What is tmux-control?

A set of operating patterns for controlling tmux, a terminal tool that keeps commands running in windows and panes. It covers finding the right pane, sending commands, synchronizing them, and capturing output.

Use it to create or split tmux windows, send commands to existing panes, monitor sessions, verify targets, and collect command output.

It reduces mistakes caused by sending commands to the wrong session or pane and avoids taking control of the user's active terminal window. It also handles timing and different pane environments more reliably.

tmux-control — Skill for Claude Code by eins78

Install

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.

Any agent

npx skills add eins78/agent-skills --skill tmux-control

Clone the repo

git clone --depth 1 https://github.com/eins78/agent-skills

Made for: Claude Code.

Or install eins78-skills, the plugin that ships this one along with the rest of its 15 skills.

Its marketplace also offers this one on its own, as the plugin tmux-control — /plugin install tmux-control after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eins78/agent-skills/tmux-control/github.svg)](https://agentmods.dev/skills/eins78/agent-skills/tmux-control)

Your own site

<a href="https://agentmods.dev/skills/eins78/agent-skills/tmux-control"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/tmux-control/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eins78/agent-skills/tmux-control"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/tmux-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,681 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.03681
Opus 5	$0.00019	$0.01840
Sonnet 5	$0.00008	$0.00736
Haiku 4.5	$0.00004	$0.00368

Measured 9d ago against content hash 86ae2e4ae7b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tmux-control 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/tmux-run.sh, scripts/tmux-watch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/tmux-control/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tmux Control Patterns

Reliable patterns for programmatic tmux interaction. The #1 source of bugs is targeting — follow these rules strictly.

Golden Rules

Use unique IDs for targeting: %N (pane), @N (window), $NAME (session) — never bare indexes
Use wait-for instead of sleep for synchronization
Pass commands to new-window/split-window directly — avoid send-keys to freshly created panes (race condition)
Always use -d (detached) with new-window and split-window — never steal focus from the user's active window
Verify targets exist before sending — use list-panes -a to check panes, list-windows for windows, has-session for sessions
Use full binary paths in commands sent to panes — the pane's environment may differ from yours

Targeting

The format is SESSION:WINDOW.PANE. All three parts are optional but be explicit.

Discover targets first — always

# List all panes with their IDs and human-readable positions
tmux list-panes -a -F '#{pane_id} #{session_name}:#{window_index}.#{pane_index} #{pane_current_command}'

# List sessions
tmux list-sessions -F '#{session_id} #{session_name}'

# List windows in current session
tmux list-windows -F '#{window_id} #{window_index} #{window_name}'

Targeting syntax

Target	Meaning	Reliability
`%42`	Pane ID (unique, stable)	Best
`@3`	Window ID (unique, stable)	Good
`$main`	Session by name	Good
`main:2.0`	Session:Window.Pane by index	Fragile — indexes shift
`:2`	Window 2 in current session	OK for interactive use
`-t 2`	Ambiguous (session? window?)	Avoid

Capture pane ID at creation

# Best pattern: capture the ID when you create the pane
# Pass the command directly to avoid the send-keys race condition
PANE_ID=$(tmux split-window -d -P -F '#{pane_id}' 'echo hello; exec bash')
# or
PANE_ID=$(tmux new-window -d -P -F '#{pane_id}' 'echo hello; exec bash')

Read the full file on GitHub · 411 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

9d ago First seen · 411 lines · 39 tokens per session scan A 86ae2e4ae7b9

Subscribe to this mod's changes

tmux-control is a skill published in the GitHub repository eins78/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 3,681 once invoked, about $0.0002 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 2026-08-31.

Productivity agent-skills claude-code-skills

add-teams

Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.

microsoft/power-platform-skills · 31 tokens

triage-inbox

Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…

pedrohcgs/claude-code-my-workflow · 132 tokens

tmux-control