agentmods.dev

hb-analyzer-performance

hb-analyzer-performance is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 163 tokens per session (587 once invoked), scanned A, original, Apache-2.0.

A performance-analysis workflow for checking ONNX, HBIR, and HBM machine-learning models on Horizon Robotics J5 and J6 hardware. It examines measurements such as delay, memory bandwidth, and BPU use.

In plain words
What is it for?
Use it to evaluate models, inspect performance logs, test models on the device, compare floating-point and quantized versions, and investigate Transformer or Attention models in greater depth.
Why use it?
It helps explain why a model is slow or misses its timing target, instead of leaving performance problems as unexplained numbers. It also provides reports and data for comparing measurements and locating bottlenecks.

Skill for Claude CodeCodex

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

not rated 27repo 4mo ago A scan 163 tokens original Apache-2.0

Good fit Use it to evaluate models, inspect performance logs, test models on the device, compare floating-point and quantized versions, and investigate Transformer or Attention models in greater depth.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/hb-analyzer-performance
View source ↗ HorizonRobotics/OE-Skills
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 hb-analyzer-performance
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 hb-analyzer-performance

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/hb-analyzer-performance/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/hb-analyzer-performance)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/hb-analyzer-performance"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/hb-analyzer-performance/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 hb-analyzer-performance

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/hb-analyzer-performance"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/hb-analyzer-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 587 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 $0.00163 $0.00587
Opus 5.5 $0.00065 $0.00235
Sonnet 5.5 $0.00033 $0.00117
Haiku 4.5 $0.00016 $0.00059

Measured 2mo ago against content hash 1bd4924497d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hb-analyzer-performance 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/horizon_tc_ui/hb-analyzer-performance/SKILL.md · 57 lines

What it actually says

HB Analyzer 模型性能分析

当用户需要在 Horizon Robotics J5/J6 平台上使用 hb_analyzer 工具分析模型性能时，使用此技能。

何时使用

  • 用户要求分析模型性能
  • 用户想检查模型带宽或延时
  • 用户提到 "hb_analyzer" 或性能评测
  • 用户需要性能报告或瓶颈分析
  • 用户想评估浮点/量化模型

工作流程

按照以下步骤执行性能分析。详细说明请参考 references/ 目录中的文档。

第 1 步：理解需求

参考：references/step1-requirements.md

第 2 步：运行分析

参考：references/step2-run-analysis.md

第 3 步：检查结果

参考：references/step3-check-results.md

第 4 步：解读报告

参考：references/step4-interpret-results.md

重要：对于包含 Transformer/Attention 结构的模型，或延时不达标需要深入分析的场景，必须执行 step4 中的进阶分析（§F Block 级深度分析、§G 量化配置精度审计、§H 模型结构与硬件匹配分析），不能仅停留在算子类型聚合（hbm_op_time_by_type）层面。

第 5 步：提供建议

参考：references/step5-recommendations.md

快速参考

支持的模型格式：

  • ONNX (.onnx)
  • HBIR (.bc)
  • HBM (.hbm)

关键输出文件：

  • hb_analyzer_report.html - 交互式性能报告
  • analysis_summary.json - 详细分析数据
  • hb_analyzer*.log - 执行日志

常见问题：参考 references/troubleshooting.md

Files

What ships with it

7 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.

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 · 57 lines · 163 tokens per session scan A 1bd4924497d5

Subscribe to this mod's changes

hb-analyzer-performance is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 163 tokens to every session and 587 once invoked, about $0.0007 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.

Analytics and metricsHardware and IoT
Related

hb-analyzer-performance compared with skills from other repositories

hb-analyzer-performance next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hb-analyzer-performanceHorizonRobotics/OE-SkillsSkill274mo agoApache-2.0A163Claude 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