass C),这里只出环境。
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 · 48 lines · 90 tokens per session scan A 989f8f9de692
setup-env is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (9 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,006 once invoked, about $0.0005 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
mspm0-ccs
Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib. Use when an agent needs to inspect or modify MSPM0 projects, edit .syscfg configuration, avoid generated SysConfig/build files, use DriverLib APIs, validate SysConfig output…
mspm0-skill
Tool-neutral CLI agent rules for TI MSPM0 development with SysConfig, DriverLib, CCS, Keil/uVision, CMake/GCC/OpenOCD, and supported board references. Use when an agent needs to inspect or modify MSPM0 projects, validate SysConfig output, package examples, or work on NUEDC embedded firmware.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
iot-expert
Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.
embedded-debugging
Debug embedded firmware on real hardware through the jlink-mcp server — crashes, hangs, peripheral misconfiguration, silent devices. Covers loading ELF symbols for source-level backtraces, supplying an SVD for named peripheral fields, and the halt/read/resume discipline. Use whenever debugging a microcontroller over a…
agentic-hil
Use when a request operates this project's connected target board through the configured bench (flashing, resetting, probing, debugging, UART and CAN stimulus and feedback, firmware artifacts, test reports) or configures Agentic HIL, the safe local MCP bridge that performs them. Use it instead of invoking a debugger…