agentmods.dev

intelligent-terminal AGENTS.md

Repository guidance for Intelligent Terminal, a Windows Terminal fork with built-in AI-agent workflows. It explains the system structure, supported agents, settings, and important files.

In plain words
What is it for?
Use it when developing or debugging Intelligent Terminal, its Rust agent coordinator, terminal controls, communication channels, or session tools.
Why use it?
It gives coding agents the project context they need before changing the code, reducing misunderstandings about how the terminal and agent processes connect.

Instructions file for CodexOpenCode

1.9k +13 changed today A scan 1,777 tokens original MIT
View the source file microsoft/intelligent-terminal
Install

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.

agentmods
npx agentmods add instructions/microsoft/intelligent-terminal/agents-md
Clone the repo
git clone --depth 1 https://github.com/microsoft/intelligent-terminal

Made for: Codex, OpenCode.

Per session 1,777 This file is loaded in full into every session.
When invoked 1,777 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01777 $0.01777
Opus 5 $0.00889 $0.00889
Sonnet 5 $0.00355 $0.00355
Haiku 4.5 $0.00178 $0.00178

Measured today against content hash 58d406cc9eec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

AGENTS.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 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-master lazily owns 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.
  • WT Protocol is the terminal-control boundary. wtcli.exe activates IProtocolServer through the package COM registration.
  • Session MCP exposes run_command_in_current_shell, create_workspace, delegate_task_in_new_workspace, and request_user_input. It routes requests to the owning helper and never executes terminal actions itself.
  • Agent panes are ordinary ConptyConnection panes hosting wta-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.

{
    "acpAgent": "copilot",
    "acpModel": "",
    "acpCustomCommand": "",
    "delegateAgent": "copilot",
    "delegateModel": "",
    "delegateCustomCommand": "",
    "agentPanePosition": "bottom",
    "autoErrorDetectionEnabled": true,
    "autoFixEnabled": false,
    "aiIntegration.coordinator.enabled": false,
    "aiIntegration.coordinator.commandline": "wta",
    "aiIntegration.coordinator.profile": "{fd19208a-412b-4857-8a2d-9ca592b4b16e}",
    "aiIntegration.confirmation.readOperations": "auto",
    "aiIntegration.confirmation.createOperations": "auto",
    "aiIntegration.confirmation.inputOperations": "auto"
}

Read the full file on GitHub · 185 lines

Changes

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.

  1. today Changed · +4 tokens per session 58d406cc9eec
  2. 3d ago First seen · 185 lines · 1,773 tokens per session scan A 4c056a72d19a

Subscribe to this mod's changes

intelligent-terminal AGENTS.md is an instructions file published in the GitHub repository microsoft/intelligent-terminal (1,908 stars, last pushed yesterday), licensed MIT. It adds 1,777 tokens to every session, about $0.0089 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.

acpagentagent-client-protocolagentic-aiaicli
Related

Other instructions, from other repositories

coddy-agent AGENTS.md

Instructions for coddy-project/coddy-agent, covering agent notes for coddy, repository navigation, builds, pre-commit gate and documentation contract.

coddy-project/coddy-agent · 3,647 tokens

coddy-agent CLAUDE.md

Instructions for coddy-project/coddy-agent, a project described as: General-purpose agent in one static Go binary. ReAct loop, ACP server for IDEs, OpenAI-compatible REST API with embedded web UI, Telegram gateway, cron scheduler, long-term memory, context compaction, rules, skills, MCP. Distroless-ready, works with…

coddy-project/coddy-agent · 3 tokens

mini-swe-agent copilot-instructions.md

Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.

SWE-agent/mini-swe-agent · 378 tokens

ii-agent AGENTS.md

Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.

Intelligent-Internet/ii-agent · 3,294 tokens

thinkrail AGENTS.md

Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.

JetBrains/thinkrail · 4,503 tokens

sortie copilot-instructions.md

Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).

sortie-ai/sortie · 1,030 tokens