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.
curl -O https://raw.githubusercontent.com/research-developer/iterm-mcp-claude-agency/main/.github/agents/iterm2-orchestration.agent.mdgit clone --depth 1 https://github.com/research-developer/iterm-mcp-claude-agencyWrote 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/agents/research-developer/iterm-mcp-claude-agency/iterm2-orchestration)<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.
<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>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 | $0.00035 | $0.02507 |
| Sonnet 5 | $0.00014 | $0.01003 |
| Haiku 4.5 | $0.00007 | $0.00501 |
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 10d 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 — 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)
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.
- 10d ago First seen · 707 lines · 70 tokens per session scan A d87d04fe52aa
iterm2-orchestration is an agent published in the GitHub repository research-developer/iterm-mcp-claude-agency (4 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 5,014 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.