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/microsoft/aks-lab-githubcopilot/agents-mdgit clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilotWhat 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 | $0.01718 | $0.01718 |
| Opus 5 | $0.00859 | $0.00859 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
AKS-Lab-GitHubCopilot 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — House rules for AI coding agents
Inspired by
microsoft/agent-framework/python/AGENTS.md. Read this before you write any code in this repo — whether you are a human, GitHub Copilot, or the Copilot Coding Agent.
1. Project Context
This repository implements ZavaShop, a multi-agent retail supply-chain demo. It runs on AKS (long-lived orchestrator) and Azure Container Apps (event-driven specialist agents). Agents are built with Microsoft Agent Framework (MAF) and the GitHub Copilot SDK Python provider.
Treat every change as production-style: typed, tested, observable.
1.1 How we build: GitHub Copilot Custom Agents
This repo is delivered through GitHub Copilot Custom Agents. Every code change flows through one of the six agents below. Each agent owns a slice of the repo and has its own tools, skills, and refusal rules. Invoke an agent by typing /<name> in Copilot Chat.
| Phase | Agent | Owns | File |
|---|---|---|---|
| Requirements | requirements-analyst |
specs/*.md |
.github/agents/requirements-analyst.agent.md |
| MCP impl | mcp-builder |
src/mcp_servers/* |
.github/agents/mcp-builder.agent.md |
| Agent impl | agent-builder |
src/agents/<specialist>/* |
.github/agents/agent-builder.agent.md |
| Orchestration | orchestrator-architect |
src/agents/orchestrator/*, src/shared/*, docker-compose.yml |
.github/agents/orchestrator-architect.agent.md |
| Tests | test-author |
tests/** |
.github/agents/test-author.agent.md |
| Deploy | deploy-engineer |
infra/**, .github/workflows/** |
.github/agents/deploy-engineer.agent.md |
Workflow prompts that chain the agents live in .github/prompts/:
feature-from-issue.prompt.md— issue → spec → code → tests → PR → deploy.spec-to-code.prompt.md— drive an existing spec through code + tests.ship-it.prompt.md— roll the current SHA to ACR + ACA + AKS.
Shared, agent-agnostic knowledge lives in .github/skills/<skill>/SKILL.md (inspired by the agent-framework Python skills layout). Every agent lists which skills it must consult before writing code.
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.
- yesterday First seen · 104 lines · 1,718 tokens per session scan A 11ff0182bc24
AKS-Lab-GitHubCopilot AGENTS.md is an instructions file published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It adds 1,718 tokens to every session, about $0.0086 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.