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/agent365-devtools/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/Agent365-devToolsWhat 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 | $0.03398 | $0.03398 |
| Opus 5 | $0.01699 | $0.01699 |
| Sonnet 5 | $0.00680 | $0.00680 |
| Haiku 4.5 | $0.00340 | $0.00340 |
Grade A, and why
Agent365-devTools 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for Agent365-devTools
Agent365 CLI Development Guidelines
Engineering Principles
- Follow KISS, DRY, SOLID, and YAGNI principles
- Align CLI patterns with Azure CLI (
az) conventions - Keep changes minimal and focused on the problem at hand
- Reuse existing functions across commands; avoid duplication
- Critically review all changes before committing
Code Organization
- Keep files small and focused
- Use constants for strings and values (see
Constants/folder) - Use
ErrorCodes.csandErrorMessages.csfor error handling
File Organization Guidelines
Multiple Classes Per File - Allowed Cases
- Model/DTO files: Related model classes, records, or structs can be grouped in a single file
- Request/Response pairs: API request and response classes for the same endpoint
- Small supporting types: Enums, small records, or helper classes closely tied to a main class
- Nested or related interfaces: Interface and its related types
When to Separate
- Large classes with significant logic
- Classes that could be reused independently
- Classes with different lifecycle or ownership
Cross-Platform Compatibility
- All code must work on Windows, macOS, and Linux
- Test file paths, line endings, and shell commands for compatibility
Testing Standards
- Use xUnit, FluentAssertions, and NSubstitute
- Focus on quality over quantity of tests
- Add regression tests for bug fixes
- Tests should verify CLI reliability
- Tests must assert requirements, not implementation — when a test is changed to match new code behavior (rather than to reflect a changed requirement), that is a red flag. A test that silently tracks whatever the code does provides no regression protection. If a test needs to be updated, explicitly document the requirement the new assertion encodes (use
because:in FluentAssertions). If you cannot articulate a requirement reason, the test change should be questioned. - FluentAssertions
because:is mandatory for non-obvious assertions — any assertion on a URL structure, encoding format, security-sensitive behavior, or protocol requirement must include abecause:clause explaining the invariant being enforced. - Dispose IDisposable objects properly:
HttpResponseMessageobjects created in tests must be disposed- Even in mock/test handlers, follow proper disposal patterns
- Consider using
usingstatements or ensure test handlers dispose responses - This applies to all
IDisposabletest objects to avoid analyzer warnings
- Disable parallel execution for tests with shared state:
- Tests that modify environment variables must disable parallelization
- Tests that access shared file system resources must run sequentially
- Use
[CollectionDefinition("TestName", DisableParallelization = true)]pattern - Add
[Collection("TestName")]attribute to test class - Pattern to follow:
/// <summary> /// Tests must run sequentially because they modify environment variables. /// </summary> [CollectionDefinition("EnvTests", DisableParallelization = true)] public class EnvTestCollection { } [Collection("EnvTests")] public class MyTests { [Fact] public void Test_ModifiesEnvironmentVariable() { Environment.SetEnvironmentVariable("VAR", "value"); try { // Test logic } finally { Environment.SetEnvironmentVariable("VAR", null); } } }
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 · 291 lines · 3,398 tokens per session scan A 15517903e5bc
Agent365-devTools copilot-instructions.md is an instructions file published in the GitHub repository microsoft/Agent365-devTools (61 stars, last pushed 5d ago), licensed MIT. It adds 3,398 tokens to every session, about $0.0170 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
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.