wan-automation-examples AGENTS.md

wan-automation-examples AGENTS.md is an instructions file for Codex, OpenCode from CiscoDevNet/wan-automation-examples. It costs 1,874 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for coding agents working with Cisco network-automation examples. It covers examples for Cisco Catalyst SD-WAN Manager and Meraki Dashboard using Python, Bruno, Terraform, and an MCP server.

In plain words
What is it for?
Use it when modifying or adding network-automation examples, especially Python, Bruno, Terraform, or MCP work for Cisco Catalyst SD-WAN or Meraki Dashboard.
Why use it?
It helps keep changes in the correct folders and aligned with the repository’s lab-focused purpose. It also points agents to the relevant documentation before editing examples.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/ciscodevnet/wan-automation-examples/agents-md
Clone the repo
git clone --depth 1 https://github.com/CiscoDevNet/wan-automation-examples

Made for: Codex, 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 wan-automation-examples AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ciscodevnet/wan-automation-examples/agents-md.svg)](https://agentmods.dev/instructions/ciscodevnet/wan-automation-examples/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ciscodevnet/wan-automation-examples/agents-md"><img src="https://agentmods.dev/badge/instructions/ciscodevnet/wan-automation-examples/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,874 This file is loaded in full into every session.
When invoked 1,874 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01874 $0.01874
Opus 5 $0.00937 $0.00937
Sonnet 5 $0.00375 $0.00375
Haiku 4.5 $0.00187 $0.00187

Measured 3d ago against content hash 5239a6b410d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wan-automation-examples AGENTS.md 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 3d 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.

AGENTS.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidance for Coding Agents

Purpose and Scope

This repository contains learning and demonstration examples for automating:

  • Cisco Catalyst SD-WAN Manager with Python, Bruno, Terraform, and an MCP server.
  • Cisco Meraki Dashboard with Python, Bruno, and Terraform.

The examples are not production-supported SDKs or applications. Keep changes small, readable, safe for lab use, and focused on a practical automation task. Read the nearest area-specific README.md before modifying an example.

Repository Layout

catalystwan/
├── bruno/       Current Catalyst SD-WAN Bruno collection
├── lab/         Archived Python scripts retained for older Cisco documentation
├── mcp-sdwan/   Podman-based Catalyst SD-WAN MCP server
├── python/      Maintained Catalyst SD-WAN Python examples
└── terraform/   Provider and NetAsCode module examples
meraki/
├── bruno/       Meraki Dashboard Bruno collection
├── python/      Meraki Python examples
└── terraform/   Provider and NetAsCode module examples
scripts/         Contribution helpers

Keep examples with their architecture: Catalyst SD-WAN changes belong under catalystwan/; Meraki changes belong under meraki/. Bruno collections stay beside the Python and Terraform examples for the same platform.

Do not add a general documentation tree. Guided Cisco Catalyst SD-WAN lessons, API concepts, and hands-on labs belong in the external Catalyst SD-WAN API Learning Hub. The URL is provisional and may be updated when an official URL is available.

Authoritative Documentation

Use primary documentation and verify current API paths, schemas, and product version compatibility before adding or changing requests:

Read the full file on GitHub · 182 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. 3d ago First seen · 182 lines · 1,874 tokens per session scan A 5239a6b410d5

Subscribe to this mod's changes

wan-automation-examples AGENTS.md is an instructions file published in the GitHub repository CiscoDevNet/wan-automation-examples (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 1,874 tokens to every session, about $0.0094 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.