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 automateyournetwork/netclaw --skill kubeshark-trafficgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/kubeshark-traffic)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/kubeshark-traffic"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/kubeshark-traffic/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/automateyournetwork/netclaw/kubeshark-traffic"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/kubeshark-traffic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.01935 |
| Opus 5 | $0.00032 | $0.00967 |
| Sonnet 5 | $0.00013 | $0.00387 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade A, and why
kubeshark-traffic 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 9d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kubeshark Kubernetes Traffic Analysis
MCP Server
| Property | Value |
|---|---|
| Source | kubeshark/kubeshark — MCP docs |
| Transport | Remote HTTP (JSON-RPC 2.0, default port 8898) |
| Language | Go (built into Kubeshark Hub) |
| Tools | 6 (capture, export pcap, snapshot, filter, L4 flows, flow summary) |
| Auth | None (cluster-internal); requires kubectl port-forward for remote access |
| Requires | Kubernetes cluster with Kubeshark installed via Helm |
How to Run
# Install Kubeshark with MCP enabled
helm install kubeshark kubeshark/kubeshark \
--set mcp.enabled=true \
--set mcp.port=8898
# Port-forward for local access (if not in-cluster)
kubectl port-forward svc/kubeshark-hub 8898:8898
# MCP endpoint is now available at:
# http://localhost:8898/mcp
Environment Variables
| Variable | Required | Example | Description |
|---|---|---|---|
KUBESHARK_MCP_URL |
Yes | http://localhost:8898/mcp |
Kubeshark MCP endpoint URL |
KUBESHARK_MCP_PORT |
No | 8898 |
MCP server port (default: 8898) |
Tools
| Tool | Parameters | What It Does |
|---|---|---|
capture_traffic |
filter?, duration? |
Start targeted packet capture across cluster pods |
export_pcap |
filter?, time_range? |
Export captured traffic as pcap for Wireshark/tshark analysis |
create_snapshot |
filter? |
Create point-in-time traffic snapshot within retention window |
apply_filter |
kfl_expression |
Apply Kubeshark Filter Language (KFL) expressions to narrow results |
list_l4_flows |
filter? |
List TCP/UDP flows with connection stats, RTT metrics, byte counts |
get_l4_flow_summary |
filter? |
High-level summary: top talkers, protocol distribution, traffic volume |
Resources Exposed
- Real-time L7 API streams (HTTP, gRPC, GraphQL, Redis, Kafka, DNS) with full request/response payloads
- Historical traffic queries within the configured retention window
- Decrypted TLS/HTTPS traffic via eBPF (no manual key management)
- TCP/UDP connection flows with timing, RTT, and byte statistics
- Kubernetes pod identity and service mapping (source → destination with namespace/labels)
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.
- 9d ago First seen · 173 lines · 64 tokens per session scan A ba5c5c608aa2
kubeshark-traffic is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,935 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.