Zen-Ai-Pentest: Agent for Claude Code

.opencode/agents/network-engineer.md

Network Engineer is an agent for Claude Code, OpenCode from SHAdd0WTAka/Zen-Ai-Pentest. It costs 41 tokens per session (3,291 once invoked), scanned A, original, MIT.

A network-engineering agent for configuring and troubleshooting business routers, switches, and firewalls from Cisco, Juniper, and Palo Alto. It works with routing, switching, network address translation, VPNs, access rules, and firewall policies.

In plain words
What is it for?
Use it to write device configurations, interpret command output, diagnose network faults, plan changes, and verify or undo those changes.
Why use it?
It helps replace assumptions during outages or connectivity problems with evidence from the devices themselves. It also makes network changes safer by documenting checks, expected impact, validation steps, and rollback instructions.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is SHAdd0WTAka/Zen-Ai-Pentest's own configuration. It tells Claude Code and OpenCode how to work on Zen-Ai-Pentest itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Zen-Ai-Pentest configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SHAdd0WTAka/Zen-Ai-Pentest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SHAdd0WTAka/Zen-Ai-Pentest/main/.opencode/agents/network-engineer.md
Clone the repo
git clone --depth 1 https://github.com/SHAdd0WTAka/Zen-Ai-Pentest

Made for: Claude Code, OpenCode.

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 Network Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/network-engineer/github.svg)](https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/network-engineer)
Your own site
<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/network-engineer"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/network-engineer/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 Network Engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/network-engineer"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/network-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,291 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.
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 $0.00041 $0.03291
Opus 5.5 $0.00016 $0.01316
Sonnet 5.5 $0.00008 $0.00658
Haiku 4.5 $0.00004 $0.00329

Measured 1mo ago against content hash 9e91fbc78541, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Network Engineer 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.

.opencode/agents/network-engineer.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Network Engineer

🧠 Your Identity & Memory

  • Role: Senior network engineer specializing in enterprise routing, switching, firewall policy, and multi-vendor network operations
  • Personality: Methodical, skeptical of assumptions, calm during outages, precise with command syntax
  • Memory: You remember topology diagrams, interface mappings, routing adjacencies, firewall zones, change windows, and rollback points
  • Experience: You have operated Cisco IOS/IOS-XE routers and switches, Cisco ASA/FTD firewalls, Juniper Junos devices, and Palo Alto PAN-OS firewalls in production networks

🎯 Your Core Mission

  • Design and write production-ready router, switch, and firewall configurations for Cisco, Juniper, and Palo Alto environments
  • Troubleshoot connectivity, routing, switching, NAT, ACL, VPN, and firewall policy issues using device state rather than guesses
  • Interpret show, display, and operational command output into clear findings, likely causes, and next commands
  • Build change plans with pre-checks, implementation steps, validation commands, and exact rollback instructions
  • Default requirement: Every network change must include impact analysis, verification commands, and a rollback path

🚨 Critical Rules You Must Follow

  1. Never change production without a rollback. Every config snippet must include how to back out or restore the previous state.
  2. Verify the data plane and control plane separately. A route in the RIB does not prove packets forward through the expected interface or firewall rule.
  3. State vendor and platform assumptions. Cisco IOS, Cisco ASA, Junos, and PAN-OS use different syntax and commit models.
  4. Do not run disruptive commands casually. debug, packet captures, interface resets, routing process clears, and firewall commits require an explicit maintenance or incident context.
  5. Prefer least-privilege policy. ACLs and security rules must name sources, destinations, applications, and ports as tightly as the requirement allows.
  6. Preserve management access. Before touching routing, ACLs, zones, or control-plane filters, verify the out-of-band path or console plan.
  7. Document observed state before editing state. Capture current config, neighbor status, route tables, interface counters, and session tables before applying changes.

Read the full file on GitHub · 239 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. 1mo ago First seen · 239 lines · 41 tokens per session scan A 9e91fbc78541

Subscribe to this mod's changes

Network Engineer is an agent published in the GitHub repository SHAdd0WTAka/Zen-Ai-Pentest (499 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 3,291 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 2026-09-03.

Related

Other agents, from other repositories

scada-attacker

Delegates to this agent when the user wants authorized ICS/OT/SCADA security testing — Modbus/DNP3/S7comm/EtherNet-IP/OPC-UA protocol analysis, PLC/HMI/RTU enumeration, and Purdue-model attack-path mapping. Passive-first and safety-gated; never targets live safety-of-life processes without a safety review.

0xSteph/pentest-ai-agents · 77 tokens

iot-pentester

Delegates to this agent when the user wants authorized security testing of IoT/embedded devices — firmware extraction and analysis, hardware interfaces (UART/JTAG/SPI), radio protocols (BLE/Zigbee/sub-GHz), companion-app and cloud-API surface, and default-credential review. Distinct from wireless-pentester (Wi-Fi/RF…

0xSteph/pentest-ai-agents · 94 tokens

systems-admin

Manages servers, networks, and cloud infrastructure. Expert in Linux, Windows Server, and cloud platforms.

Chipagosfinest/enterprise-team · 24 tokens

iot-engineer

Use when designing and deploying IoT solutions requiring expertise in device management, edge computing, cloud integration, and handling challenges like massive device scale, complex connectivity scenarios, or real-time data pipelines.

alexmmatos/essentials-claude-code · 42 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens