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-admingit 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-admin)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/cml-admin"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cml-admin/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-admin"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/cml-admin.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 | $0.00044 | $0.01440 |
| Opus 5.5 | $0.00018 | $0.00576 |
| Sonnet 5.5 | $0.00009 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
cml-admin 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 29d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CML Administration
MCP Server
- Command:
cml-mcp(pip-installed, stdio transport) - Requires:
CML_URL,CML_USERNAME,CML_PASSWORDenvironment variables
Available Tools
User Management
| Tool | Parameters | What It Does |
|---|---|---|
get_users |
none | List all CML users |
create_user |
username, password, fullname?, email?, admin? |
Create a new CML user |
get_user |
user_id/username |
Get user details (labs, resource usage) |
update_user |
user_id/username, fields to update |
Update user properties |
delete_user |
user_id/username |
Delete a CML user |
Group Management
| Tool | Parameters | What It Does |
|---|---|---|
get_groups |
none | List all CML groups |
create_group |
name, description?, members? |
Create a new group |
update_group |
group_id/name, fields to update |
Update group properties |
delete_group |
group_id/name |
Delete a group |
System Information
| Tool | Parameters | What It Does |
|---|---|---|
get_system_info |
none | CML version, uptime, resource usage (CPU, RAM, disk) |
get_node_defs |
none | List all available node definitions and their resource requirements |
get_licensing |
none | License status, node count, expiration |
get_resource_usage |
none | Current resource utilization across all labs |
Workflow: Onboard a New Lab User
When an admin wants to add a new team member:
- Check existing users:
get_usersto see current user list - Create the user:
create_userwith their credentials - Add to group (optional):
update_groupto add user to a team group - Verify:
get_userto confirm creation - Share credentials: Report the username and CML URL to the admin (never share the password in Slack)
Workflow: Resource Capacity Check
Before building a large lab:
- Check system resources:
get_system_infofor CPU, RAM, disk - Check licensing:
get_licensingfor available node count - Check node definitions:
get_node_defsfor per-node resource requirements - Calculate: Does the planned lab fit within available resources?
- Report: "You have X GB RAM free, Y CPU cores available, Z node licenses remaining. Your planned lab needs A GB RAM and B nodes."
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.
- 29d ago Changed · +5 lines 939af65ed8e5
- 1mo ago First seen · 126 lines · 44 tokens per session scan A 1c77f54a5f51
cml-admin is a skill published in the GitHub repository automateyournetwork/netclaw (684 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,440 once invoked, about $0.0002 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.
Other skills, from other repositories
m4-api
Query M4 clinical datasets (MIMIC-IV, MIMIC-IV-Note, MIMIC-IV-ED, eICU, MIMIC-III, MIMIC-CXR-JPG, and demos) from Python with import m4: find tables, run SQL into pandas, search clinical notes, select chest X-ray cohorts and fetch their images, handle M4's errors. Use before writing Python or SQL against M4 data.
documentdb-collection-admin
Database, collection, and user administration on a DocumentDB (MongoDB-compatible, PostgreSQL-backed) server via the documentdb-mcp MCP server — list/create/drop/rename databases and collections, and manage database users and their roles. Use when the agent must provision or tear down namespaces, enumerate the…
ai-use-case-assessment
Identify, score, and prioritize Salesforce AI use cases before any implementation begins — opportunity identification, Impact-Effort matrix scoring, feasibility evaluation across Technical/Operational/Data/Risk dimensions, and ROI framing. NOT for the license checks and enablement steps once a use case is approved …
b2b-vs-b2c-requirements
Use this skill to determine whether a Salesforce Commerce project should use B2B Commerce (account-gated, BuyerGroup-based, contract pricing) or D2C Commerce (consumer storefront, guest checkout, individual-based). Trigger keywords: B2B vs B2C, commerce platform selection, buyer journey, account-based purchasing…
system-admin
Linux system administration and monitoring.
free-model-manager
Free AI model management - discover, download, and manage free/open-source AI models from Ollama, HuggingFace, and other sources.