fabric-benchmarking

fabric-benchmarking is a skill for Claude Code from fabric-testbed/claude-plugin-marketplace. It costs 21 tokens per session (1,931 once invoked), scanned B, original, Apache-2.0.

A guide for measuring network performance on FABRIC, a research testbed, with iPerf3, a tool for network throughput testing. It covers basic container tests and optional CPU, memory, NUMA, and SmartNIC tuning.

In plain words
What is it for?
Use it to generate iPerf3 benchmark code for FABRIC, from basic FABNet tests to configurations using CPU pinning, NUMA tuning, or dedicated ConnectX network cards.
Why use it?
It gives a structured way to choose how much performance tuning a FABRIC benchmark needs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the fablib plugin — 18 skills, 1 command shipped together

Good fit Use it to generate iPerf3 benchmark code for FABRIC, from basic FABNet tests to configurations using CPU pinning, NUMA tuning, or dedicated ConnectX network cards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking
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 fabric-testbed/claude-plugin-marketplace --skill fabric-benchmarking
Clone the repo
git clone --depth 1 https://github.com/fabric-testbed/claude-plugin-marketplace

Made for: Claude Code.

Or install fablib, the plugin that ships this one along with the rest of its 18 skills, 1 command.

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 fabric-benchmarking

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking/github.svg)](https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking)
Your own site
<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking/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 fabric-benchmarking

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-benchmarking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,931 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00021 $0.01931
Opus 5 $0.00010 $0.00966
Sonnet 5 $0.00004 $0.00386
Haiku 4.5 $0.00002 $0.00193

Measured 11d ago against content hash 2ced395b8413, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

fabric-benchmarking scanned grade B 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 11d 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.

node1.add_post_boot_execute('sudo node_tools/host_tune.sh')
plugins/fablib/skills/fabric-benchmarking/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

When invoked, generate code for network performance benchmarking on FABRIC using iPerf3. Three tiers:

  1. Basic — iPerf3 over FABNet with Docker containers
  2. Optimized — CPU pinning, NUMA tuning, and host_tune.sh
  3. SmartNIC — Dedicated ConnectX NICs with full hardware optimization

Help the user choose the right level and generate complete code.

API Reference

Performance Tuning

node.pin_cpu(component_name='nic1')  # Pin vCPUs to NIC's NUMA node
node.numa_tune()                      # Pin memory to same NUMA node
node.os_reboot()                      # Reboot to apply

Post-Reboot Reconfiguration

slice.wait_ssh()
for node in slice.get_nodes():
    node.config()  # Re-configure network interfaces

Patterns

Basic iPerf3 (FABNet + Docker)

from fabrictestbed_extensions.fablib.fablib import FablibManager

fablib = FablibManager()

[site1, site2] = fablib.get_random_sites(count=2)

slice = fablib.new_slice(name="iperf3-basic")

node1 = slice.add_node(
    name="server",
    site=site1,
    cores=4,
    ram=16,
    disk=50,
    image="default_rocky_9",
)
node1.add_fabnet()
node1.add_post_boot_upload_directory('node_tools', '.')
node1.add_post_boot_execute('sudo node_tools/host_tune.sh')
node1.add_post_boot_execute('node_tools/enable_docker.sh {{ _self_.image }}')
node1.add_post_boot_execute(
    'docker pull fabrictestbed/slice-vm-rocky8-multitool:0.0.2'
)

node2 = slice.add_node(
    name="client",
    site=site2,
    cores=4,
    ram=16,
    disk=50,
    image="default_rocky_9",
)
node2.add_fabnet()
node2.add_post_boot_upload_directory('node_tools', '.')
node2.add_post_boot_execute('sudo node_tools/host_tune.sh')
node2.add_post_boot_execute('node_tools/enable_docker.sh {{ _self_.image }}')
node2.add_post_boot_execute(
    'docker pull fabrictestbed/slice-vm-rocky8-multitool:0.0.2'
)

slice.submit()
server = slice.get_node(name="server")
client = slice.get_node(name="client")

server_addr = server.get_interface(
    network_name=f"FABNET_IPv4_{server.get_site()}"
).get_ip_addr()

# Start iPerf3 server (single test mode)
server.execute(
    "docker run -d --rm --network host "
    "fabrictestbed/slice-vm-rocky8-multitool:0.0.2 iperf3 -s -1"
)

# Run iPerf3 client (4 parallel streams, 30 sec, 10 sec omit)
stdout, stderr = client.execute(
    f"docker run --rm --network host "
    f"fabrictestbed/slice-vm-rocky8-multitool:0.0.2 "
    f"iperf3 -c {server_addr} -P 4 -t 30 -i 10 -O 10"
)
print(stdout)

Read the full file on GitHub · 252 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. 11d ago First seen · 252 lines · 21 tokens per session scan B 2ced395b8413

Subscribe to this mod's changes

fabric-benchmarking is a skill published in the GitHub repository fabric-testbed/claude-plugin-marketplace (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,931 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens