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 5.5 | $0.00011 | $0.00489 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo 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 (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,223 once invoked, about $0.0001 per session on Opus 5.5. 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.
j6-plugin-set-march compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| j6-plugin-set-marchHorizonRobotics/OE-Skills | Skill | 27 | 4mo ago | Apache-2.0 | A | 27 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |