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 oe-package-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/oe-package-detection)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/oe-package-detection"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/oe-package-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/oe-package-detection"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/oe-package-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 | $0.02350 |
| Opus 5 | $0.00036 | $0.01175 |
| Sonnet 5 | $0.00014 | $0.00470 |
| Haiku 4.5 | $0.00007 | $0.00235 |
Grade A, and why
oe-package-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 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OE 包环境检测
执行方式
本 Skill 应通过 subagent 执行。 主 agent 在前置检查中发现
.env.oe-package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(OE 路径、版本、执行模式),主 agent 读取.env.oe-package继续后续流程。
目标
检测 OE 包路径、版本及本地环境匹配情况,写入 .horizon/.env.oe-package,供后续所有工具链任务直接使用。
触发条件
任何涉及量化、编译、部署、板端推理、性能/精度评估的任务进入 horizon-router 前,如果 .horizon/.env.oe-package 不存在,顶层 Skill 会中断任务并提示用户:
未检测到 OE 包环境配置(
.horizon/.env.oe-package)。请提供 OE 包路径,或回复"跳过"暂不配置。
- 用户提供路径 → 进入本检测流程
- 用户回复"跳过" → 记录跳过(仅当次对话有效,下次仍会提示),继续后续任务
检测流程
1. 检查 .horizon/.env.oe-package 是否存在
- 文件存在且内容完整(包含
OE_DIR、OE_VERSION、EXECUTION_MODE等字段)→ 直接读取,跳过后续步骤 - 文件不存在或不完整 → 进入步骤 2
2. 定位 OE 包路径
按优先级查找:
- 环境变量:
OE_DIR、OPEN_EXPLORER_DIR、HORIZON_OE_DIR - 项目配置文件:
.env、.horizon/oe.env、CLAUDE.md中声明的路径 - 常见路径探测:
/open_explorer、~/open_explorer、/opt/openexplorer - 以上都没有 → 询问用户 OE 包路径
找到路径后,验证目录中存在 OE 包的标志性文件(如 run_docker.sh、samples/、docs/、toolchain/ 等至少两个),否则提示用户确认路径是否正确。
3. 采集 OE 版本信息
从 OE 包目录中提取以下信息:
OE 包整体版本:
- 检查
version.txt、VERSION、release_notes.md或release_notes.txt - 从文件名推断(如
OpenExplorer_v3.9.0_rc4) - 以上都无法确定时询问用户
各组件版本(通过 pip show 检查已安装版本,同时记录 OE 包内 whl 文件名中的版本):
| 组件 | pip 包名 | 说明 |
|---|---|---|
horizon_tc_ui |
horizon-tc-ui |
模型集成工具 |
hmct |
hmct |
模型转换/量化工具 |
horizon_plugin_pytorch |
horizon-plugin-pytorch |
PyTorch 量化插件(QAT) |
hbdk4_compiler |
hbdk4-compiler |
编译器 |
Docker 信息:
- 检查
run_docker.sh是否存在 - 从
run_docker.sh内容或 OE 版本推断 Docker 镜像名称:- CPU:
openexplorer/ai_toolchain_ubuntu_22_j6_cpu:{version} - GPU:
openexplorer/ai_toolchain_ubuntu_22_j6_gpu:{version}
- CPU:
4. 本地环境匹配检查
在当前环境中逐项检测:
- Python 版本:
python3 --version,要求 >= 3.8 - pip 组件:对每个组件执行
pip show <包名>,记录:- 是否安装
- 版本号是否与 OE 包声明一致
- CLI 工具可用性:检查以下命令是否可执行:
hb_compile --version(或which hb_compile)hb_model_info --version(或which hb_model_info)hmct-debugger --version(或which hmct-debugger)
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 · 177 lines · 72 tokens per session scan A f816dd0e5ac8
oe-package-detection is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,350 once invoked, about $0.0004 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.