What is iterm2-orchestration?

A reference for using iTerm2, a macOS terminal app, to run multiple Claude Code agents asynchronously. It shows how to create windows, tabs, and split terminal panes, then send commands to them.

Building multi-agent terminal layouts, starting agent processes, splitting panes, and sending commands through iTerm2's Python API.

It helps coordinate several coding agents in organized terminal sessions instead of managing each one manually.

How research-developer/iterm-mcp-claude-agency configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to research-developer/iterm-mcp-claude-agency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/research-developer/iterm-mcp-claude-agency/main/.github/agents/iterm2-orchestration.agent.md

Clone the repo

git clone --depth 1 https://github.com/research-developer/iterm-mcp-claude-agency

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration/github.svg)](https://agentmods.dev/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration)

Your own site

<a href="https://agentmods.dev/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration"><img src="https://agentmods.dev/badge/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration"><img src="https://agentmods.dev/badge/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 5,014 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.05014
Opus 5.5	$0.00028	$0.02006
Sonnet 5.5	$0.00014	$0.01003
Haiku 4.5	$0.00007	$0.00501

Measured 2mo ago against content hash d87d04fe52aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iterm2-orchestration 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 2mo 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.

.github/agents/iterm2-orchestration.agent.md · 707 lines

How it starts

The opening of the file, as written. The whole thing — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iTerm2 Python API for Multi-Agent Orchestration

Complete reference for building Claude Code multi-agent orchestration using iTerm2's async Python API.

Quick Reference

import iterm2

async def main(connection):
    app = await iterm2.async_get_app(connection)
    window = app.current_terminal_window
    session = window.current_tab.current_session
    
    # Split panes
    right = await session.async_split_pane(vertical=True)
    bottom = await session.async_split_pane(vertical=False)
    
    # Send commands
    await session.async_send_text("claude-code --agent worker-1\n")

iterm2.run_forever(main)

Core Hierarchy: App → Window → Tab → Session

app = await iterm2.async_get_app(connection)
windows = app.terminal_windows           # All windows
window = app.current_terminal_window     # Active window
tab = window.current_tab
session = tab.current_session            # Active pane (session = pane)

Creating Windows and Tabs

window = await iterm2.Window.async_create(connection, profile="AgentWorker")
tab = await window.async_create_tab(profile="Default", index=0)

Splitting Panes (tmux-style)

right_pane = await session.async_split_pane(vertical=True)   # Side-by-side
bottom_pane = await session.async_split_pane(vertical=False) # Stacked

# 2x2 grid (3 splits from original)
top_left = tab.current_session
top_right = await top_left.async_split_pane(vertical=True)
bottom_left = await top_left.async_split_pane(vertical=False)
bottom_right = await top_right.async_split_pane(vertical=False)

Session Lookup and Tab Movement

session = app.get_session_by_id(session_id)
new_window = await tab.async_move_to_window()
await window.async_set_tabs([tabs[2], tabs[0], tabs[1]])  # Reorder

Arrangements (Save/Restore Layouts)

await iterm2.Arrangement.async_save(connection, "agent-workspace")
await iterm2.Arrangement.async_restore(connection, "agent-workspace")

Event Monitors (12 Types)

Read the full file on GitHub · 707 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.

2mo ago First seen · 707 lines · 70 tokens per session scan A d87d04fe52aa

Subscribe to this mod's changes

iterm2-orchestration is an agent published in the GitHub repository research-developer/iterm-mcp-claude-agency (4 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 5,014 once invoked, about $0.0003 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 2026-08-31.

Building agents

iterm2-orchestration next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
iterm2-orchestrationresearch-developer/iterm-mcp-claude-agency	Agent	4	13d ago	MIT	A	70	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	yesterday	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code

iterm-mcp-claude-agency: Agent for Claude Code