Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
TUI automation and visual testing - Playwright for terminal applications. Spawn, interact with, and screenshot TUI apps.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin tuivisionTUI automation and visual testing for Claude Code: Playwright for terminal applications.
tuivision lets Claude spawn TUI apps in virtual terminals, send keystrokes, read screen state, and capture screenshots as PNG or SVG. It's an MCP server backed by node-pty (real PTY processes), xterm.js headless (ANSI parsing), and node-canvas (image rendering). The same stack that powers VS Code's terminal, minus the UI.
Useful for TUI development (see your Textual/Bubbletea/Ratatui app as you build it), visual testing (capture screenshots for verification), interactive debugging (step through TUI state), and documentation (generate terminal screenshots that aren't faked).
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install tuivision
Requires Node.js 20+ and system dependencies for canvas rendering:
Ubuntu/Debian:
apt install build-essential python3 libcairo2-dev libpango1.0-dev libjpeg-dev libgif-dev librsvg2-dev
macOS:
brew install pkg-config cairo pango libpng jpeg giflib librsvg
enter, tab, ctrl+c, f1-f12), key sequences, or raw textSome TUI frameworks need extra TTY features. For Bubble Tea apps, use both use_script (wraps in script for /dev/tty access) and answer_queries (auto-responds to ANSI terminal queries):
{ "command": "./my-bubbletea-app", "use_script": true, "answer_queries": true }
tuivision also includes a CLI for bash-friendly automation:
# Single-shot: spawn, wait, capture, done
tuivision run htop --cols 120 --rows 40 --wait 2000 --screenshot /tmp/htop.png
# Daemon mode for persistent sessions
tuivision daemon start
tuivision spawn "./my-app" --script --answer-queries
tuivision screen <session-id>
tuivision close <session-id>
MIT
Admin access level
Server config contains admin-level keywords
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
TUI automation for AI agents β interact with REPLs, interactive installers, and TUI applications
Expert CLI/TUI design consultant for command structure, visual design, accessibility, and UX patterns
Headless, in-memory terminal emulator for AI agents. Full ANSI/VT100 emulation with PTY spawning.
Agent Skills for automating and testing Tauri v2 applications
SwiftCUI framework guide β build terminal-based interactive applications with a SwiftUI-like declarative architecture over TCP
TabzChrome integration: spawn terminals, browser automation, and project integration via HTML/WebSocket/JS API
[DEPRECATED β use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim