wterm

Web terminal server: manage the wterm-server daemon for browser-based shell access (local or remote via Tailscale). This skill should be used when checking wterm status, listing or creating terminal sessions, killing sessions, or managing the wterm LaunchAgent. Trigger on: wterm, web terminal, remote terminal, remote shell, browser terminal, terminal sessions.

Jump to install Review files

Repository: tdimino/claude-code-minoan
Last source activity: April 23, 2026 at 21:30
Detected SKILL.md language: English
Stars: 41
Forks: 4

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/tdimino/claude-code-minoan/tree/main/skills/integration-automation/wterm.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/tdimino/claude-code-minoan --skill wterm

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

8 files

SKILL.md

Source instructions · Read-only preview

name: wterm
description: Web terminal server: manage the wterm-server daemon for browser-based shell access (local or remote via Tailscale). This skill should be used when checking wterm status, listing or creating terminal sessions, killing sessions, or managing the wterm LaunchAgent. Trigger on: wterm, web terminal, remote terminal, remote shell, browser terminal, terminal sessions.
argument-hint: ["status|list|create|kill <id>|restart"]

# wterm Manage the wterm-server daemon — a Node.js service providing browser-based shell access via `@wterm/react` + `node-pty`. Access locally at `https://wterm.localhost` (via portless) or remotely from any tailnet device at `http://<hostname>:3036`. ## Commands ### Check status ```bash bash ~/.claude/skills/wterm/scripts/status.sh ``` Reports whether the daemon is running, its PID, port, and active session count. ### List sessions ```bash bash ~/.claude/skills/wterm/scripts/list-sessions.sh ``` Shows all active PTY sessions (id, name, command, PID, client count, last activity). ### Create a session ```bash bash ~/.claude/skills/wterm/scripts/create-session.sh # default: zsh bash ~/.claude/skills/wterm/scripts/create-session.sh claude # Claude Code bash ~/.claude/skills/wterm/scripts/create-session.sh /bin/bash # explicit shell ``` Spawns a new PTY session. Default shell is zsh. Pass `claude` to start a Claude Code session. ### Kill a session ```bash bash ~/.claude/skills/wterm/scripts/kill-session.sh <session-id> ``` Terminates a session by its hex ID (get IDs from `list-sessions.sh`). ### Restart the daemon ```bash bash ~/.claude/skills/wterm/scripts/restart.sh ``` Restarts the wterm-server LaunchAgent. All active sessions are lost. ## Architecture - **Daemon**: `~/daimones/wterm-server/` — TypeScript, node-pty, ws, Vite React SPA - **Port**: 3036 (bound to `0.0.0.0` for Tailscale access) - **Auth**: Bearer token from `WTERM_AUTH_TOKEN` in `~/.config/env/secrets.env`. Auth is fail-closed — server rejects all requests if no token is configured. - **LaunchAgent**: `com.minoan.wterm-server` — RunAtLoad, KeepAlive - **Logs**: `~/.claude/logs/wterm-server.{out,err}.log` ## Gotchas - Sessions default to zsh, not Claude Code. Pass `claude` explicitly to create-session.sh. - The daemon must be running on the host machine. If status shows not running, use `restart.sh` or check `launchctl list | grep wterm`. - Auth token is required for remote access. If scripts return 401, verify `WTERM_AUTH_TOKEN` is set in `~/.config/env/secrets.env`. - Restarting the daemon kills all active sessions — the scrollback buffer is in-memory only.

View on GitHub

Back to search Back to installation

claude-peers

Discover, message, and coordinate AI coding agents (Claude Code, Codex CLI) running on the same machine via a shared Unix socket broker backed by SQLite. The broker wakes recipients natively (Claude inbox socket, codex queue) and turn-boundary hooks catch missed wakes. Supports cross-session task delegation, peer summaries, and session lifecycle management. Triggers on 'peer agents', 'cross-session communication', 'message Codex', 'inter-agent messaging', 'coordinate agents'.

2026-09-27

parakeet

Local speech-to-text on Apple Silicon with two cross-checking MLX engines: NVIDIA Parakeet TDT v2 (parakeet-mlx) and Qwen3-ASR 1.7B (mlx-audio, hotword biasing). Batch JSONL with word timestamps, confidence, provenance, and an agreement verdict. No NeMo or PyTorch. Use when transcribing audio files, identifying game or legacy voice clips by content, telling speech from SFX, serving an OpenAI-compatible STT endpoint, or dictating. For push-to-talk into any text field, use the Handy app.

2026-09-24

codex-orchestrator

This skill should be used to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs. It adds each persona through process-local developer instructions while preserving the project's AGENTS.md chain, including during parallel launches. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.

2026-09-19

View all from this repository

wterm

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository