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/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/jinchen-yang/diansai-skill/setup-env"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/setup-env.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 | $0.00090 | $0.01006 |
| Opus 5.5 | $0.00036 | $0.00402 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (12 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,006 once invoked, about $0.0004 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 2026-08-31.
setup-env compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-envJinchen-Yang/diansai-skill | Skill | 12 | 3mo ago | MIT | A | 90 | Claude Code |
| mspm0-ccsmc3545dada/mspm0-skill | Skill | 378 | 3mo ago | MIT | A | 101 | Claude Code, Codex |
| mspm0-skillIbook000/mspm0-skill | Skill | 13 | 1mo ago | MIT | A | 76 | Claude Code, Codex |
| volt-otatonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 70 | Claude Code |
| volt-firmwaretonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 76 | Claude Code |
| agentic-hilagentic-hil/agentic-hil | Skill | 24 | yesterday | Apache-2.0 | A | 104 | Claude Code |
| iot-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 59 | Claude Code |