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 cml-packet-capturegit 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/cml-packet-capture)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/cml-packet-capture"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cml-packet-capture/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/cml-packet-capture"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cml-packet-capture.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 | $0.01643 |
| Opus 5.5 | $0.00026 | $0.00657 |
| Sonnet 5.5 | $0.00013 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
cml-packet-capture 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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CML Packet Capture
MCP Server
- Command:
cml-mcp(pip-installed, stdio transport) - Requires:
CML_URL,CML_USERNAME,CML_PASSWORDenvironment variables
Available Tools
Packet Capture Operations
| Tool | Parameters | What It Does |
|---|---|---|
start_capture |
lab_id/lab_title, link_id, max_packets?, pcap_filter? |
Start capturing packets on a link |
stop_capture |
lab_id/lab_title, link_id |
Stop an active capture |
get_capture_status |
lab_id/lab_title, link_id |
Check capture status (running, packet count) |
download_capture |
lab_id/lab_title, link_id, file_path? |
Download the captured pcap file |
list_captures |
lab_id/lab_title |
List all active and completed captures in a lab |
Workflow: Capture and Analyze (Full Pipeline)
When a user says "capture traffic between R1 and R2 and analyze it":
- Find the link: Use
get_links(from cml-topology-builder) to find the link ID between R1 and R2 - Start capture:
start_capturewith optional filter (e.g., "icmp", "tcp port 179") - Generate traffic: Tell the user to generate traffic (or use
execute_commandto ping) - Stop capture:
stop_captureafter sufficient traffic is collected - Download pcap:
download_captureto save the pcap file locally - Analyze with Packet Buddy: Hand off to the packet-analysis skill:
pcap_summary— overviewpcap_protocol_hierarchy— protocol breakdownpcap_conversations— who talked to whompcap_expert_info— errors, retransmissionspcap_filter— drill into specific traffic
- Report findings: Summarize the analysis in plain English
Workflow: Targeted Protocol Capture
When troubleshooting a specific protocol:
BGP Troubleshooting
1. start_capture with pcap_filter="tcp port 179"
2. Wait for BGP events (or trigger with clear ip bgp)
3. stop_capture
4. download_capture
5. Analyze: Look for OPEN, KEEPALIVE, UPDATE, NOTIFICATION messages
6. Check for: hold timer expiry, capability mismatch, prefix limit exceeded
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.
- 1mo ago Changed 90bcefed1879
- 1mo ago Changed · +5 lines 88b026841e55
- 2mo ago First seen · 142 lines · 64 tokens per session scan A 7512564ca4ef
cml-packet-capture is a skill published in the GitHub repository automateyournetwork/netclaw (717 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,643 once invoked, about $0.0003 per session on Opus 5.5. 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.
cml-packet-capture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cml-packet-captureautomateyournetwork/netclaw | Skill | 717 | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | B | 49 | Claude Code |
| analyzing-network-traffic-with-wiresharkkillvxk/cybersecurity-skills-zh | Skill | 57 | 6mo ago | Apache-2.0 | B | 58 | Claude Code |
| analyzing-network-traffic-with-wireshark26zl/cybersec-toolkit | Skill | 93 | 6d ago | MIT | B | 49 | Claude Code |
| analyzing-network-traffic-with-wiresharkandycungkrinx91/konoha | Skill | 62 | today | MIT | B | 49 | Claude Code, Codex |
| analyzing-network-traffic-of-malwareautohandai/community-skills | Skill | 13 | 3mo ago | Apache-2.0 | A | 81 | Claude Code, Codex |
| analyzing-network-traffic-of-malwareYoungmaidainon/Agent-Level-Up | Skill | 4 | 2mo ago | MIT | A | 81 | Claude Code, Codex |