agentmods.dev

nccl

nccl is a skill for Claude Code, Codex from jstzwj/ai-infra-plugins. It costs 150 tokens per session (2,417 once invoked), scanned A, original, no licence file.

A reference guide for NVIDIA NCCL, a library that lets GPUs exchange data during multi-GPU or multi-machine computing. It covers operations such as combining, sharing, sending, and receiving data between GPUs.

In plain words
What is it for?
Use it when implementing or investigating GPU communication, including all-reduce, all-gather, reduce-scatter, broadcast, gather/scatter, all-to-all, and point-to-point send or receive operations.
Why use it?
It helps developers understand and use NCCL communication operations without having to piece together the library's terminology and behavior themselves.

Skill for Claude CodeCodex

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

not rated 4repo 6mo ago A scan 150 tokens no licence

Good fit Use it when implementing or investigating GPU communication, including all-reduce, all-gather, reduce-scatter, broadcast, gather/scatter, all-to-all, and point-to-point send or receive operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jstzwj/ai-infra-plugins/nccl
View source ↗ jstzwj/ai-infra-plugins
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 jstzwj/ai-infra-plugins --skill nccl
Clone the repo
git clone --depth 1 https://github.com/jstzwj/ai-infra-plugins

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin nccl — /plugin install nccl after adding the marketplace above.

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 nccl

README.md
[![agentmods](https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/nccl/github.svg)](https://agentmods.dev/skills/jstzwj/ai-infra-plugins/nccl)
Your own site
<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/nccl"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/nccl/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 nccl

Your own site · 80×15
<a href="https://agentmods.dev/skills/jstzwj/ai-infra-plugins/nccl"><img src="https://agentmods.dev/badge/skills/jstzwj/ai-infra-plugins/nccl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00150 $0.02417
Opus 5.5 $0.00060 $0.00967
Sonnet 5.5 $0.00030 $0.00483
Haiku 4.5 $0.00015 $0.00242

Measured 2mo ago against content hash 365d2a9ffca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nccl 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 2mo 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.

plugins/nccl/skills/nccl/SKILL.md · 158 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 158 lines · 150 tokens per session scan A 365d2a9ffca6

Subscribe to this mod's changes

nccl is a skill published in the GitHub repository jstzwj/ai-infra-plugins (4 stars, last pushed 6mo ago), with no licence file. It adds 150 tokens to every session and 2,417 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.

Hardware and IoTScientific
Related

nccl compared with skills from other repositories

nccl next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nccljstzwj/ai-infra-pluginsSkill46mo agononeA150Claude Code, Codex
neuroskill-bciNousResearch/hermes-agentSkill261kyesterdayMITA18Claude Code, Codex
ruview-applicationsruvnet/RuViewSkill103kyesterdayMITA79Claude Code
lab-hardware-cadK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA108Claude Code
pylabrobotK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA49Claude Code
pybammK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA70Claude Code, Codex
calibrate-roomruvnet/RuViewSkill103kyesterdayMITA41Claude Code