Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aey-Sama/tmux-arsenal/plugin install tmux-arsenalWrote 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/commands/aey-sama/tmux-arsenal/tmux-squad)<a href="https://agentmods.dev/commands/aey-sama/tmux-arsenal/tmux-squad"><img src="https://agentmods.dev/badge/commands/aey-sama/tmux-arsenal/tmux-squad/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/commands/aey-sama/tmux-arsenal/tmux-squad"><img src="https://agentmods.dev/badge/commands/aey-sama/tmux-arsenal/tmux-squad.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 | $0.00017 | $0.00580 |
| Opus 5 | $0.00009 | $0.00290 |
| Sonnet 5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
tmux-squad 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 10d 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.
What it actually says
Run the squad layout with $ARGUMENTS:
bash "${CLAUDE_PLUGIN_ROOT}/src/bin/tmux-squad.sh" $ARGUMENTS
First argument is the worker count (default 2, max 8). Second is an optional
agent command to start in every worker pane — claude, codex, or anything
else on PATH. With no agent named, the panes are left at a shell and the user
starts what they want.
/tmux-squad 4 # 1 primary + 4 workers, nothing launched
/tmux-squad 4 claude # same, with claude running in each worker
/tmux-squad 3 codex
/tmux-squad --isolate 3 claude # each worker in its own git worktree
--isolate gives every worker its own git worktree under
.git/tmux-squad/, so agents editing the same file no longer overwrite each
other. Requires a git repository. Re-running reuses existing worktrees. It fixes
file conflicts only — two agents binding the same port or sharing one
database still collide. Remove them with git worktree remove <path>.
Panes are laid out with select-layout tiled, so they form a grid (2x2, 2x3,
3x3) rather than a vertical stack — a stack gives each pane roughly half the
rows. Worker panes are titled worker-1..worker-N and the first pane is
primary.
Report the session name, the grid the user got, and the per-pane height. If the script warns that panes are under ~14 rows, pass that along: agent UIs need the room, and the fix is fewer workers or a bigger window. Note that a worker count of 4 (5 panes total) cannot tile into a rectangle, so one pane ends up full-width; 3 or 5 workers give a clean grid.
Squad sessions are the user's own workspace, named squad (then squad-2,
squad-3 if one already exists) — NOT _*. Never kill one as if the plugin
had created it.
Do not launch agents in these panes on the user's behalf unless they named one in the arguments. Spawning several agents multiplies token spend, and each is a separate context that shares nothing with this session.
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.
- 10d ago First seen · 51 lines · 17 tokens per session scan A dacd5bf5e34e
tmux-squad is a command published in the GitHub repository Aey-Sama/tmux-arsenal (1 stars, last pushed 17d ago), licensed MIT. It adds 17 tokens to every session and 580 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 2026-08-31.
Other commands, from other repositories
cleanup
Remove statusline configuration before uninstalling the plugin.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
release
Generate changelog, bump version, and create git tag.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.