Borrowing it
Nothing to install: this file belongs to AXERA-TECH/Magnetar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AXERA-TECH/Magnetar/main/.codex/skills/magnetar/hidden/runonboard/SKILL.mdgit clone --depth 1 https://github.com/AXERA-TECH/MagnetarWrote 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/axera-tech/magnetar/runonboard)<a href="https://agentmods.dev/skills/axera-tech/magnetar/runonboard"><img src="https://agentmods.dev/badge/skills/axera-tech/magnetar/runonboard.svg" alt="Measured on agentmods" 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 | $0.00546 |
| Opus 5 | $0.00014 | $0.00273 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
runonboard 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 7d 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.
What it actually says
RUNONBOARD
执行
board_metrics = magnetar.stages.runonboard.run(task_dir, sample, target_hw, pwd)
需要 PyAXEngine 在板端可用。C++ 需先交叉编译（用 AARCH64_GXX 环境变量或 BSP 工具链）。
选到板后先 ensure_remote_infer(board)：检查 TCP 18500，daemon 未装则用官方 release 静默安装（装后可扫端口发现板子）。
LLM 分支（model_route=llm）
magnetar.stages.llm.install_axllm(board)：板端装 ax-llm（install.sh， 默认 axllm 分支，install.sh 下载经GH_PROXY代理，AX650 片上编译耗时较长，超时放宽）；serve_axllm(board, compile/llm_model_dir, port=8000)：上传模型目录 +axllm serve后台启动，轮询/health就绪；- 板端运行 Python SDK 示例（OpenAI 兼容客户端）：
validate_chat≥3 组 prompt greedy 语义验证，记录 TTFT（serve 日志ttft:）/ completion_tokens / token 速率 （avg token/s）/ 系统内存增量（free -m前后）/ CMM 占用 （/proc/ax_proc/mem_cmm_info前后）； runonboard_report.md记录上述指标；语义验证失败 → 检查 tokenizer/config/ 内存预检（mem_guard）并重试 ≤3 次。
验证
- Python SDK 板端推理成功，Python/C++ 输出 cosine ≥ 0.98
runonboard_report.md含 board host、chip_type、延迟、内存- LLM 分支：axllm serve 就绪 + ≥3 组 prompt 全非空 + TTFT/token 速率/内存已记录
STOP
- 无（BOARD 未配置时自动跳过，返回 None）
- LLM 分支：axllm 安装失败（缺 gcc/网络）且无法获取预编译产物 → STOP 说明缺失项
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.
- 7d ago First seen · 36 lines · 27 tokens per session scan A db2db228482f
runonboard is a skill published in the GitHub repository AXERA-TECH/Magnetar (22 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 546 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
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.