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 HorizonRobotics/OE-Skills --skill board-detectiongit clone --depth 1 https://github.com/HorizonRobotics/OE-SkillsWrote 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/horizonrobotics/oe-skills/board-detection)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/board-detection"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/board-detection/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/horizonrobotics/oe-skills/board-detection"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/board-detection.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 | $0.00072 | $0.02166 |
| Opus 5.5 | $0.00029 | $0.00866 |
| Sonnet 5.5 | $0.00014 | $0.00433 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
board-detection 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
板卡硬件平台检测
执行方式
本 Skill 应通过 subagent 执行。 主 agent 在前置检查中发现
.env.board缺失或不完整时,应将本文件的完整内容作为 subagent prompt 派发执行。subagent 完成后汇报写入结果和需要用户确认的事项(如有),主 agent 读取.env.board继续后续流程。
目标
检测用户的板卡硬件平台信息,写入 .horizon/.env.board,供后续所有板端任务直接使用。
板卡检查规则
- 板卡类型按三类处理:
nash-e/m(Linux)、nash-p(Linux)与nash-b(QNX) - 优先从环境变量中查找板卡信息,例如
HORIZON_BOARD_TYPE、OE_BOARD_TYPE、BOARD_TYPE、BOARD、NASH_BOARD - 如果环境变量没有提供,再检查项目内相关配置文件,例如
.env、.env.local、.horizon/board.env、.horizon/board.json、AGENTS.md、CLAUDE.md - 如果任务涉及板端运行、板端推理、远端 HBM、性能压测或 BPU 实测,但没有找到板卡信息,必须先向用户确认是否有可用板卡
- 如果用户明确没有可用板卡,涉及板端的任务应回退到 X86 评测、仿真、静态检查或可离线执行的分析工具,并说明该结果不能替代真实板端验证
- nash-b 板卡为可选项:用户可以跳过 nash-b 配置,但系统必须给出明确提示:"已跳过 nash-b 板卡配置。后续涉及 nash-b 板端的任务将不可用,仅可在 X86 环境进行编译和离线分析。如需启用,请删除
.horizon/.env.board重新执行板卡检测。" - 板卡工作目录(
BOARD_WORKDIR)也是.env.board完整性的必要字段。如果文件中缺少该字段,需要重新执行工作目录检测(步骤 3.5)
检测流程
-
检查
.horizon/.env.board是否存在- 文件存在且内容完整(包含
BOARD_TYPE、BOARD_IP、BPU_ARCH、BOARD_WORKDIR等字段)→ 直接读取,跳过后续步骤 - 文件不存在或不完整(含缺少
BOARD_WORKDIR)→ 进入步骤 2
- 文件存在且内容完整(包含
-
获取板卡 IP
- 先读取项目根目录
.env文件,查找BOARD_IP、BOARD_IP_NASH_P、BOARD_IP_NASH_B等字段 - 如果
.env中有板卡 IP → 进入步骤 3 - 如果
.env中没有 → 询问用户是否有可用板卡 IP- 用户提供了 IP → 进入步骤 3
- 用户明确表示没有可用板卡 → 跳过本阶段,说明"当前任务将回退到 X86 评测或仿真模式,结果不能替代真实板端验证"
- 先读取项目根目录
-
自动检测板卡架构
- 使用 SSH 连接板卡(默认用户名
root),执行:uname -a hrut_somstatus - 从输出中自动解析架构、内核版本、镜像日期、BPU 状态等信息
- 根据
.env中 IP 与变量的对应关系自动判断板卡类型:BOARD_IP/ 无后缀 →nash-e/m(Linux 平台)BOARD_IP_NASH_P/_NASH_P后缀 →nash-p(Linux 平台)BOARD_IP_NASH_B/_NASH_B后缀 →nash-b(QNX 平台,uname -a输出含QNX)
- nash-b (QNX) 特殊说明:nash-b 运行 QNX 实时操作系统,SSH 连接后
uname -a的输出格式与 Linux 不同(系统名为QNX,无发行版信息)。hrut_somstatus命令仍可用。如果 SSH 连接或命令执行失败,可能是 QNX 板卡的 SSH 服务配置不同,需要向用户确认 - 全程不需要用户手动确认架构信息,全部自动推断
- 跳过选项:对于每种板卡类型,用户都可以选择跳过。跳过时给出明确提示:
⚠️ 已跳过 [板卡类型] 的配置。后续涉及该板卡的板端任务将不可用。如需启用,请删除
.horizon/.env.board重新执行板卡检测。
- 使用 SSH 连接板卡(默认用户名
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 · 117 lines · 72 tokens per session scan A 85336343ae65
board-detection is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,166 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 2026-08-30.
board-detection compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| board-detectionHorizonRobotics/OE-Skills | Skill | 27 | 4mo ago | Apache-2.0 | A | 72 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |