lirrensi/tmux
skills/tmux/SKILL.md
Control tmux/psmux sessions for interactive CLIs, SSH connections, and parallel agent orchestration. Works cross-platform: tmux on Linux/macOS, psmux on Windows. Provides sync commands that send keys and automatically capture output. Triggers: "run in tmux", "create tmux session", "tmux", "SSH session", "parallel terminals", "run multiple agents".
$ install --global
skillsauthnpx skillsauth add lirrensi/agent-cli-helpers tmuxInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 12, 2026, 7:38 AM101.3s2 files scanned
SKILL.md
- name:
- tmux
- description:
- >
- Works cross-platform:
- tmux on Linux/macOS, psmux on Windows. Provides sync commands that send keys
- and automatically capture output. Triggers:
- run in tmux", "create tmux session", "tmux", "SSH session",
tmux Skill
Control tmux sessions programmatically. Send keys, capture output, run interactive processes.
Cross-platform:
- Linux/macOS: Uses native
tmux - Windows: Uses
psmux(native Windows tmux, 95%+ syntax compatible)
Use tmux when:
- SSH to remote servers (persistent sessions)
- Interactive TTY needed (REPLs, shells, prompts)
- Running multiple processes in parallel
- Orchestrating coding agents
Don't use tmux for:
- Simple background tasks → use
bg runinstead - One-shot commands → run directly
Helper: tmx
Primary: Python CLI tool (tmx) — installable via agent-sommelier-cli.
Fallback: Shell scripts at skills/tmux/scripts/tmx.sh (bash) and tmx.ps1 (PowerShell).
Commands
| Command | Description |
|---------|-------------|
| tmx install | Ensure tmux/psmux is available (auto-install on Windows) |
| tmx create <name> [cmd] | Create session, optionally run init cmd |
| tmx rm <name> | Kill session |
| tmx sk <name> "<cmd>" | Send keys (fire and forget) |
| tmx r <name> | Read output (full scrollback) |
| tmx run <name> "<cmd>" [--timeout N] | Send + wait N seconds + read output |
| tmx list [--json] | List all sessions (rich table or JSON) |
| tmx manager | Interactive session picker |
Quick Start
tmx install
tmx create mysession
tmx run mysession "ls -la"
tmx r mysession
tmx rm mysession
tmx install
tmx create mysession
tmx run mysession "Get-ChildItem"
Pattern 1: SSH Sessions (Most Common)
# Create SSH session
tmx create server "ssh [email protected]"
tmx run server "hostname" --timeout 3
tmx sk server "mypassword"
tmx run server "tail -100 nginx/access.log" --timeout 5
tmx r server
Pattern 2: Background Process Monitoring
tmx create api "cd /app && python api.py"
tmx r api | grep -q "Listening" && echo "API is up"
tmx create db "docker run --name postgres postgres"
tmx list
Pattern 3: Interactive REPL
tmx create python "python3 -q"
tmx run python "import sys; print(sys.version)"
tmx run python "2 + 2" --timeout 3
Pattern 4: Parallel Agents
for i in 1 2 3; do
tmx create "agent-$i" "cd /tmp/project$i && codex --yolo 'Fix bugs'"
done
tmx list
tmx r agent-1
Key Bindings (when attached)
| Key | Action |
|-----|--------|
| Ctrl+b d | Detach from session |
| Ctrl+b c | Create new window |
| Ctrl+b n/p | Next/Previous window |
| Ctrl+b % | Split vertical |
| Ctrl+b " | Split horizontal |
Deeper Reading
| Topic | File |
|---|---|
| Installation per-platform, platform differences, gotchas | references/setup.md |
Related Skills
lirrensi/essh
data-ai
VerifiedTrustedCommunity
Portable SSH profile manager for agents. Run remote commands on saved hosts by friendly name instead of typing user@host -i key every time. Type less crap around your SSH commands.
4SKILL.mdUpdated May 27, 2026
lirrensi/engage
development
VerifiedTrustedCommunity
Autonomous execution mode triggered by the word "engage". Use when the user has finished planning and wants the agent to execute autonomously without further questions until the workflow is fully complete. The agent must build, test, verify, and deliver proof of work — never exiting with an incomplete or unverified result. Trigger on: "engage", "go autonomous", "execute the plan", "run it", "make it happen", or any explicit signal to switch from planning mode into fully autonomous build-and-verify mode.
4SKILL.mdUpdated May 27, 2026
lirrensi/task-system
tools
VerifiedTrustedCommunity
Use this skill when you need to manage project tasks — create, update, complete, prioritize, filter, review, track dependencies, or find unblocked work. Trigger on: 'add a task', 'create task', 'show tasks', 'what's next', 'mark done', 'update task', 'task status', 'task history', 'next task', 'task inbox', 'list tasks', 'init tasks', 'task deps', 'ready tasks', 'blocked tasks', 'search tasks', 'tag-any', 'dependency graph'. Also use proactively when starting a new work session — check `tasks status` and `tasks ready` to orient yourself. This skill covers the project's static, file-based task system (persistent, in-repo history) with typed dependency tracking, ready queue, and priority management — NOT ephemeral runtime task tools.
4SKILL.mdUpdated May 10, 2026
lirrensi/edge-tts
tools
VerifiedTrustedCommunity
Generate complete, production-ready TTS (Text-to-Speech) scripts and CLI tools using edge-tts — Microsoft's neural voice engine with 400+ natural-sounding voices. Use this skill whenever the user wants to speak text aloud from the terminal/PowerShell, list or search voices, select voices by name/language/gender, control rate/volume/pitch, save speech to MP3/audio files, or pipe text into a speak command. Trigger for ANY request involving TTS, speech synthesis, say command, speak function, voice output, edge-tts, or audio from scripts — even small snippets. Always check installation first and prefer uv tool install for setup.
4SKILL.mdUpdated Apr 6, 2026