Magnetar: Skill for Codex

.codex/skills/magnetar/hidden/package/SKILL.md

package is a skill for Codex from AXERA-TECH/Magnetar. It costs 27 tokens per session (1,272 once invoked), scanned A, original, MIT.

A delivery-packaging stage for Magnetar that gathers the converted model, software libraries, reports, and instructions into one customer folder.

In plain words
What is it for?
Use it to prepare one-click setup and run scripts, Python and C++ examples, model-conversion instructions, model files, and validation reports.
Why use it?
It turns internal conversion results into files that a customer can install and run with copied commands.

Skill for Codex

Written for Codex: installed under .codex/.

This is AXERA-TECH/Magnetar's own configuration. It tells Codex how to work on Magnetar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Magnetar configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AXERA-TECH/Magnetar/main/.codex/skills/magnetar/hidden/package/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AXERA-TECH/Magnetar

Made for: 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 package

README.md
[![agentmods](https://agentmods.dev/badge/skills/axera-tech/magnetar/package/github.svg)](https://agentmods.dev/skills/axera-tech/magnetar/package)
Your own site
<a href="https://agentmods.dev/skills/axera-tech/magnetar/package"><img src="https://agentmods.dev/badge/skills/axera-tech/magnetar/package/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 package

Your own site · 80×15
<a href="https://agentmods.dev/skills/axera-tech/magnetar/package"><img src="https://agentmods.dev/badge/skills/axera-tech/magnetar/package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 49
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
How audits are shown
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 $0.00027 $0.01272
Opus 5.5 $0.00011 $0.00509
Sonnet 5.5 $0.00005 $0.00254
Haiku 4.5 $0.00003 $0.00127

Measured 1mo ago against content hash b7404c5137b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

package scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `setup.sh`:安装 axllm(`curl -fsSL
.codex/skills/magnetar/hidden/package/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PACKAGE

设计理念

交付包面向零基础小白用户。假设用户只会:

  1. 打开终端
  2. 复制粘贴命令
  3. 按回车

因此 README 必须极简、脚本必须一键跑通、所有命令必须完整可复制。

执行

pkg = magnetar.stages.package.assemble(task_dir, metrics, pulsar_image, model_name, labels)

交付包结构

package/
├── README.md           # 面向小白:两步跑起来(setup.sh → run.sh)
├── setup.sh            # 一键环境安装
├── run.sh              # 一键推理运行
├── models/
│   ├── model.axmodel
│   └── model_meta.json
├── python/             # Python SDK(基于 pyaxengine)
│   ├── demo.py         # 最简单的推理示例(复制即用)
│   └── requirements.txt
├── cpp/                # C++ SDK(CMake + 直接链接 AX runtime)
├── model_convert/      # export_onnx.py + pulsar2_config.json + compile_pulsar2.sh + README
│   └── README.md       # 覆盖环境准备、导出、编译、产物检查,命令可直接复制执行
└── reports/            # export/compile/simulate/runonboard 报告

LLM 分支(model_route=llm)

交付内容适配 axllm:

  • models/ 放 axllm 模型目录(config.json + tokenizer + 逐层/post *.axmodel
    • embedding bin + model_meta.json),不再要求单个 model.axmodel;
  • model_convert/ 放可复现 llm_build.sh(完整 pulsar2 llm_build2 命令 + embed_process.sh + axllm config 生成说明)+ README 覆盖 权重获取 → llm_build2 → embedding/tokenizer 处理 → 板端 axllm serve;
  • setup.sh:安装 axllm(curl -fsSL https://gh-proxy.com/https://raw.githubusercontent.com/AXERA-TECH/ax-llm/axllm/install.sh | bash, GH_PROXY 可覆盖) 或检查已装;run.sh:axllm serve models/ --port 8000 & 后运行 python/demo.py(OpenAI 兼容客户端)并打印回复;
  • python/requirements.txt 依赖仅 requests;reports/performance_report.md 记录 TTFT / token 速率 / 逐层 cosine(替代张量对分指标)。

一键脚本默认走国内镜像:setup.sh 中 pip 安装使用 PIP_INDEX_URL(默认 https://mirrors.aliyun.com/pypi/simple/)。

README 编写规范

  • 开头一句话说清这是什么模型(精度 + 速度 + 大小)
  • 快速开始不超过 2 步:bash setup.sh → bash run.sh
  • 不要出现占位符(如 ...、<path>、<fill me>)
  • 不要出现术语堆砌,必要时用 FAQ 解释
  • 所有代码块必须可直接复制粘贴执行

一键脚本规范

setup.sh

  • 安装 Python 依赖(pip install -r requirements.txt)
  • 检查必要组件(pyaxengine 等)
  • 打印明确成功/失败提示

run.sh

  • 调用 python/demo.py 或等价入口
  • 无需额外参数(若需图片则内置默认或从 models/ 取)
  • 输出清晰可读

Read the full file on GitHub · 114 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. 1mo ago First seen · 114 lines · 27 tokens per session scan A b7404c5137b0

Subscribe to this mod's changes

package is a skill published in the GitHub repository AXERA-TECH/Magnetar (22 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,272 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.