Microsoft 365 Agents SDK for JavaScript and TypeScript is a software development kit for building agents that handle conversations and requests across Microsoft 365, Teams, Copilot Studio, Webchat, and selected third-party messaging platforms. Developers use its packages to host agents, validate activity data, add channel features, and connect AI components.
Borrowing it
Nothing to install: this file belongs to microsoft/Agents-for-js. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/Agents-for-js/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/Agents-for-jsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/microsoft/agents-for-js/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/agents-for-js/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-js/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/agents-for-js/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-js/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.01444 | $0.01444 |
| Opus 5.5 | $0.00578 | $0.00578 |
| Sonnet 5.5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
Agents-for-js 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for microsoft/Agents-for-js
The Microsoft 365 Agents SDK for JavaScript/TypeScript (successor to BotFramework SDK v4) — a framework for building agents across M365, Teams, Copilot Studio, and Webchat. It is an npm-workspaces monorepo (packages/* and test-agents/*) using ES modules ("type": "module", module: node16) and TypeScript project references. Requires Node.js 22+ (development and CI use Node 24).
Commands
npm run quality # concise report for the complete standard validation suite
npm run quality -- --verbose # include the captured output of every check
npm run build # TypeScript 7 native build via scripts/tsc7.mjs and tsconfig.build.json
npm run build:clean # wipe dist/ then rebuild
npm test # all tests (node:test runner + tsx, emits test-report.xml)
npm run lint # eslint (neostandard config)
npm run lint:deps:ci # knip: unused files/exports/deps must be clean
npm run repo:doctor # repository structure, metadata, docs, and runtime drift
npm run compat # api-extractor public-API compatibility check
npm run build:samples # build the test-agents
Run a single test (the runner is node:test with tsx, not jest/mocha):
node --test --import tsx packages/agents-activity/test/exceptionHelper.test.ts # one file
node --test --import tsx 'packages/agents-hosting/test/**/*.test.ts' # one package
Run npm run repo:doctor after structural, package, documentation, build-reference, dependency, API-baseline, test-agent, Docker, or runtime-configuration changes. Its ESLint-style diagnostics include stable rule IDs and concrete fix instructions for agents and humans.
Do not add npm pre* / post* lifecycle wrappers or install-time hooks (preinstall, install, postinstall, prepare). npm --ignore-scripts skips those hooks; make required script dependencies explicit in the invoked command.
CI (.github/workflows/ci.yml) runs npm run quality, which performs repo:doctor → lint → lint:deps:ci → build → test → (compat and build:samples). It folds each command log in the GitHub Actions output and uploads a seven-day quality-logs artifact. Match this before assuming work is done.
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.
- 1mo ago Changed · -11 tokens per session 7721f4094623
- 1mo ago Changed · +2 lines · +55 tokens per session 3a73287d209b
- 2mo ago First seen · 58 lines · 1,400 tokens per session scan A abffa2d55f4c
Agents-for-js copilot-instructions.md is an instructions file published in the GitHub repository microsoft/Agents-for-js (92 stars, last pushed yesterday), licensed MIT. It adds 1,444 tokens to every session, about $0.0058 per session on Opus 5.5. 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.
Agents-for-js copilot-instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Agents-for-js copilot-instructions.mdmicrosoft/Agents-for-js | Instructions file | 92 | yesterday | MIT | A | 1,444 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |