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 bntvllnt/agent-skills --skill tmuxgit clone --depth 1 https://github.com/bntvllnt/agent-skillsWrote 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/bntvllnt/agent-skills/tmux)<a href="https://agentmods.dev/skills/bntvllnt/agent-skills/tmux"><img src="https://agentmods.dev/badge/skills/bntvllnt/agent-skills/tmux/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.
<a href="https://agentmods.dev/skills/bntvllnt/agent-skills/tmux"><img src="https://agentmods.dev/badge/skills/bntvllnt/agent-skills/tmux.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.01665 |
| Opus 5 | $0.00028 | $0.00833 |
| Sonnet 5 | $0.00011 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00167 |
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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux
Complete tmux management for terminal multiplexing.
Core Concepts
┌─────────────────────────────────────────────────────────────┐
│ SERVER (one per socket) │
│ ┌───────────────────────────────────────────────────────┐ │
│ │ SESSION ($0, $1, ...) │ │
│ │ ┌─────────────────┐ ┌─────────────────┐ │ │
│ │ │ WINDOW (@0) │ │ WINDOW (@1) │ ... │ │
│ │ │ ┌────┬────┐ │ │ ┌────────────┐ │ │ │
│ │ │ │PANE│PANE│ │ │ │ PANE │ │ │ │
│ │ │ │ %0 │ %1 │ │ │ │ %2 │ │ │ │
│ │ │ └────┴────┘ │ │ └────────────┘ │ │ │
│ │ └─────────────────┘ └─────────────────┘ │ │
│ └───────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
- Server: Background process managing all state
- Session (
$id): Named container of windows, persists after detach - Window (
@id): Tab-like container of panes within a session - Pane (
%id): Individual terminal within a window - Client: Terminal attached to a session
Router
| User says | Load reference | Do |
|---|---|---|
| list sessions / status | references/session-management.md |
inspect sessions |
| new session / create session | references/session-management.md |
create session |
| attach / detach | references/session-management.md |
attach/detach |
| kill session | references/session-management.md |
terminate session |
| new window / create window | references/window-management.md |
create window |
| rename window | references/window-management.md |
rename window |
| kill window / close window | references/window-management.md |
close window |
| switch window | references/window-management.md |
navigate windows |
| split / new pane | references/pane-management.md |
split pane |
| resize pane | references/pane-management.md |
resize pane |
| move pane / swap pane | references/pane-management.md |
rearrange panes |
| kill pane / close pane | references/pane-management.md |
close pane |
| layout | references/layouts.md |
apply/manage layouts |
| copy / paste / buffer | references/copy-mode.md |
copy mode operations |
| config / tmux.conf / settings | references/configuration.md |
configure tmux |
| keybind / bind / unbind | references/keybindings.md |
key bindings |
| script / automate / send-keys | references/scripting.md |
scripting/automation |
| capture / log / output | references/scripting.md |
capture pane content |
| help / keys / cheatsheet | inline | show key reference |
What ships with it
9 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.
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 · 177 lines · 56 tokens per session scan A dd9d51a5ff8a
tmux is a skill published in the GitHub repository bntvllnt/agent-skills (16 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,665 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
caveman-save
A set of rules for keeping coding-agent work small, direct, and resource-conscious. It encourages batching work, limiting file and function size, checking ideas before adding code, and verifying results.
tmux-interactive-processes
Use tmux instead of background bash for long-running, interactive, inspectable, or user-attachable terminal processes. Use for development servers, watch-mode tests, REPLs, debuggers, interactive CLIs, log tailing, and commands that may run indefinitely or need later input/inspection.
khal
Read calendar events with the khal CLI. Use when the user asks about meetings, schedule, upcoming events, or calendar searches.
notmuch
Search and read local email with the notmuch CLI. Use when the user asks to find messages, inspect threads, or review email tags.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.