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.
npx agentmods add instructions/oetiker/mcpretentious/claude-mdgit clone --depth 1 https://github.com/oetiker/MCPretentiousWrote 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/oetiker/mcpretentious/claude-md)<a href="https://agentmods.dev/instructions/oetiker/mcpretentious/claude-md"><img src="https://agentmods.dev/badge/instructions/oetiker/mcpretentious/claude-md.svg" alt="Measured on agentmods" 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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
MCPretentious 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCPretentious is a universal terminal MCP - a Model Context Protocol server that enables AI assistants to control terminals across platforms. It supports tmux (cross-platform - Linux, macOS, BSD, remote servers) via control mode, and iTerm2 (macOS) via high-performance WebSocket API with Protocol Buffers (20x faster than AppleScript-based iTerm2 solutions, with no focus stealing). Both backends provide real terminal addressing and proper TUI screen content reading with cursor position and color information.
Development Commands
# Install dependencies
npm install
# Run the server locally
npm start
# or
node mcpretentious.js
# Link for local development
npm link
# Run tests
npm test
npm run test:integration # Integration tests with real iTerm2
npm run test:all # All tests
Architecture
The project is a modular MCP server with mcpretentious.js as the main entry point that:
- Supports multiple backends: tmux (control mode) and iTerm2 (WebSocket API with Protocol Buffers)
- Implements the MCP protocol using
@modelcontextprotocol/sdk - Provides terminal control with session tracking for window management
- Terminal IDs follow format:
iterm-{windowId}-{tabIndex}(iTerm2) ortmux-{sessionName}(tmux) - Includes utility libraries for terminal operations, color handling, and focus management
- Auto-detects available backend or allows manual selection
Key Implementation Details
Backend Integration
- iTerm2: Native WebSocket API using Protocol Buffers, 20x faster than AppleScript
- Authentication via iTerm2's Python API (must be enabled in Preferences)
- Focus restoration logic handles VS Code and other Electron apps specially
- TMux: Control mode for cross-platform support
- Works on Linux, macOS, BSD, and remote servers via SSH
- Unix permission-based authentication
Terminal Input System
The mcpretentious-type tool is the universal input method that handles:
- Text strings with proper escaping for each backend
- ASCII codes (0-255)
- Special keys via escape sequences (stored in
TERMINAL_KEY_MAP) - Mixed sequences combining all input types
- Mouse events (click, drag, scroll) with SGR protocol support in both backends
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.
- 5d ago First seen · 62 lines · 584 tokens per session scan A f8dc319b11e9
MCPretentious CLAUDE.md is an instructions file published in the GitHub repository oetiker/MCPretentious (21 stars, last pushed 6mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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.
Other instructions, from other repositories
localnest CLAUDE.md
Instructions for wmt-mobile/localnest, covering claude code configuration - claude flow v3, behavioral rules (always enforced), file organization, project architecture and project config.
whoop-mcp CLAUDE.md
Claude Code instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, project structure and code conventions.
whoop-mcp copilot-instructions.md
Copilot instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, code conventions and testing.
daz-mcp-server CLAUDE.md
Claude Code instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).
mcpscore AGENTS.md
AGENTS.md instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).
gsd-task-manager CLAUDE.md
Claude Code instructions for vscarpenter/gsd-task-manager, covering claude.md, project overview, design context, core commands and development.