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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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/commands/hermeticormus/libresecops-claude-code/network-audit)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/network-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/network-audit/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/commands/hermeticormus/libresecops-claude-code/network-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/network-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.01086 |
| Opus 5.5 | $0.00010 | $0.00434 |
| Sonnet 5.5 | $0.00005 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
network-audit 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/network-audit
Structured audit of network configuration covering firewalls, segmentation, exposure, and monitoring.
Trigger
Use when you need to:
- Review firewall rules (iptables, nftables, cloud security groups) for security
- Assess network segmentation and lateral movement risk
- Identify unnecessary network exposure
- Audit VPN or tunnel configurations
- Evaluate network monitoring and IDS/IPS coverage
Input
One or more of:
- Firewall rules:
iptables-saveoutput,nft list rulesetoutput, cloud security group exports - Network diagram: Topology showing segments, trust zones, and traffic flows
- Live system access: SSH access to hosts for
ss,iptables-save,ip routeinspection - Cloud configuration: Terraform files defining security groups/NSGs/firewall rules
- Specific scope: Focus area (e.g., "DMZ security", "internal segmentation", "VPN config")
Process
Phase 1: Topology & Exposure
-
External attack surface
- Internet-facing IP addresses and services
- Open ports visible from the internet (authorized scan or cloud config review)
- Services that should NOT be internet-facing (databases, admin panels, monitoring)
- Management interfaces (SSH, RDP) accessible from internet
-
Network segments
- Identified trust zones (public, DMZ, internal, management, database)
- Inter-zone firewall rules
- Flat network segments (no internal firewalling)
- VLAN configuration and trunk security
Phase 2: Firewall Rules
-
Rule assessment
- Default policy (ACCEPT is a critical finding for INPUT/FORWARD chains)
- Rules allowing
0.0.0.0/0ingress (any source) - Rules allowing broad port ranges or
anyport - Rules with no logging
- Orphaned rules (reference dead IPs or decommissioned services)
- Rule ordering (iptables processes sequentially -- early broad allows bypass later specific denies)
-
Egress filtering
- Outbound traffic restrictions (default allow outbound is common and dangerous)
- Permitted outbound ports (HTTP/HTTPS/DNS are common, but should be the only allowed)
- Data exfiltration paths (can internal hosts send arbitrary traffic outbound?)
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.
- 12d ago Changed · +5 lines · +25 tokens per session e63515d22a17
- 1mo ago First seen · 137 lines · 0 tokens per session scan A fec83ee7636d
network-audit is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 1,086 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
get-organization-inventory-devices
Call the get-organization-inventory-devices tool from meraki-dashboard-api.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.