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 fabric-testbed/claude-plugin-marketplace --skill fabric-routinggit clone --depth 1 https://github.com/fabric-testbed/claude-plugin-marketplaceWrote 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-routing)<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-routing"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-routing/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-routing"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-routing.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 | $0.00024 | $0.03304 |
| Opus 5.5 | $0.00010 | $0.01322 |
| Sonnet 5.5 | $0.00005 | $0.00661 |
| Haiku 4.5 | $0.00002 | $0.00330 |
Grade B, and why
fabric-routing 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
node2.execute("echo 1 | sudo tee /proc/sys/net/ipv4/ip_forward") How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
When invoked, generate code for routing and tunneling on FABRIC nodes. Options include:
- Static Routes — Manual IP routing with IP forwarding between subnets
- WireGuard VPN — Encrypted overlay network between FABRIC nodes or to external hosts
- sshuttle — TCP-over-SSH tunnel for quick access without VPN setup
- Performance Tuning — Network buffer and kernel parameter optimization
Ask the user what connectivity problem they're solving.
Use the modern API pattern: create networks with add_l2network(subnet=...), use iface.set_mode('auto') and net.add_interface(iface) for auto IP configuration.
API Reference
IP Routing on Nodes
# High-level route (preferred for FABnet)
node.add_route(
subnet: IPv4Network | IPv6Network,
next_hop: IPv4Address | IPv6Address | NetworkService,
)
# Low-level IP configuration (for manual setup)
node.ip_addr_add(addr, subnet, interface, persistent=None)
node.ip_link_up(subnet, interface)
node.ip_route_add(subnet, gateway, interface=None, persistent=None)
Patterns
Static Routes Between Subnets (Three Nodes)
from ipaddress import IPv4Network
from fabrictestbed_extensions.fablib.fablib import FablibManager
fablib = FablibManager()
slice = fablib.new_slice(name="routing-experiment")
[site1, site2, site3] = fablib.get_random_sites(count=3)
net1_subnet = IPv4Network("192.168.1.0/24")
net2_subnet = IPv4Network("192.168.2.0/24")
# Create L2 networks with subnets for auto IP
net1 = slice.add_l2network(name="net1", subnet=net1_subnet)
net2 = slice.add_l2network(name="net2", subnet=net2_subnet)
# Node1 on site1 — connected to net1
node1 = slice.add_node(name="Node1", site=site1, image="default_ubuntu_24")
iface1 = node1.add_component(model="NIC_Basic", name="nic1").get_interfaces()[0]
iface1.set_mode('auto')
net1.add_interface(iface1)
# Node2 on site2 — bridging node with interfaces on both networks
node2 = slice.add_node(name="Node2", site=site2, image="default_ubuntu_24")
iface2a = node2.add_component(model="NIC_Basic", name="nic1").get_interfaces()[0]
iface2a.set_mode('auto')
net1.add_interface(iface2a)
iface2b = node2.add_component(model="NIC_Basic", name="nic2").get_interfaces()[0]
iface2b.set_mode('auto')
net2.add_interface(iface2b)
# Node3 on site3 — connected to net2
node3 = slice.add_node(name="Node3", site=site3, image="default_ubuntu_24")
iface3 = node3.add_component(model="NIC_Basic", name="nic1").get_interfaces()[0]
iface3.set_mode('auto')
net2.add_interface(iface3)
slice.submit()
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.
- 2mo ago First seen · 345 lines · 24 tokens per session scan B 052b46b92501
fabric-routing is a skill published in the GitHub repository fabric-testbed/claude-plugin-marketplace (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 3,304 once invoked, about $0.0001 per session on Opus 5.5. 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.
fabric-routing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fabric-routingfabric-testbed/claude-plugin-marketplace | Skill | 2 | 8mo ago | Apache-2.0 | B | 24 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |