j6-hbdk-export-compile

j6-hbdk-export-compile is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 125 tokens per session (1,694 once invoked), scanned A, original, Apache-2.0.

Um gerador de código que transforma um modelo já quantizado num ficheiro HBM compilado para implantação em hardware Horizon. HBM é o formato de modelo usado pelo processo de compilação para execução no dispositivo.

In plain words
What is it for?
Serve para exportar modelos calibrados ou treinados com QAT, convertê-los, analisar as operações, remover operações de interface e gerar o ficheiro HBM final.
Why use it?
Evita ligar manualmente a exportação, conversão, remoção de operações de entrada e saída, verificação de operadores e compilação. Também verifica se o modelo pode depender de operações executadas no CPU.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Serve para exportar modelos calibrados ou treinados com QAT, convertê-los, analisar as operações, remover operações de interface e gerar o ficheiro HBM final.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/j6-hbdk-export-compile
Install

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.

Any agent
npx skills add HorizonRobotics/OE-Skills --skill j6-hbdk-export-compile
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for j6-hbdk-export-compile

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-hbdk-export-compile/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-hbdk-export-compile)
Your own site
<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.

agentmods 80×15 button for j6-hbdk-export-compile

Your own site · 80×15
<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>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01694
Opus 5.5 $0.00050 $0.00678
Sonnet 5.5 $0.00025 $0.00339
Haiku 4.5 $0.00013 $0.00169

Measured 2mo ago against content hash 84b8aa0025eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

horizon/skills/plugin/j6-plugin-hbdk-generating/j6-hbdk-export-compile/SKILL.md · 150 lines

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:

  1. export 必须从 horizon_plugin_pytorch.quantization.hbdk4 导入。 不得从 horizon_plugin_pytorch.quantization 或 horizon_plugin_pytorch 导入。
  2. 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。
  3. 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:

  1. 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:

  1. 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)。
  2. 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。
  3. 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。

Read the full file on GitHub · 150 lines

Changes

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.

  1. 2mo ago First seen · 150 lines · 125 tokens per session scan A 84b8aa0025eb

Subscribe to this mod's changes

j6-hbdk-export-compile is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,694 once invoked, about $0.0005 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.

Related

j6-hbdk-export-compile compared with skills from other repositories

j6-hbdk-export-compile next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
j6-hbdk-export-compileHorizonRobotics/OE-SkillsSkill274mo agoApache-2.0A125Claude Code, Codex
gke-compute-classesgoogle/skillsSkill22kyesterdayApache-2.0A83Claude Code, Codex
jetson-diagnosticNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code, Codex
holoscan-install-wheelNVIDIA/skillsSkill3.9kyesterdayApache-2.0A34Claude Code, Codex
offensive-z-waveSnailSploit/Claude-RedSkill10k25d agoMITA113Claude Code, Codex
doca-socket-relayNVIDIA/skillsSkill3.9kyesterdayApache-2.0A236Claude Code, Codex
hsb-flashNVIDIA/skillsSkill3.9kyesterdayApache-2.0B94Claude Code