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 j6-hbdk-export-compilegit 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/j6-hbdk-export-compile)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-hbdk-export-compile"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-hbdk-export-compile/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/j6-hbdk-export-compile"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-hbdk-export-compile.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 | $0.00125 | $0.01694 |
| Opus 5 | $0.00063 | $0.00847 |
| Sonnet 5 | $0.00025 | $0.00339 |
| Haiku 4.5 | $0.00013 | $0.00169 |
Grade A, and why
j6-hbdk-export-compile 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基础结构导出编译流程代码生成
目标
将校准或 QAT 训练后的模型导出并编译为可部署的 HBM 文件。本 Skill 接收量化流程产出的模型(calib_net 或 qat_net),完成从 export 到编译的全部流程。
本 Skill 覆盖的流程:
export QAT BC → convert → remove_io_op → statistics → compile HBM
前置条件
本 Skill 依赖 j6-plugin-quantization skill 的输出:
- 校准后或 QAT 训练后的模型(
calib_net或qat_net) - 示例输入(
example_input) - 目标平台 march
导入
from horizon_plugin_pytorch.quantization.hbdk4 import export
from hbdk4.compiler import convert, compile, statistics, save
导入路径严禁违反以下规则:
export必须从horizon_plugin_pytorch.quantization.hbdk4导入。 不得从horizon_plugin_pytorch.quantization或horizon_plugin_pytorch导入。convert, compile, statistics, save必须全部从hbdk4.compiler导入。 不得从horizon_plugin_pytorch.quantization或任何其他模块路径导入。- 不得使用其他导入路径替代上述路径。
注意: 当本 sub-skill 作为 j6-plugin-hbdk-generating(编排型 skill)的一部分被调用时,导入语句必须与量化子 skill 的导入合并到文件顶部的一个统一导入块中,格式严格遵循 references/full-pipeline-template.md。
Step 1: 导出 QAT BC
将量化模型导出为 BC 格式。先切换到 VALIDATION 状态,验证推理正常后再 export:
# model 为 calib_net 或 qat_net
model.eval()
set_fake_quantize(model, FakeQuantState.VALIDATION)
# 验证量化模型在 VALIDATION 状态下推理正常
with torch.no_grad():
model(example_input)
qat_bc = export(model, example_input)
Step 2: Convert — 转换为量化模型
将 QAT BC 转换为目标平台专用的量化模型:
quantized_model = convert(qat_bc, march)
save(quantized_model, "quantized.bc")
convert 调用严禁违反以下规则:
march参数不可省略。 必须写成convert(qat_bc, march),禁止写成convert(qat_bc)或convert(exported_model)。
Step 3: Remove IO Op — 删除首尾 Quantize/Dequantize 算子
部署时输入输出不需要首尾的量化/反量化节点,必须删除。不删除会导致模型在 BPU 上无法正确运行:
func = quantized_model.functions[0]
func.remove_io_op(op_types=["Dequantize", "Quantize"])
save(quantized_model, "quantized_remove.bc")
remove_io_op 调用严禁违反以下规则:
- 必须先取
quantized_model.functions[0]得到 func,再对 func 调用remove_io_op。 禁止直接对quantized_model调用remove_io_op()(即converted_model.remove_io_op()是错误写法)。 - 必须指定
op_types=["Dequantize", "Quantize"]参数。 禁止省略op_types写成func.remove_io_op(),不指定 op_types 可能删除错误节点。 - remove_io_op 之后必须
save。 保存 remove_io_op 后的 BC 文件,便于对比和排查。
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 · 150 lines · 125 tokens per session scan A 84b8aa0025eb
j6-hbdk-export-compile is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,694 once invoked, about $0.0006 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.