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-plugin-set-marchgit 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-plugin-set-march)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-set-march"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-set-march/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-plugin-set-march"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-set-march.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 | $0.00027 | $0.01223 |
| Opus 5 | $0.00014 | $0.00611 |
| Sonnet 5 | $0.00005 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
j6-plugin-set-march 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 11d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
为 Horizon 量化/部署流程设置 march(先询问用户版)
目标
在接入 horizon_plugin_pytorch 的训练、推理、校准、导出或编译流程中,显式设置当前使用的 BPU march。
本 Skill 强约束:
- 先询问用户想用哪个 march:只有在用户明确给出 march 后,才插入对应的
set_march(...)代码。 - 不擅自猜具体 march:如果用户没有说明,只能提示可选值并请求确认;不能默认写死成
NASH_E/NASH_M等。 - 只做 march 设置相关改动:不顺带改 prepare、qconfig、fake quantize、dynamic block 或其他量化逻辑。
- 优先放在脚本入口或模型构建前:通常应在模型构建、prepare、train/predict/export 之前调用。
理解 march.py 的核心用法
1) march 枚举值
horizon.march.March.NASH_E
horizon.march.March.NASH_M
horizon.march.March.NASH_P
horizon.march.March.NASH_B
2) 设置 march
horizon.march.set_march(horizon.march.March.NASH_E)
标准改法(通用模板)
1) 先向用户确认 march
在执行改动前,必须询问:
- 你想使用哪个 march?
推荐给用户的可选项表达:
horizon.march.March.NASH_Ehorizon.march.March.NASH_Phorizon.march.March.NASH_B
如果用户没有给出明确 march:
- 不要直接修改代码。
- 先停在方案说明阶段,等待用户确认具体 march。
2) 增加 import
如果文件里还没有 horizon_plugin_pytorch 导入,先补:
import horizon_plugin_pytorch as horizon
如果文件已经导入 horizon_plugin_pytorch,则直接复用,不重复导入。
3) 在合适位置插入 set_march
通常插入位置优先级:
- 脚本
main()/if __name__ == "__main__":中,且在模型构建前 - 推理/训练/导出入口函数开头
- 若工程统一从配置读取,则在读取完 config 后、build model 前
import horizon_plugin_pytorch as horizon
def main():
horizon.march.set_march(horizon.march.March.NASH_E)
model = build_model()
...
适用场景
这个 Skill 适合以下需求:
- 适配
horizon_plugin_pytorch时,需要补 march 设置 - 训练/校准/验证/导出脚本里缺少
horizon.march.set_march(...) - 需要把用户指定的 march 显式写进入口逻辑
- 需要统一脚本行为,避免依赖进程中的全局残留 march
不适用场景
以下情况不属于本 Skill 的直接处理范围:
- 给模型做
prepare(...) - 调整 fake quantize 状态
- 插入
QuantStub/DeQuantStub - 处理动态控制流 / dynamic block
- 根据不同 march 大规模改模型实现细节
如果用户同时提这些需求,应分步处理,march 设置仅负责其中一环。
常见插入位置建议
训练/推理/导出脚本
典型结构:
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
horizon.march.set_march(horizon.march.March.NASH_E)
model = build_from_registry(cfg.model)
注意:
set_march(...)一般应在build_model()/prepare()/export()之前。- 如果后续代码依赖
get_march()或with_march,更要提前设置。
What ships with it
1 file 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.
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.
- 11d ago First seen · 165 lines · 27 tokens per session scan A 2253bd6eacc8
j6-plugin-set-march is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,223 once invoked, about $0.0001 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.