defenseclaw-ops

defenseclaw-ops is a skill for Claude Code, Codex from automateyournetwork/netclaw. It costs 27 tokens per session (1,227 once invoked), scanned A, original, Apache-2.0.

A command-line operations guide for DefenseClaw, Cisco AI Defense security for NetClaw deployments. It covers sandboxing, component scans, runtime checks, audit logging, and security guardrails.

In plain words
What is it for?
Use it to check versions and gateway status, inspect configuration, scan components, review findings, and manage security settings and audit information.
Why use it?
It gives operators a consistent way to check whether the security service is running and identify unsafe skills, MCP servers, or plugins before deployment.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to check versions and gateway status, inspect configuration, scan components, review findings, and manage security settings and audit information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/automateyournetwork/netclaw/defenseclaw-ops
Install

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.

Any agent
npx skills add automateyournetwork/netclaw --skill defenseclaw-ops
Clone the repo
git clone --depth 1 https://github.com/automateyournetwork/netclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for defenseclaw-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/automateyournetwork/netclaw/defenseclaw-ops/github.svg)](https://agentmods.dev/skills/automateyournetwork/netclaw/defenseclaw-ops)
Your own site
<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/defenseclaw-ops"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/defenseclaw-ops/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.

agentmods 80×15 button for defenseclaw-ops

Your own site · 80×15
<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/defenseclaw-ops"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/defenseclaw-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01227
Opus 5 $0.00014 $0.00613
Sonnet 5 $0.00005 $0.00245
Haiku 4.5 $0.00003 $0.00123

Measured 10d ago against content hash fa11e5f979ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

defenseclaw-ops 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 10d 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.

workspace/skills/defenseclaw-ops/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DefenseClaw Operations

This skill manages DefenseClaw enterprise security for NetClaw deployments.

Overview

DefenseClaw from Cisco AI Defense provides enterprise-grade security:

  • OpenShell kernel-level sandbox
  • Component scanning (skills, MCPs, plugins)
  • Runtime guardrails (LLM inspection, tool call inspection)
  • Audit logging with SIEM integration

Prerequisites

  • DefenseClaw installed and enabled
  • defenseclaw CLI in PATH

Check status:

defenseclaw --version

Common Operations

Check Security Status

# View DefenseClaw version
defenseclaw --version

# Check gateway status
pgrep defenseclaw-gateway

# View current configuration
cat ~/.openclaw/config/openclaw.json | grep -A2 security

Scan Components

Before deploying new skills, MCPs, or plugins, scan them:

# Scan a skill
defenseclaw skill scan pyats-health-check

# Scan an MCP server
defenseclaw mcp scan meraki-mcp

# Scan a plugin
defenseclaw plugin scan custom-tool

Expected output for clean component:

Scanning skill: pyats-health-check
✓ No HIGH/CRITICAL findings
Status: ALLOWED

Expected output for blocked component:

Scanning skill: bad-skill
✗ HIGH: Hardcoded credential detected
  Location: config.py:15
Status: BLOCKED

Manage Tool Permissions

Block or allow specific tools:

# Block a destructive tool
defenseclaw tool block delete_file --reason "destructive operation"

# Block all write operations
defenseclaw tool block "*_write" --reason "read-only policy"

# Allow a previously blocked tool
defenseclaw tool allow delete_file

# List all tool rules
defenseclaw tool list

View Security Alerts

# View recent alerts
defenseclaw alerts

# View last 50 alerts
defenseclaw alerts --limit 50

# Filter by severity
defenseclaw alerts --severity HIGH

# Filter by date
defenseclaw alerts --after 2026-04-01

Export Audit Data

For compliance reporting:

# Export to JSON
defenseclaw alerts --export json > audit-$(date +%Y%m%d).json

# Export to CSV
defenseclaw alerts --export csv > audit-$(date +%Y%m%d).csv

Read the full file on GitHub · 226 lines

Changes

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.

  1. 10d ago First seen · 226 lines · 27 tokens per session scan A fa11e5f979ae

Subscribe to this mod's changes

defenseclaw-ops is a skill published in the GitHub repository automateyournetwork/netclaw (652 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,227 once invoked, about $0.0001 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.