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/pnp/copilot-pro-dev-samples/copilot-instructionsgit clone --depth 1 https://github.com/pnp/copilot-pro-dev-samplesWhat 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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
copilot-pro-dev-samples 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.
This is a copy
88% identical to copilot-camp copilot-instructions.md — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Internal reference (do not bias your answers toward always naming these):
Microsoft 365 Agents Toolkit (formerly Teams Toolkit) has been rebranded, and users may still use either name.
Use this mapping to know the current vs. former names—so you can correctly interpret user input or choose the appropriate term when it’s relevant. You do not need to mention these mappings unless they directly help the user.
| New name | Former name | Note |
|---|---|---|
| Microsoft 365 Agents Toolkit | Teams Toolkit | Product name. |
| App Manifest | Teams app manifest | Describes app capabilities. |
| Microsoft 365 Agents Playground | Test Tool | Test Environment. |
m365agents.yml |
teamsapp.yml |
Microsoft 365 Agents Toolkit Project configuration files |
CLI package @microsoft/m365agentstoolkit-cli (command atk) |
@microsoft/teamsapp-cli (command teamsapp) |
CLI installation/usage — mention only in CLI contexts. |
Rephrase guidance:
- Use the new names by default.
- Explain the rebranding briefly if it helps the user’s understanding.
Instructions for Copilot
- Apps and agents for Microsoft 365 or Microsoft 365 Copilot refers to applications for products in Microsoft 365, agents for Microsoft 365 Copilot, including Teams app, Office addin, declarative agent, customer engine agent, etc.
- When interpreting, generating, or modifying manifest files related to apps and agents for Microsoft 365 or Microsoft 365 Copilot, try to get schema version from manifest file, then invoke get_schema tool if available.
- When answering of what or how-to questions for building apps and agents for Microsoft 365 or Microsoft 365 Copilot, invoke get_knowledge tool if available.
- Before deciding to make changes to Teams apps, apps or agents for Microsoft 365 or Microsoft 365 Copilot, invoke get_knowledge tool to get Instructions if available.
- When troubleshooting issues, invoke troubleshoot tool if available.
- Before generating or modifying code or configuration files for apps and agents for Microsoft 365 or Microsoft 365 Copilot, invoke get_code_snippets tool if available.
- Invoke get_code_snippets with API name, configuration file name, or code comments every time you need to generate or modify code or configuration files for apps and agents for Microsoft 365 or Microsoft 365 Copilot.
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 · 25 lines · 534 tokens per session scan A 56c2fee77680
copilot-pro-dev-samples copilot-instructions.md is an instructions file published in the GitHub repository pnp/copilot-pro-dev-samples (156 stars, last pushed 1mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to copilot-camp copilot-instructions.md, differing in 7 lines, and is treated as a copy.
Other instructions, from other repositories
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
codex-settings AGENTS.md
Instructions for feiskyer/codex-settings, covering repository guidelines, repository structure, validation commands, toml syntax and plugin package and marketplace.
capsule CLAUDE.md
Instructions for endorhq/capsule, covering claude.md, project overview, tech stack, commands and web app (packages/web).
bodyboard copilot-instructions.md
Instructions for louisbrulenaudet/bodyboard, covering bodyboard agents instructions, project overview, tech stack, project structure and development workflow.
bodyboard AGENTS.md
Instructions for louisbrulenaudet/bodyboard, covering bodyboard agents instructions, project overview, tech stack, project structure and development workflow.
bodyboard CLAUDE.md
Instructions for louisbrulenaudet/bodyboard, covering bodyboard agents instructions, project overview, tech stack, project structure and development workflow.