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.
npx agentmods add instructions/charris-msft/azure-plugin/claude-mdgit clone --depth 1 https://github.com/charris-msft/azure-pluginWrote 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/instructions/charris-msft/azure-plugin/claude-md)<a href="https://agentmods.dev/instructions/charris-msft/azure-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/charris-msft/azure-plugin/claude-md.svg" alt="Measured on agentmods" 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 | $0.02429 | $0.02429 |
| Opus 5 | $0.01215 | $0.01215 |
| Sonnet 5 | $0.00486 | $0.00486 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade B, and why
azure-plugin CLAUDE.md scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Linux:** `sudo systemctl start docker` 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.
Azure MCP Plugin Development Guidelines
⚠️ CRITICAL: Docker Daemon Errors - Auto-Start Required
When ANY Docker error occurs (daemon not running, cannot connect, etc.), you MUST:
- DO NOT just tell the user to start Docker manually
- DO ask: "Docker isn't running. Would you like me to start Docker Desktop for you?"
- If yes, run the appropriate command:
- Windows:
"/c/Program Files/Docker/Docker/Docker Desktop.exe" & - macOS:
open -a Docker - Linux:
sudo systemctl start docker
- Windows:
- Wait for Docker to be ready (30-60 seconds):
for i in {1..30}; do docker info >/dev/null 2>&1 && echo "Docker is ready!" && break; sleep 2; done - Retry the original command automatically
Error patterns to detect:
docker daemon is not runningCannot connect to the Docker daemonfailed to connect to the docker APIThe system cannot find the file specified(Docker pipe error)Is the docker daemon running?
azd Commands - ALWAYS Use Non-Interactive Mode
CRITICAL: azd commands MUST be run non-interactively. Claude cannot provide interactive input.
Before ANY azd command:
- Create environment first:
azd env new <env-name> --no-prompt - Set required values:
azd env set AZURE_SUBSCRIPTION_ID "<subscription-id>" azd env set AZURE_LOCATION "<location>" - Always use
--no-prompt: All azd commands should include--no-prompt
Correct patterns:
# Initialize with environment name
azd init --environment my-app-dev --no-prompt
# Or create environment separately first
azd env new my-app-dev --no-prompt
azd env set AZURE_SUBSCRIPTION_ID "xxxx-xxxx-xxxx"
azd env set AZURE_LOCATION "eastus2"
# Then provision/deploy
azd up --no-prompt
azd provision --no-prompt
azd deploy --no-prompt
NEVER run these without --no-prompt or pre-configured environment:
azd init(prompts for environment name)azd up(prompts for environment, subscription, location)azd provision(prompts for subscription)
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.
- 4d ago First seen · 239 lines · 2,429 tokens per session scan B 65a641d59309
azure-plugin CLAUDE.md is an instructions file published in the GitHub repository charris-msft/azure-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 2,429 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
timoni AGENTS.md
AGENTS.md instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).
aks-mcp copilot-instructions.md
Instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
serverless-litellm CLAUDE.md
Instructions for cncoder/serverless-litellm, covering claude.md — litellm on eks 项目指南, 项目概述, 快速部署(一键), 前置条件 and 部署流程.
tasks CLAUDE.md
Instructions for andrewrothstein/tasks, covering claude.md, repository organization, cluster lifecycle management (ephemeral clusters), application deployment (cluster-agnostic) and essential commands.
openclaw-kubernetes AGENTS.md
Instructions for feiskyer/openclaw-kubernetes, covering agents.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).
tor-mcp CLAUDE.md
Claude Code instructions for globalion/tor-mcp, covering deploying tor-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy, first-time subdomain wiring and env vars.