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-project)<a href="https://agentmods.dev/commands/aey-sama/tmux-arsenal/tmux-project"><img src="https://agentmods.dev/badge/commands/aey-sama/tmux-arsenal/tmux-project/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-project"><img src="https://agentmods.dev/badge/commands/aey-sama/tmux-arsenal/tmux-project.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 | $0.00015 | $0.00326 |
| Opus 5 | $0.00008 | $0.00163 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
tmux-project 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.
What it actually says
Run the preset for $ARGUMENTS (default: the current directory):
bash "${CLAUDE_PLUGIN_ROOT}/src/bin/tmux-project.sh" $ARGUMENTS
It creates three windows in a session named after the project directory, then attaches (or switches, if already inside tmux):
| Window | Name | Contents |
|---|---|---|
| 1 | server |
two empty panes, side by side — docker, dev server |
| 2 | agent |
starts claude |
| 3 | editor |
starts nvim (falls back to vim) |
The server panes stay empty: starting a dev server in the wrong project costs something, so the user does that. The agent and editor windows launch their tool, because the worst case there is a shell they were getting anyway.
If a tool is missing, crashes, or is quit, the pane becomes a normal shell in the project directory — the window never disappears. Re-running reuses the session instead of duplicating windows.
The session is named after the project, NOT _*, so it is the user's own
workspace — never kill it as if the plugin had created it. Need a scratch shell?
That is prefix c, no preset required.
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 · 35 lines · 15 tokens per session scan A bdea9ea082c4
tmux-project is a command published in the GitHub repository Aey-Sama/tmux-arsenal (1 stars, last pushed 16d ago), licensed MIT. It adds 15 tokens to every session and 326 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
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
ask
Ask a single expert agent a question - like a Slack ping to a colleague.
settings
View or update Shipyard workflow settings.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
config
Configure iterm2-tab-status plugin settings (emoji prefixes, colors, display target, subtitle activity, badge, notifications).
delete-session
A command for safely listing, inspecting, moving, and restoring Claude Code history sessions.