hccl-test

hccl-test is a skill for Claude Code, Codex from Ascend/agent-skills. It costs 69 tokens per session (3,934 once invoked), scanned C, original, MulanPSL-2.0.

A performance and function tester for HCCL, Huawei’s library for communication between Ascend NPUs. It tests distributed communication across multiple machines and operations such as AllReduce and AllGather, which combine or share data between devices.

In plain words
What is it for?
Installing MPI, checking SSH and CANN versions across machines, verifying HCCL, and measuring communication bandwidth in multi-node NPU clusters.
Why use it?
It helps verify that an NPU cluster can communicate correctly and shows how efficiently it moves data. Its checks can reveal setup problems before a distributed training run.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Installing MPI, checking SSH and CANN versions across machines, verifying HCCL, and measuring communication bandwidth in multi-node NPU clusters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ascend/agent-skills/hccl-test
Install

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.

Any agent
npx skills add Ascend/agent-skills --skill hccl-test
Clone the repo
git clone --depth 1 https://github.com/Ascend/agent-skills

Made for: Claude Code, 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 hccl-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/ascend/agent-skills/hccl-test.svg)](https://agentmods.dev/skills/ascend/agent-skills/hccl-test)
Your own site
<a href="https://agentmods.dev/skills/ascend/agent-skills/hccl-test"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/hccl-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00069 $0.03934
Opus 5 $0.00034 $0.01967
Sonnet 5 $0.00014 $0.00787
Haiku 4.5 $0.00007 $0.00393

Measured 8d ago against content hash da3a701a3123, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

hccl-test scanned grade C 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 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/multi-node-test.sh, scripts/parse-hccl-result.py, scripts/pre-test-check.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

ssh-copy-id -i ~/.ssh/id_rsa.pub root@<node1_ip>
skills/hccl-test/SKILL.md · 423 lines

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.

Read it on GitHub

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. 8d ago First seen · 423 lines · 69 tokens per session scan C da3a701a3123

Subscribe to this mod's changes

hccl-test is a skill published in the GitHub repository Ascend/agent-skills (39 stars, last pushed 4mo ago), licensed MulanPSL-2.0. It adds 69 tokens to every session and 3,934 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

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-ai-coding/awesome-ascend-skills · 71 tokens

plugin-test

A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.

zhinjs/zhin · 51 tokens

workflow-design

A method for designing and testing multi-step computer workflows, including their inputs, actions, conditions, and error handling.

mrpulor-gh/nuphus · 0 tokens

metago-delivery-gate

A delivery checklist for software work that links each requirement to code, tests, and proof that the result looks right. It includes screenshot comparison, where a new image is checked against a reference image.

metago-ai/metagolifeform · 81 tokens

metago-test-generator

Test Generation Engineer - specializes in automatically generating unit tests, boundary case tests, and integration tests from source code.

metago-ai/metagolifeform · 26 tokens

limrun-android-emulator

Drive an app running on a Limrun cloud Android emulator: install an APK, launch and terminate apps with crash reports, tap, type, read the UI element tree, screenshot, record video, inject microphone audio, shape network bandwidth, and use adb over the CLI's tunnel for logcat, files, and shell. Use after a build (from…

sutchan/Agent-Skills-Hub · 147 tokens