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/matsest/lazyazure/agents-mdgit clone --depth 1 https://github.com/matsest/lazyazureWrote 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/matsest/lazyazure/agents-md)<a href="https://agentmods.dev/instructions/matsest/lazyazure/agents-md"><img src="https://agentmods.dev/badge/instructions/matsest/lazyazure/agents-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 | $0.09566 | $0.09566 |
| Opus 5 | $0.04783 | $0.04783 |
| Sonnet 5 | $0.01913 | $0.01913 |
| Haiku 4.5 | $0.00957 | $0.00957 |
Grade A, and why
lazyazure 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 5d 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 — 1,033 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LazyAzure - Agent Guidelines
This document provides guidelines and lessons learned for agents working on the LazyAzure codebase.
Project Overview
LazyAzure is a TUI (Terminal User Interface) application for Azure resource management, inspired by lazydocker. It uses:
- gocui for the terminal interface
- Azure SDK for Go for Azure API interactions
- DefaultAzureCredential for authentication (supports multiple auth methods)
Critical Guidelines
1. TUI Development with gocui
Event Loop and Threading
- CRITICAL: Never hold locks (mutex) when calling gocui operations
- CRITICAL: Never call
gui.g.Update()orgui.g.UpdateAsync()while holding a lock - Use
go func()for async operations, then usegui.g.UpdateAsync()for UI updates UpdateAsync()is safer thanUpdate()as it doesn't spawn a goroutine
Cursor Handling
- Use
v.SetCursor(x, y)directly instead ofv.TextArea.MoveCursorDown/Up - Get cursor position with
v.Cursor()which returns (x, y) - Don't mix cursor tracking with origin/offset calculations unless necessary
View Management
- Use
gocui.IsUnknownView(err)to check if a view already exists - Views are identified by string names (e.g., "subscriptions", "resourcegroups")
- Set current view with
gui.g.SetCurrentView("viewname")
2. Mutex Best Practices
Deadlock Prevention
// ❌ WRONG: Holding lock while calling another function that needs lock
func (gui *Gui) nextLine() {
gui.mu.Lock()
defer gui.mu.Unlock()
gui.selectItem() // selectItem() also needs Lock = DEADLOCK!
}
// ✅ CORRECT: Release lock before calling other methods
func (gui *Gui) nextLine() {
gui.mu.RLock()
count := len(gui.items)
gui.mu.RUnlock()
// ... do work ...
gui.selectItem() // Now safe to acquire Lock
}
Lock Hierarchy
RLock()for reading data length/slices- Do work without locks
Lock()only for updating state- Never hold locks during I/O or UI operations
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.
- 5d ago First seen · 1,033 lines · 9,566 tokens per session scan A dd5d5cec27a9
lazyazure AGENTS.md is an instructions file published in the GitHub repository matsest/lazyazure (46 stars, last pushed 4d ago), licensed MIT. It adds 9,566 tokens to every session, about $0.0478 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 2026-08-30.
Other instructions, from other repositories
azure-search-openai-demo bicep.instructions.md
Infrastructure as Code with Bicep.
waveloom AGENTS.md
AGENTS.md instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.
unifly AGENTS.md
Instructions for hyperb1iss/unifly, covering agents.md, what this repository is, quick command reference, the canonical "before commit" gate and individual gates.
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.
apex-accelerator governance-discovery.instructions.md
MANDATORY Azure Policy discovery requirements for governance constraints.
r3bl-open-core AGENTS.md
AGENTS.md instructions for r3bl-org/r3bl-open-core, covering agent instructions for r3bl-open-core, ai agent security & system integrity mandates, 1. critical directory protection, 2. ownership & integrity and 3. execution safety.