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 pranav7/domux --skill domux-startgit clone --depth 1 https://github.com/pranav7/domuxWrote 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/pranav7/domux/domux-start)<a href="https://agentmods.dev/skills/pranav7/domux/domux-start"><img src="https://agentmods.dev/badge/skills/pranav7/domux/domux-start/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/pranav7/domux/domux-start"><img src="https://agentmods.dev/badge/skills/pranav7/domux/domux-start.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 | $0.00000 | $0.00755 |
| Opus 5 | $0.00000 | $0.00378 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
domux-start 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/domux-start — kick off a task in a tmux+domux workbench
You're being kicked off in a tmux+domux workbench. The task to start is
whatever you were asked to do — the argument passed to /domux-start, or the
request you're currently acting on. Set up the workspace before touching code.
What domux is
domux pins each tmux session to a git worktree root and tracks per-session
state (label, AI status, focused TODO). Worktrees are independent checkouts of
the same repo at different paths — typically one per in-flight task — so each
session is meant to be a fresh, short-lived branch off origin/main.
- Session is pinned to the worktree root, so
cding into subdirs is fine. - TODO list lives at the path printed by
domux --path. - Session label shows in the switcher; set it so the human can find you.
Restricted branches — never commit directly to: main, master, workspace-*.
Setup steps (do these before anything else)
-
Resolve the workspace.
git rev-parse --show-toplevel→ worktree root.git worktree list→ check whether this checkout is the primary or a worktree.git status --porcelain→ check for uncommitted changes.
-
Refresh main.
git fetch origin main. -
Branch off fresh main. Pick a kebab-case branch name from the task (e.g.
fix-login-redirect,add-export-csv— short, 2–5 words).- If this is a worktree AND it's clean:
git checkout main && git reset --hard origin/main && git checkout -b <branch>. Worktrees are meant to be wiped between tasks. - If this is the primary checkout OR there are uncommitted changes: do NOT reset. Just
git checkout -b <branch> origin/main(or stop and ask the user how to handle the dirty state).
- If this is a worktree AND it's clean:
-
Label the session so it shows up in the domux switcher:
domux label set "<2–4 word task title>". Current tmux session is auto-detected. -
Acknowledge in one line, then start the task.
domux quick reference
| Command | What it does |
|---|---|
domux --path |
Print the pinned TODO file for this session |
domux label set "..." |
Name the current session (shown in switcher) |
domux label clear |
Clear the session name |
domux sessions |
Open the session switcher TUI |
domux todo |
Open the per-worktree TODO TUI |
domux --status |
Top active task (for status bars) |
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 · 57 lines · 0 tokens per session scan A 036adaac4c8e
domux-start is a skill published in the GitHub repository pranav7/domux (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 755 tokens. 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 skills, from other repositories
crawlkit
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
github-issue-fix-flow
Use when asked to take a GitHub issue number, implement a fix, run builds/tests, commit with a closing message, and push. End-to-end workflow using gh CLI, local code changes, and git.
release-app-store-changelog
Create user-facing App Store release notes from git history. Use when asked to generate release changelog, App Store "What's New" text, or release notes based on git tags.
manager-loop
Run a large batch of independent work items (a fleet-wide harvest, a multi-repo sync-down, an overnight backlog) as a persistent coordinator loop instead of one item at a time. Use when there are enough independent units of work that dispatch-review-merge would otherwise repeat many times in a row, or when the batch…
goal-orchestrator
Run a long-lived, headless per-project GOAL orchestrator on hyperpanes — hold a project's goal list, spawn a fable/opus spec agent per goal, have it fan work out to sonnet impl agents via the durable work queue, watchdog wedged agents, rotate across Claude accounts on limits, and loop 24/7. Use when the user wants a…
release
Build, version bump, update README/marketplace, commit, push, create GitHub release, and clean local caches.