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/skills/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/skillsWhat 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 | $0.02575 | $0.02575 |
| Opus 5 | $0.01288 | $0.01288 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
skills 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 2d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for Agent Skills
Project Overview
Agent Skills is a repository of skills, prompts, and MCP configurations for AI coding agents working with Azure SDKs and Microsoft AI Foundry services.
⚠️ Fresh Information First
Azure SDKs and Foundry APIs change constantly. Never work with stale knowledge.
Before implementing anything with Azure/Foundry SDKs:
- Search official docs first — Use the Microsoft Docs MCP (
microsoft-docs) to get current API signatures, parameters, and patterns - Verify SDK versions — Check
pip show <package>for installed versions; APIs differ between versions - Don't trust cached knowledge — Your training data is outdated. The SDK you "know" may have breaking changes.
If you skip this step and use outdated patterns, you will produce broken code.
Core Principles
Apply these principles to every task.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them — don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- If you write 200 lines and it could be 50, rewrite it.
The test: Would a senior engineer say this is overcomplicated? If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it — don't delete it.
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
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.
- 2d ago First seen · 306 lines · 2,575 tokens per session scan A 80f69f465c39
skills copilot-instructions.md is an instructions file published in the GitHub repository microsoft/skills (2,979 stars, last pushed today), licensed MIT. It adds 2,575 tokens to every session, about $0.0129 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
ApplicationInsights-dotnet AGENTS.md
Instructions for microsoft/ApplicationInsights-dotnet, covering agents.md, repository structure, build & test, ai-assisted instrumentation skills and what it does.
azure-dev documentation.instructions.md
Instructions for Azure/azure-dev, covering documentation maintenance, documentation structure, when to update documentation, documentation placement guide and documentation standards.
azure-ai-travel-agents AGENTS.md
Instructions for Azure-Samples/azure-ai-travel-agents, covering azure ai travel agents - developer guide, project structure & architecture, high-level architecture, ai agent specialization and service communication.
AI-Gateway AGENTS.md
Instructions for Azure-Samples/AI-Gateway, covering agents.md, directory structure, labs/, modules/ and shared/.
azure-dev extensions.instructions.md
Instructions for Azure/azure-dev, a project described as: A developer CLI for working with Azure resources to build and deploy AI applications. Commands map to key workflow stages: code, build, deploy, and monitor.
azure-dev go.instructions.md
Instructions for Azure/azure-dev, covering modern go (1.26+) — pr review guidelines, new(expr) creates typed pointers from values, other modern patterns to accept (not flag), review the full file, not just the diff and cli behavior and domain filtering.