Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add beel-collab/presets.dev --skill tmuxgit clone --depth 1 https://github.com/beel-collab/presets.devWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/beel-collab/presets.dev/tmux)<a href="https://agentmods.dev/skills/beel-collab/presets.dev/tmux"><img src="https://agentmods.dev/badge/skills/beel-collab/presets.dev/tmux.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.03000 |
| Opus 5 | $0.00012 | $0.01500 |
| Sonnet 5 | $0.00005 | $0.00600 |
| Haiku 4.5 | $0.00002 | $0.00300 |
Grade A, and why
tmux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux — Terminal Multiplexer
Overview
tmux keeps terminal sessions alive across SSH disconnects, splits work across multiple panes, and enables fully scriptable terminal automation. This skill covers session management, window/pane layout, keybinding patterns, and using tmux non-interactively from shell scripts — essential for remote servers, long-running jobs, and automated workflows.
When to Use This Skill
- Use when setting up or managing persistent terminal sessions on remote servers
- Use when the user needs to run long-running processes that survive SSH disconnects
- Use when scripting multi-pane terminal layouts (e.g., logs + shell + editor)
- Use when automating
tmuxcommands from bash scripts without user interaction
How It Works
tmux has three hierarchy levels: sessions (top level, survives disconnects), windows (tabs within a session), and panes (splits within a window). Everything is controllable from outside via tmux <command> or from inside via the prefix key (Ctrl-b by default).
Session Management
# Create a new named session
tmux new-session -s work
# Create detached (background) session
tmux new-session -d -s work
# Create detached session and start a command
tmux new-session -d -s build -x 220 -y 50 "make all"
# Attach to a session
tmux attach -t work
tmux attach # attaches to most recent session
# List all sessions
tmux list-sessions
tmux ls
# Detach from inside tmux
# Prefix + d (Ctrl-b d)
# Kill a session
tmux kill-session -t work
# Kill all sessions except the current one
tmux kill-session -a
# Rename a session from outside
tmux rename-session -t old-name new-name
# Switch to another session from outside
tmux switch-client -t other-session
# Check if a session exists (useful in scripts)
tmux has-session -t work 2>/dev/null && echo "exists"
Window Management
# Create a new window in the current session
tmux new-window -t work -n "logs"
# Create a window running a specific command
tmux new-window -t work:3 -n "server" "python -m http.server 8080"
# List windows
tmux list-windows -t work
# Select (switch to) a window
tmux select-window -t work:logs
tmux select-window -t work:2 # by index
# Rename a window
tmux rename-window -t work:2 "editor"
# Kill a window
tmux kill-window -t work:logs
# Move window to a new index
tmux move-window -s work:3 -t work:1
# From inside tmux:
# Prefix + c — new window
# Prefix + , — rename window
# Prefix + & — kill window
# Prefix + n/p — next/previous window
# Prefix + 0-9 — switch to window by number
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 373 lines · 24 tokens per session scan A 8c21ac1d1eb3
tmux is a skill published in the GitHub repository beel-collab/presets.dev (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 3,000 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
markedit-tools
Provides tools for managing MarkEdit, a macOS markdown editor.
differed-task-execution
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly asks to you use or configure Herdr.
ask-copilot
Use GitHub Copilot CLI in non-interactive mode to ask questions, review code, or generate snippets without manual interaction.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).