Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fabric-testbed/claude-plugin-marketplacenpx agentmods add skills/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networkingWrote 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/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networking)<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networking"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networking/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/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networking"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-programmable-networking.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 | $0.00034 | $0.03550 |
| Opus 5 | $0.00017 | $0.01775 |
| Sonnet 5 | $0.00007 | $0.00710 |
| Haiku 4.5 | $0.00003 | $0.00355 |
Grade B, and why
fabric-programmable-networking 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.
("sudo $SDE_INSTALL/bin/./bf_kdrv_mod_load $SDE_INSTALL", r"\[nix\-shell\(SDE-9.13.3\):.*\$ ", 20), How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
When invoked, generate code for programmable networking on FABRIC. Four main capabilities:
- P4 Tofino — Barefoot Tofino programmable switches with SDE compilation and table population
- DPDK SmartNIC — High-performance packet processing with Mellanox ConnectX NICs
- BlueField DPU — NVIDIA BlueField-3 Data Processing Units with RShim management
- Open vSwitch (OVS) — Software-defined switching with STP support
Help the user choose the right approach and generate complete setup code.
API Reference
P4 Switch
# Add P4 Tofino switch to slice
switch = slice.add_switch(name="p4-switch", site=site)
# Get switch ports
iface1 = switch.get_interfaces()[0]
iface2 = switch.get_interfaces()[1]
# Interactive command execution (regex prompt matching)
switch.execute(command=[
("command", r"expected_prompt_regex", timeout_seconds),
])
# Get logical port numbers
port = switch.get_interfaces()[0].get_device_name()
NIC Models for Programmable Networking
# Standard SR-IOV (10 Gbps virtual function, 1 port)
model = 'NIC_Basic'
# Mellanox ConnectX-5 (25 Gbps dedicated, 2 ports)
model = 'NIC_ConnectX_5'
# Mellanox ConnectX-6 (100 Gbps dedicated, 2 ports)
model = 'NIC_ConnectX_6'
# BlueField-3 DPU (100 Gbps, 2 ports)
model = 'NIC_ConnectX_7_100'
# BlueField-3 DPU (400 Gbps, 2 ports)
model = 'NIC_ConnectX_7_400'
Hardware Info Methods
pci_addr = iface.get_component().get_pci_addr()[0]
mac_addr = iface.get_mac()
os_iface = iface.get_physical_os_interface_name()
dev_name = iface.get_device_name()
BlueField DPU Configuration
bluefield = node.get_component(name='nic1')
output = bluefield.configure() # Push BFB image via RShim
output = bluefield.configure(commands=['cmd1', 'cmd2']) # With custom commands
CPU/NUMA Tuning
node.pin_cpu(component_name='nic1') # Pin vCPUs to NIC's NUMA node
node.numa_tune() # Pin memory to same NUMA node
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.
- 11d ago First seen · 416 lines · 34 tokens per session scan B 03ad8b1edc0b
fabric-programmable-networking 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 34 tokens to every session and 3,550 once invoked, about $0.0002 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.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.