sideshell CLAUDE.md

Project instructions for sideshell, an AI sidecar terminal that lets Claude or Cursor run commands in a visible, persistent terminal.

In plain words
What is it for?
Developing and testing sideshell, installing optional dependencies, running its server, and checking code with pytest, Ruff, or mypy.
Why use it?
They explain how to install, run, test, lint, and type-check the project across its supported terminal backends.

Instructions file

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/menemy/sideshell/claude-md
Clone the repo
git clone --depth 1 https://github.com/menemy/sideshell
Per session 840 This file is loaded in full into every session.
When invoked 840 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 $0.00840 $0.00840
Opus 5 $0.00420 $0.00420
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured yesterday against content hash 505c92648b8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sideshell 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 yesterday.

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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 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 when working with this repository.

Project Overview

sideshell is an AI sidecar terminal - an MCP server that lets Claude/Cursor run commands in a visible, persistent terminal. Cross-platform with pluggable backends (iTerm2, tmux, Ghostty, WezTerm, Kitty, maquake).

Commands

Development

  • uv pip install -e . - Install in development mode (minimal: tmux/ghostty/kitty/wezterm/maquake)
  • uv pip install -e ".[all]" - Install with all optional deps (iTerm2 + IDE backends)
  • python -m sideshell_mcp.server - Run the MCP server directly
  • uvx sideshell-mcp - Run via uvx (after publishing)

Testing

  • python tests/test_iterm2_backend.py - Run iTerm2 backend tests
  • python tests/test_tmux_backend.py - Run tmux backend tests
  • uv run python tests/test_maquake_backend.py - Run maquake backend tests (requires maquake running)
  • pytest - Run all pytest-based tests

Linting & Formatting

  • ruff format . - Format code
  • ruff check . --fix - Lint and fix issues
  • mypy sideshell_mcp - Type check

Architecture

Directory Structure

sideshell_mcp/
├── server.py           # MCP server with 17 tools
├── backends/
│   ├── base.py             # Abstract base class, ControlKey enum
│   ├── iterm2_backend.py   # iTerm2 Python API backend
│   ├── tmux_backend.py     # tmux subprocess backend
│   ├── ghostty_backend.py  # Ghostty (via tmux)
│   ├── maquake_backend.py  # maquake Unix socket backend
│   ├── wezterm_backend.py  # WezTerm
│   └── kitty_backend.py    # Kitty

Backend Pattern

Each backend implements TerminalBackend abstract class:

  • connect(), ensure_connection()
  • execute_command(), read_terminal(), send_control()
  • split_pane(), create_tab(), create_window()
  • focus_session(), close_session()
  • set_appearance(), list_color_presets(), set_color_preset()

ControlKey Enum

Special keys in base.py:

  • Ctrl keys: c, d, z, a, e, k, l, u, w
  • Navigation: up, down, left, right, home, end, pageup, pagedown
  • Function keys: f1-f12
  • Other: enter, esc, tab, backspace, insert, delete

Read the full file on GitHub · 71 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. yesterday First seen · 71 lines · 840 tokens per session scan A 505c92648b8d

Subscribe to this mod's changes

sideshell CLAUDE.md is an instructions file published in the GitHub repository menemy/sideshell (1 stars, last pushed 2mo ago), licensed MIT. It adds 840 tokens to every session, about $0.0042 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.