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 hbdk-manualgit 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/hbdk-manual)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/hbdk-manual"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/hbdk-manual/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/hbdk-manual"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/hbdk-manual.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 | $0.00021 | $0.01107 |
| Opus 5.5 | $0.00008 | $0.00443 |
| Sonnet 5.5 | $0.00004 | $0.00221 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
skills 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基于HBDK4版本 4.9.7 编写，Docker镜像版本 v3.9.0_rc4。
流程总览
.bc模型有两个来源：
- PTQ流程：ONNX模型通过
hbdk4.compiler.onnx.export导出（ptq.onnx → ptq.bc） - QAT流程：由其它模块从
torch.nn.Module导出（qat.bc），该torch模型不在hbdk工作流内，由外部提供
PTQ: ONNX模型(ptq.onnx) → 导出HBIR(ptq.bc) ─┐
├→ 定点化(quantized.bc) → 编译(HBM) → 部署
QAT: torch.nn.Module → qat.bc（外部提供） ────┘
│ │
插入预处理节点 性能评估
查询/修改模型 推理验证
│
完整工作流参考 → references/workflow_reference.md
Skill列表
模型导入与序列化
| Skill | 说明 |
|---|---|
| model-export.md | 将ONNX模型导出为伪量化HBIR模型（.bc文件），支持模型统计和可视化 |
| model-serialization.md | 将HBIR模型保存到.bc文件，或从.bc文件加载HBIR模型 |
模型转换与编译
| Skill | 说明 |
|---|---|
| model-convert.md | 将伪量化HBIR模型转换为指定march的定点模型 |
| model-compile.md | 将定点化HBIR模型编译为HBM文件 |
模型修改
| Skill | 说明 |
|---|---|
| model-info-query.md | 查询和修改HBIR模型的输入输出、march信息、tensor名称、精度配置等 |
| insert-nodes.md | 在HBIR模型输入输出参数上插入预处理节点（pyramid/preprocess/resize/transpose/split/rle） |
| remove-io-nodes.md | 删除HBIR模型输入输出相邻节点或指定类型/名称的节点 |
HBM模型
| Skill | 说明 |
|---|---|
| model-inference.md | 推理HBIR和HBM模型，包括本地推理和远程BPU推理 |
| hbm-perf.md | 对HBM模型进行性能分析，包括静态perf和动态perf |
| hbm-modify.md | 修改HBM模型描述信息和名称，查询量化信息 |
参考
| 文档 | 说明 |
|---|---|
| references/api_reference.md | API快速参考 |
| references/workflow_reference.md | 端到端工作流参考 |
快速入门路径
场景：我有一个ONNX模型，想部署到BPU
- model-export.md — 导出ONNX为HBIR
- model-convert.md — 定点化转换
- model-compile.md — 编译为HBM
- hbm-perf.md — 评估性能
What ships with it
13 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.
- CHANGELOG.md 1.5 KB
- hbm-modify.md 2.3 KB
- hbm-perf.md 23 KB
- insert-nodes.md 6.5 KB
- model-compile.md 3.3 KB
- model-convert.md 2.6 KB
- model-export.md 2.3 KB
- model-inference.md 3.1 KB
- model-info-query.md 5.0 KB
- model-serialization.md 1.3 KB
- references/api_reference.md 5.4 KB
- references/workflow_reference.md 4.0 KB
- remove-io-nodes.md 2.8 KB
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 · 89 lines · 21 tokens per session scan A 604e77e2737e
skills is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,107 once invoked, about $0.0001 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.
skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skillsHorizonRobotics/OE-Skills | Skill | 27 | 4mo ago | Apache-2.0 | A | 21 | Claude Code, Codex |
| spark-environment-setupwshobson/agents | Skill | 42k | yesterday | MIT | A | 76 | Claude Code |
| spark-memory-thermal-opswshobson/agents | Skill | 42k | yesterday | MIT | A | 59 | Claude Code |
| spark-training-gotchaswshobson/agents | Skill | 42k | yesterday | MIT | A | 63 | Claude Code |
| inference-serving-llama-cppdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 80 | Claude Code, Codex |
| amc-run-rtsp-calibrationNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 59 | Claude Code, Codex |
| deepstream-generate-pipelineNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 108 | Claude Code |