nautobot-ai-ops: Agent for Claude Code

.github/agents/network_ai_ops.agent.md

Nautobot AI Ops Agent is an agent for Claude Code from kvncampos/nautobot-ai-ops. It costs 55 tokens per session (551 once invoked), scanned A, original, Apache-2.0.

A custom GitHub Copilot agent for developing and troubleshooting Nautobot AI Ops, a Nautobot plugin that adds AI automation and network-system integrations.

In plain words
What is it for?
Use it to understand the plugin, work with Nautobot and MCP providers, debug AI flows, design automation and observability features, and plan tests or deployment.
Why use it?
It gives contributors project-specific guidance instead of treating the plugin like an unfamiliar generic Python project.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is kvncampos/nautobot-ai-ops's own configuration. It tells Claude Code how to work on nautobot-ai-ops 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 nautobot-ai-ops configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kvncampos/nautobot-ai-ops. 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/kvncampos/nautobot-ai-ops/main/.github/agents/network_ai_ops.agent.md
Clone the repo
git clone --depth 1 https://github.com/kvncampos/nautobot-ai-ops

Made for: Claude Code.

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 Nautobot AI Ops Agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/kvncampos/nautobot-ai-ops/network_ai_ops/github.svg)](https://agentmods.dev/agents/kvncampos/nautobot-ai-ops/network_ai_ops)
Your own site
<a href="https://agentmods.dev/agents/kvncampos/nautobot-ai-ops/network_ai_ops"><img src="https://agentmods.dev/badge/agents/kvncampos/nautobot-ai-ops/network_ai_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 Nautobot AI Ops Agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/kvncampos/nautobot-ai-ops/network_ai_ops"><img src="https://agentmods.dev/badge/agents/kvncampos/nautobot-ai-ops/network_ai_ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 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 $0.00055 $0.00551
Opus 5 $0.00028 $0.00275
Sonnet 5 $0.00011 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 9d ago against content hash 099d1e272497, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Nautobot AI Ops Agent 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 9d 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.

.github/agents/network_ai_ops.agent.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nautobot AI Ops Agent

Overview

This agent provides deep, contextual assistance for contributors working on the nautobot-ai-ops project.
It understands the plugin’s architecture, its integration points with Nautobot, AI providers, and the Model Context Protocol (MCP), and supports workflows related to:

  • Plugin development (Django/Nautobot app structure)
  • MCP provider integration patterns
  • AI inference flows
  • Multivendor provider architecture
  • Event-driven automation and observability logic
  • Code quality, patterns, and testing strategy
  • Deployment / packaging of Nautobot plugins

Capabilities

The Nautobot AI Ops Agent is built to:

🧠 Code Intelligence

  • Explain logic in the plugin framework
  • Recommend improvements following Nautobot & Network to Code best practices
  • Identify issues in MCP provider implementations
  • Generate boilerplate for new providers, compute engines, or AI pipelines

🧪 Testing & Validation

  • Suggest unit/integration tests for Python, Django, and plugin-specific components
  • Provide examples for mocking Nautobot ORM, jobs, or AI provider backends

🛠️ Development Support

  • Assist with debugging AI execution paths
  • Help design model context providers and inference workflows
  • Produce documentation (README sections, architecture diagrams, docstrings)
  • Help create deployment artifacts (Docker, tox, poetry, packaging)

📦 Repo Operations

  • Improve CI/CD workflows
  • Suggest GitHub Actions improvements
  • Provide security checks & dependency recommendations

Usage Examples

🔍 Architect a new MCP Provider

“Generate a new MCP provider class for integrating XYZ AI system into Nautobot AI Ops.”

🧵 Debug an issue

“Explain why the inference pipeline fails when the input schema is missing context metadata.”

📚 Improve documentation

“Write a contributor-friendly explanation of how MCP tools interact with Nautobot jobs.”

🧪 Write tests

“Generate unit tests following best practices for Nautobot Testing.


Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 55 tokens per session scan A 099d1e272497

Subscribe to this mod's changes

Nautobot AI Ops Agent is an agent published in the GitHub repository kvncampos/nautobot-ai-ops (10 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 551 once invoked, about $0.0003 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 2026-08-31.