What is iterm-mcp-claude-agency CLAUDE.md?

A project instruction document for an iTerm MCP server, which lets an AI assistant work with iTerm terminal sessions through MCP. It describes the project, fixed problems, and remaining improvements.

Use it when researching or changing the iTerm MCP server, especially its session layouts, screen monitoring, WebSocket handling, logging, and connection behaviour.

It gives developers a shared reference for known issues, error handling, screen monitoring, layouts, and WebSocket communication.

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/CLAUDE.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/instructions/research-developer/iterm-mcp-claude-agency/claude-md/github.svg)](https://agentmods.dev/instructions/research-developer/iterm-mcp-claude-agency/claude-md)

Your own site

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

Your own site · 80×15

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

Per session 4,512 This file is loaded in full into every session.

When invoked 4,512 The same file — it is already loaded in full.

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	$0.04512	$0.04512
Opus 5.5	$0.01805	$0.01805
Sonnet 5.5	$0.00902	$0.00902
Haiku 4.5	$0.00451	$0.00451

Measured 2mo ago against content hash d2769f83b8c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iterm-mcp-claude-agency CLAUDE.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 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.

CLAUDE.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP (Model Context Protocol) Project Guide

Known Issues with iTerm MCP Server

Fixed Issues

✅ Parameter mismatch in create_layout:
- Fixed by keeping parameter name as session_names in the MCP server and passing it as pane_names to the layout manager
- Also fixed enum mapping for layout types: HORIZONTAL_SPLIT, VERTICAL_SPLIT
✅ Missing attribute issue:
- Fixed error "'Session' object has no attribute 'is_processing'"
- Added attribute existence checking with hasattr() and fallback defaults
- Improved error handling in the is_processing property
✅ Improved WebSocket frame handling:
- Added comprehensive try/except blocks to all async functions
- Added detailed logging for all exceptions
- Improved connection initialization with better error handling
- Implemented graceful shutdown handlers for WebSocket connections
✅ Better logging and debugging:
- Added detailed logging for all operations
- Improved error messages with more context
- Added operation tracking for async functions

Fixed Issues (March 2025)

✅ Screen monitoring functionality:
- Replaced subscription-based monitoring with polling-based approach
- Added async initialization waiting with timeout for monitoring startup
- Implemented event-based signaling for monitor task readiness
- Updated tests to properly wait for monitoring to be established
- Added proper handling of SESSION_NOT_FOUND errors during monitoring
✅ Output filtering:
- Fixed line-by-line filtering to correctly process individual output lines
- Added debug logging for filtered content
- Updated tests to use unique identifiers for more reliable assertions
- Added explicit monitoring in filter tests to capture all output
✅ Async stop_monitoring:
- Changed stop_monitoring to async method for proper cleanup
- Added graceful shutdown period before cancellation
- Implemented proper task completion checking and waiting
- Updated all tests to use the async version

Read the full file on GitHub · 391 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 · 391 lines · 4,512 tokens per session scan A d2769f83b8c1

Subscribe to this mod's changes

iterm-mcp-claude-agency CLAUDE.md is an instructions file published in the GitHub repository research-developer/iterm-mcp-claude-agency (4 stars, last pushed 13d ago), licensed MIT. It adds 4,512 tokens to every session, about $0.0180 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.

iterm-mcp-claude-agency CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
iterm-mcp-claude-agency CLAUDE.mdresearch-developer/iterm-mcp-claude-agency	Instructions file	4	13d ago	MIT	A	4,512	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

iterm-mcp-claude-agency: Instructions file for Claude Code