Intelligent Terminal is an experimental fork of Windows Terminal that adds native support for AI agents through the Agent Client Protocol. It is for Windows users who want to manage compatible agent command-line tools alongside terminal tabs, profiles, themes, shells, and keyboard shortcuts, and the catalogue entries provide instructions, skills, hooks, and a plugin for working with it.
Borrowing it
Nothing to install: this file belongs to microsoft/intelligent-terminal. 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/intelligent-terminal/main/AGENTS.mdgit clone --depth 1 https://github.com/microsoft/intelligent-terminalWrote 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/intelligent-terminal/agents-md)<a href="https://agentmods.dev/instructions/microsoft/intelligent-terminal/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/intelligent-terminal/agents-md/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/intelligent-terminal/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/intelligent-terminal/agents-md.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 | $0.02026 | $0.02026 |
| Opus 5.5 | $0.00810 | $0.00810 |
| Sonnet 5.5 | $0.00405 | $0.00405 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
intelligent-terminal AGENTS.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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intelligent Terminal
Intelligent Terminal is a Windows Terminal fork that adds first-class AI agent
workflows. The inherited Windows Terminal build, architecture, and C++ conventions
are documented in .github/copilot-instructions.md; this file contains only the
fork-specific context.
Architecture
WindowsTerminal.exe
|-- TerminalProtocolComServer (COM, discovered through WT_COM_CLSID)
|-- SharedWta --> wta-master --> agent CLI pool (ACP over stdio)
+-- one wta-helper pane per tab
|
+-- helper/master ACP over a named pipe
+-- session-scoped MCP tools
Agent or human CLI --> wta/wtcli --> COM IProtocolServer --> Windows Terminal
- WTA (
tools/wta/) is the Rust orchestrator. - ACP means Agent Client Protocol.
wta-masterowns a pool of agent CLI processes keyed by agent identity, execution source, and command; helpers using the same key share one process and multiplex sessions through it. Installed, policy-allowed native host agents other than Gemini and Antigravity initialize in the background at master startup and remain resident. Gemini and Antigravity are excluded from automatic sidebar discovery; explicit selections initialize on demand. - WT Protocol is the terminal-control boundary.
wtcli.exeactivatesIProtocolServerthrough the package COM registration. - Session MCP exposes
run_command_in_current_shell,create_workspace,delegate_task_in_new_workspace, andrequest_user_input. It routes requests to the owning helper and never executes terminal actions itself. - Agent panes are ordinary
ConptyConnectionpanes hostingwta-helper; C++ does not speak ACP.
See doc/specs/Multi-window-agent-pane.md for the detailed lifecycle and
tools/wta/AGENTS.md for WTA-specific implementation rules.
Supported agents and settings
Built-in ACP and delegation providers are Copilot, Claude, Codex, Gemini, and
OpenCode. Custom providers use a custom:<name> ID plus the matching custom
command setting.
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.
- 3d ago Changed · +5 tokens per session fb942747cda0
- 12d ago Changed · +7 lines · +89 tokens per session 805851b90ad7
- 13d ago Changed · +1 lines · +15 tokens per session 5576fe4e689d
- 23d ago Changed · +2 lines · +18 tokens per session b4351c20f8c5
- 24d ago Changed · +2 lines · +26 tokens per session e792d89489ff
- 1mo ago Changed · +6 lines · +96 tokens per session bffa03a45a1b
- 1mo ago Changed · +4 tokens per session 58d406cc9eec
- 1mo ago First seen · 185 lines · 1,773 tokens per session scan A 4c056a72d19a
intelligent-terminal AGENTS.md is an instructions file published in the GitHub repository microsoft/intelligent-terminal (2,074 stars, last pushed today), licensed MIT. It adds 2,026 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
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
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, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.