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 agentmods add skills/scitix/siclaw/gateway-diagnosticsnpx skills add scitix/siclaw --skill gateway-diagnosticsgit clone --depth 1 https://github.com/scitix/siclawWrote 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/scitix/siclaw/gateway-diagnostics)<a href="https://agentmods.dev/skills/scitix/siclaw/gateway-diagnostics"><img src="https://agentmods.dev/badge/skills/scitix/siclaw/gateway-diagnostics.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01037 |
| Opus 5 | $0.00047 | $0.00518 |
| Sonnet 5 | $0.00019 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
gateway-diagnostics 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateway Diagnostics
Inspect and test the gateway of a network interface. Two operations, one script each; both run identically on a node or inside a pod — the only difference is how you launch them (see Targets below).
Router
| Need | Action |
|---|---|
| See the gateway / default route for an interface (with TYPE) | scripts/show-gateway.sh |
| Test whether the gateway is reachable | scripts/ping-gateway.sh |
| Target is a node (or a bound SSH host) | run directly — see Node target |
| Target is a pod | resolve the netns first — see Pod target |
| Switchdev PF caveat, or what RoCE/Ethernet/IB means | read references/switchdev-and-interface-types.md |
Targets
Node target
Prefer host_script when the node is a bound SSH host (check host_list) — it
runs over SSH with no debug pod. Fall back to node_script otherwise. Both take
the same skill / script / args.
host_script: host="<host>", skill="gateway-diagnostics", script="show-gateway.sh", args="<args>"
node_script: node="<node>", skill="gateway-diagnostics", script="show-gateway.sh", args="<args>"
Pod target
Runs in the pod's network namespace using host tools — one step: pass pod
(+ namespace) and node_script resolves the node and enters the pod's netns
for you:
node_script: pod="<pod>", namespace="<ns>", skill="gateway-diagnostics", script="ping-gateway.sh", args="<args>"
node_scriptresolves the pod → node + netns internally and runs the script in the pod's network namespace. The same script file serves both node and pod targets.
Parameters
show-gateway.sh
| Parameter | Required | Description |
|---|---|---|
--interface IFACE |
no | Network interface name. If omitted, shows all. |
--json |
no | Output in JSON format (adds a type field per gateway). |
ping-gateway.sh
| Parameter | Required | Description |
|---|---|---|
--interface IFACE |
yes | Network interface to find the gateway for |
--source-ip |
no | flag — auto-detect IP from the interface, use as ping source (-I <ip>) |
--source-dev |
no | flag — use the interface name as ping source (-I <iface>) |
--count N |
no | Number of ping packets (default: 3) |
What ships with it
3 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.
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.
- 6d ago First seen · 103 lines · 94 tokens per session scan A 9811afa02faf
gateway-diagnostics is a skill published in the GitHub repository scitix/siclaw (232 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 1,037 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
k8s-deployment-rollout
Kubernetes Deployment 发布失败、滚动更新卡住的完整诊断-修复-验证 Skill.
k8s-pod-crashloop
Pod CrashLoopBackOff / OOMKilled 诊断与修复：Pod CrashLoopBackOff 和 OOMKilled 是 Kubernetes 工作负载中最常见的问题类型。本 Skill 覆盖从症状识别到修复验证的完整闭环。.
devops-deployment
Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
kubernetes-expert
Expert-level Kubernetes cluster management, deployment strategies, networking, and production operations. Use when the user mentions containers, orchestration, devops, or cloud native, or when the task involves Kubernetes Architecture, Pods, Deployments, or Services.
lucas-runbook
Lucas runbook-driven troubleshooting for Kubernetes issues. Use when investigating pod errors, crashes, restarts, or any Kubernetes problem. Automatically search runbooks before taking action.