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 agentmods add skills/axera-tech/magnetar/toolchainnpx skills add AXERA-TECH/Magnetar --skill toolchaingit 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/toolchain)<a href="https://agentmods.dev/skills/axera-tech/magnetar/toolchain"><img src="https://agentmods.dev/badge/skills/axera-tech/magnetar/toolchain.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 | $0.00034 | $0.00667 |
| Opus 5 | $0.00017 | $0.00333 |
| Sonnet 5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
toolchain 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 yesterday.
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
TOOLCHAIN
执行
pulsar_image = magnetar.stages.toolchain.run()
LLM 分支（model_route=llm）
- 额外确认
pulsar2 llm_build2 -h可用（Pulsar2 ≥ 6.0）；不可用 → blocked， 提示升级独立包（./scripts/install_pulsar2.sh默认自动获取最新发布版）； - 准备 ax-llm-build 工具：
magnetar.stages.llm.ensure_axllm_build_tools(task_dir)（默认经GH_PROXY克隆https://github.com/AXERA-TECH/ax-llm-build.git到TASK_DIR/cache/ax-llm-build）； - Pulsar2 只使用独立安装包（强制不用 Docker）：未设置
PULSAR2_HOME时，magnetar.pulsar2_util.ensure_pulsar2_package自动获取最新发布版*_package.tar.gz并解压到~/.cache/magnetar/pulsar2/<版本>/（仓库AXERA-TECH/Pulsar2：下载 URL ModelScope 优先、hf-mirror 兜底；PULSAR2_VERSION可固定版本、PULSAR2_PACKAGE=lite|full可选变体）； - BSP/runtime 下载地址以 ax-pipeline
scripts/build_common.sh为唯一来源 （按芯片取MSP_URL_DEFAULT/TOOLCHAIN_URL_DEFAULT，CXX_BSP_URL/CXX_TOOLCHAIN_URL可覆盖），不再去 ax-knowledge / ModelScope 翻 SDK 直链； - 记录板端 axllm 安装方式（官方
install.sh，axllm 分支）到 task.md。
验证
- Pulsar2 独立包可用（
bin/pulsar2存在且pulsar2 --version正常，非 Docker） - C++ BSP 交叉编译器存在（AX650: msp_50 + Arm GNU 9.2 aarch64；AX630C: msp_20e + Arm GNU 9.2 aarch64；AX620Q/AX620E: msp_20e + ax620q_bsp_sdk uclibc）
- LLM 分支：
pulsar2 llm_build2 -h正常；ax-llm-build 工具就绪
STOP
- Pulsar2 独立包不可用且无法从 ModelScope/HF AXERA-TECH/Pulsar2 获取
- BSP/交叉编译器缺失且无法下载
- LLM 分支：Pulsar2 无
llm_build2且无法升级 → blocked
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.
- yesterday Changed · +4 lines 387eaa6250cc
- 5d ago First seen · 34 lines · 34 tokens per session scan A 9862ad5f6ef8
toolchain is a skill published in the GitHub repository AXERA-TECH/Magnetar (22 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 667 once invoked, about $0.0002 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
new-cpp-lint
Create a new C++ lint rule, test it, run it across the codebase, and selectively apply fixes. Usage - /new-cpp-lint.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.