Frankenterm — AI skill for Claude Code
Terminal hypervisor for AI agent swarms: real-time pane capture, state-machine pattern detection, and a JSON API for coordinating fleets of coding agents across WezTerm.
How to install Frankenterm
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Dicklesworthstone/frankenterm and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Frankenterm does
Terminal hypervisor for AI agent swarms: real-time pane capture, state-machine pattern detection, and a JSON API for coordinating fleets of coding agents across WezTerm.
Alternatives in AI
- Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
- OpenContext — A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC 1.1k ★
- Tokentap — Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard 763 ★
README
ft — FrankenTerm
[](./LICENSE) [](https://www.rust-lang.org/) []() []()
**A swarm-native terminal platform that replaces legacy terminal workflows for massive AI agent orchestration.** 54 workspace crates. 483 core modules. 45,000+ tests. Purpose-built for fleets of 200+ concurrent AI coding agents.
_Summary counts last verified against the current checkout on April 6, 2026: 54 workspace crates, 47 vendored workspace crates under `frankenterm/`, 483 `crates/frankenterm-core/src` Rust modules, and 790k+ core-library Rust lines._
Quick Install
cargo install --git https://github.com/Dicklesworthstone/frankenterm.git --bin ft frankenterm
`ft --version` should work immediately after install. `ft doctor` / `ft doctor --json` also run immediately. Pane/session operations that talk to the live mux require the current interop boundary to be reachable: WezTerm CLI in `PATH` and a reachable WezTerm GUI/mux for `wezterm cli list`.
TL;DR
**The Problem**: Running large AI coding swarms across ad-hoc terminal panes is chaos. You can't reliably observe state, detect rate limits or auth failures, coordinate handoffs, or automate safe recovery without brittle glue code. When you're running 50+ Claude Code / Codex / Gemini agents simultaneously, a single undetected rate limit wastes hours of compute. A stuck agent silently burns tokens. An auth failure goes unnoticed for 30 minutes. You have no search across agent output, no audit trail, no way
Related Skills
Tide
TIDE — a pattern for letting an LLM agent get better at noticing over time. Detection-pattern extraction idea
Agmsg Cmux Bridge
Bridges CLI AI agents (Claude Code, Codex, Gemini CLI, and more) over local SQLite with tmux/cmux/wezterm turn
Kibitz
Real-time decoded feed of AI agent actions — monitor multiple Claude Code & Codex sessions, see exactly what e
Vibe Cockpit
Real-time monitoring dashboard for AI coding agent fleets: session health, output streaming, and observability
Flywheel Gateway
SDK-first orchestration platform for managing AI coding agent fleets: BYOA key rotation, real-time WebSocket d
Python Agent.Py
AI-powered conversational sales agent for AutoStream SaaS. Built with Claude claude-haiku-4-5-20251001 + Anthr
Related Agents
App Tester
Builds and exercises Heron end-to-end on this machine — starts the dev app, starts and stops real claude CLI s
Csi Rf Sensing
Use PROACTIVELY and automatically — do not wait to be asked — for WiFi Channel-State-Information (CSI) human-s
Mesh Coordinator
Use for coordinating peer-to-peer swarms that need resilience and redundancy.