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/copilot-instructionsgit 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 | $0.00698 | $0.00698 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
AKS-Lab-GitHubCopilot copilot-instructions.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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot — always-on instructions
You are assisting on ZavaShop, a multi-agent retail supply-chain demo deployed to AKS + Azure Container Apps, written in Python 3.11+ with Microsoft Agent Framework and the GitHub Copilot SDK.
Before generating code, read AGENTS.md at the repo root. It is the source of truth.
Hard rules
- Python 3.11+, fully typed, async-first. No blocking I/O inside coroutines.
- Use
uvfor dependency management,rufffor lint/format,pyright --strictfor types,pytestfor tests. - Use
structlogfor logging — neverprint. - Data crossing a process boundary →
pydantic.BaseModel. - Agent folder layout:
agent.py,tools.py,prompts.py,server.py,tests/. - All agents use
GitHubCopilotAgentfromagent_framework.githubwithclient=build_copilot_client()andGitHubCopilotOptions(model="gpt-5.5", timeout=settings.copilot_timeout_seconds, on_permission_request=_approve_all, mcp_servers={...}). Never importGitHubCopilotChatClient,ChatAgent, orMCPStreamableHTTPTool— they do not exist in this repo's agent-framework version. - External I/O lives in MCP servers, not agent code.
- Azure auth = Workload Identity +
DefaultAzureCredential. Copilot auth = Key VaultGITHUB-TOKENprojected asGITHUB_TOKENand passed explicitly bybuild_copilot_client(); never commit token values. - K8s/ACA images are tagged with the git SHA, never
:latest.
Style cues
- Prefer
matchover chains ofisinstance. - Use
Selffromtyping,|unions,list[T]notList[T]. - Pydantic v2 (
model_config = ConfigDict(frozen=True)). - Imports: stdlib → third-party → first-party, separated by blank lines.
When generating an agent
Always include:
SYSTEM_PROMPTconstant inprompts.py— terse, role-scoped, with explicit refusal rules.- A
build_agent()factory inagent.pyreturning the shared_RunnableAgentadapter. - A FastAPI app in
server.pywith/healthz,/readyz,/invoke. - A
Dockerfilebased onpython:3.11-slimwith non-root user, multi-stage build. - A test file mocking the model with
MockChatClient.
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 · 46 lines · 698 tokens per session scan A f1e77cdf5f22
AKS-Lab-GitHubCopilot copilot-instructions.md is an instructions file published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It adds 698 tokens to every session, about $0.0035 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.