By 88plug
Operate and observe an interactive full-screen TUI on a REMOTE machine over tmux/screen + SSH by driving it like a human: type with send-keys, screenshot with capture-pane, in a type-wait-screenshot-read loop. For the Claude Code TUI, vim, top, curses installers, REPLs, or any program that needs a real PTY over SSH.
Teach Claude Code to operate an interactive full-screen terminal program (a TUI) on a remote machine over SSH — for people who automate work on servers, dev boxes, and headless hosts.
/plugin marketplace add 88plug/drive-remote-terminal
/plugin install drive-remote-terminal@drive-remote-terminal
Or from a local clone:
git clone https://github.com/88plug/drive-remote-terminal
/plugin marketplace add ./drive-remote-terminal
/plugin install drive-remote-terminal@drive-remote-terminal
Requires tmux (or screen) and ssh on the path — all standard.
Once installed, ask Claude Code to drive a remote TUI and it follows the bundled loop:
SSH into build-01 and run `htop`, then tell me which process is using the most memory.
Claude starts a tmux session on the remote host, launches the program, captures the screen, reads it, and reports back — the same type-wait-look loop a human uses. You see a real rendering of the remote screen in the answer, not a blind command result.
You can't drive a TUI with one-shot SSH. ssh host 'cmd' runs and exits; piping
into a full-screen program that needs a real PTY fails. This plugin uses tmux (or
screen as a fallback) to give the agent both a way to type and eyes to see, so it
can operate the Claude Code TUI, vim, top, curses installers, REPLs, or any program
that needs a real PTY over SSH — the way a human would: type a keystroke, look at
the screen, decide the next move.
The whole skill is one loop:
tmux send-keys -t SESSION 'text' Entersleep N (let the app redraw)tmux capture-pane -t SESSION -p (this is the screenshot)Plus the hard-won rules: always screenshot after acting, always wait before you
screenshot, never double-send on an unexpected screen, submit a stuck line with a
standalone Enter, and confirm the program actually launched before sending keys
(or they fall through to the shell).
[!TIP] The wait step matters more than it looks. Capturing the pane before the app has redrawn returns a stale screen, which leads the agent to act on the wrong state.
One skill (drive-remote-terminal) that teaches a method — no scripts, no MCP, no
hooks. It ships reference files for:
capture-pane tablescreen fallback playbookIssues and pull requests are welcome. Open an issue to discuss a change before sending a large pull request, and keep edits to the skill focused on the method it teaches.
FSL-1.1-ALv2 © 2026 88plug — Functional Source License; converts to Apache 2.0 two years after each release.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub 88plug/claude-code-plugins --plugin drive-remote-terminalUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Eyes and hands on a Linux Wayland desktop: screenshot any monitor and click, type, scroll, drag, and read any visible app over xdg-desktop-portal (RemoteDesktop + ScreenCast), with optional OCR + OmniParser icon grounding. Pure-Python, CPU-only. GNOME/Wayland only. Ships the MCP server plus a drive-screen skill that encodes the locate-ground-act-confirm loop.
Seamless context continuity across Claude Code compaction. Four background layers (continuous tool-call capture, mechanical PostCompact handoff, async Opus 4.7 enrichment at --effort max, async Stop-hook refinement, and preemptive snapshot before the next compact) keep the agent's working state intact across every compaction and resume. All summarization is isolated from CLAUDE.md/auto-memory and invisible to the user.
Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional rendered (Playwright) fetch for JS-heavy pages. Self-hostable. The underlying server is also usable independently of Claude Code via `uvx --from git+https://github.com/88plug/searxng-mcp searxng-mcp`.
Detects when Claude drifts away from your active output contract (a terse persona, hard formatting/length rules, an in-character voice) and quietly steers it back. Each assistant turn is scored by a deterministic, dependency-free engine; a status-line badge shows live drift and the next prompt gets a one-shot correction nudge when the previous reply broke contract.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Harness-native ECC plugin for engineering teams - 67 agents, 277 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,846 supported skills.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.