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 Ascend/agent-skills --skill cann-nnal-installergit clone --depth 1 https://github.com/Ascend/agent-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/ascend/agent-skills/cann-nnal-installer)<a href="https://agentmods.dev/skills/ascend/agent-skills/cann-nnal-installer"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/cann-nnal-installer/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/ascend/agent-skills/cann-nnal-installer"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/cann-nnal-installer.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 | $0.00080 | $0.03157 |
| Opus 5 | $0.00040 | $0.01579 |
| Sonnet 5 | $0.00016 | $0.00631 |
| Haiku 4.5 | $0.00008 | $0.00316 |
Grade B, and why
cann-nnal-installer scanned grade B with 2 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 755 <安装路径的父目录> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
jtbd-3: 当用户因官网下载链接需要登录认证而无法直接wget获取CANN安装包时。 The source is not reproduced here
Licensed MulanPSL-2.0
The repository is licensed MulanPSL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 12d ago First seen · 336 lines · 80 tokens per session scan B 3e9a916905d1
cann-nnal-installer is a skill published in the GitHub repository Ascend/agent-skills (40 stars, last pushed 4mo ago), licensed MulanPSL-2.0. It adds 80 tokens to every session and 3,157 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
external-gitcode-ascend-cann-nnal-installer
An installer for the full CANN software stack: Toolkit, Kernels, and NNAL for Ascend NPUs. It can install downloaded packages or extract them from a Docker image.
external-gitcode-ascend-atb-nnal-installer
An installer for NNAL, an ATB acceleration library used with Ascend NPUs. It relies on an existing CANN Toolkit and Kernels environment.
external-gitcode-ascend-ascend-transformer-boost
An index of skills for developing and deploying Huawei's Ascend Transformer Boost library, a set of tools for accelerating transformer-based AI models. It covers the main stages of working with Ascend NPUs and related operator libraries.
ai-for-science-ai4s-profiling
A performance-profiling guide for Huawei Ascend NPUs using `torchnpu.profiler`. Profiling records timing, call stacks, memory use, and other measurements so developers can see where training or inference spends time.
external-gitcode-ascend-atb-aclnn-operator-migration
A migration workflow for moving ATB operators to ACLNN, Ascend's operator library interface. It handles parameter mapping, runner implementation, device-based switching, and functional and performance checks.
ascend-avi-vnpu
A management workflow for Ascend virtualisation instances and virtual NPUs. A virtual NPU is a software-defined share or instance of an NPU that can be created, removed, inspected, or restored.