tabw SKILL.md skillA

tabw from ahundt/autorun is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ahundt/autorun/tabw@git:20260816.82c264e

Pins git:20260816.82c264e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ahundt/autorun
Path
plugins/autorun/skills/tabw/SKILL.md
Versions recorded
3
Latest version
git:20260816.82c264e, committed Aug 16, 2026
First version recorded
Aug 5, 2026
Size
7,978 bytes
Repository stars
13
License
a license file GitHub does not identify

Use when the user asks to "continue every session", "send this to all windows", "/ar:tabw". Acts on Claude sessions across tmux windows; destructive to in-flight work, so it states what it will do before doing it.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Claude Session Writer

<purpose>

Execute actions on Claude Code sessions across tmux windows.

## Context

Current tmux sessions:

Run `tmux list-sessions` and read its output before choosing a session.

## Your Task

The user's request is the task description for everything below.

If no arguments provided, discover sessions first, then ask user what action to execute.

</purpose>

<safety>

## Safety Warning

This command sends input to tmux windows. Before executing:

1. **VERIFY TARGETS** - Always show which windows will receive commands
2. **PREFER IDLE SESSIONS** - Use `awaiting:` prefix to target only idle sessions
3. **TEST SINGLE FIRST** - Test with one window before batch operations
4. **HAVE ESCAPE READY** - `all:escape` can stop runaway operations

</safety>

<workflow>

## Workflow

1. **Discover** - Get window states with `tmux_list_windows(content_lines=100)`
2. **Filter** - Use WindowList methods to select targets
3. **Verify** - Show user which windows will be affected
4. **Execute** - Run action via `tmux_dangerous_batch_execute()`

## Data Flow: tmux_list_windows -> tmux_dangerous_batch_execute
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ahundt/autorun/tabw@sha256:e862dea15a165732

The line at the top of this page pins the label git:20260816.82c264e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_f357odvb47cna3qu.svg)](https://markdownregistry.com/a/art_f357odvb47cna3qu)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 5, 2026 and Aug 16, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20260816.82c264e latest2026-08-16 82c264e 7,978 BA view · diff
git:20260815.2807be52026-08-15 2807be5 7,980 BA view · diff
git:20260805.96f9c4a2026-08-05 96f9c4a 7,847 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7978 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ahundt/autorun · 13 stars · license a license file GitHub does not identify · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_f357odvb47cna3qu
GET https://markdownregistry.com/api/v1/resolve?ref=ahundt/autorun/tabw
GET https://markdownregistry.com/api/v1/blob/e862dea15a16573248eb710588982527b2650ed76df0f0a4a740de4904149226

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ahundt/autorun

autorun-maintainer SKILL.md skill
ahundt/autorun · .agents/skills/autorun-maintainer/SKILL.md · Expertise in maintaining, debugging, and deploying the autorun hook system across Claude Code, Codex CLI, Gemini-family…
git:20260816.82c264e · audit A · 13 stars
AGENTS.md AGENTS.md file
ahundt/autorun · AGENTS.md
git:20261014.f772782 · audit A · 13 stars
CLAUDE.md CLAUDE.md file
ahundt/autorun · CLAUDE.md
git:20260727.9b75cd9 · audit B · 13 stars
ar SKILL.md skill
ahundt/autorun · plugins/autorun/.codex-plugin/skills/ar/SKILL.md · autorun control commands, stated as prose after $ar: status; allow/justify/find file-creation policy…
git:20260815.2807be5 · audit A · 13 stars
AGENTS.md@plugins/autorun AGENTS.md file
ahundt/autorun · plugins/autorun/AGENTS.md
git:20260818.85c8a47 · audit A · 13 stars
CLAUDE.md@plugins/autorun CLAUDE.md file
ahundt/autorun · plugins/autorun/CLAUDE.md
git:20260805.124c64e · audit B · 13 stars
ai-skill-builder SKILL.md skill
ahundt/autorun · plugins/autorun/skills/ai-skill-builder/SKILL.md · Guides creation, audit, and improvement of portable Agent Skills using the shared
v1.3.0 · audit A · 13 stars
cache SKILL.md skill
ahundt/autorun · plugins/autorun/skills/cache/SKILL.md · Use this skill when the user asks to "enable cache protection", "block on cache miss", "avoid cache expiration cost"…
git:20260816.82c264e · audit A · 13 stars
cli-demo-recorder SKILL.md skill
ahundt/autorun · plugins/autorun/skills/cli-demo-recorder/SKILL.md · Create demo videos for CLI and TUI tools. Use when user asks to "record a demo",
v5.1.0 · audit A · 13 stars
commit SKILL.md skill
ahundt/autorun · plugins/autorun/skills/commit/SKILL.md · Use before writing any git commit message or reviewing one, and when the user asks for "commit requirements", "commit…
git:20260816.da968ed · audit A · 13 stars
function-signature-and-parameter-guidance SKILL.md skill
ahundt/autorun · plugins/autorun/skills/function-signature-and-parameter-guidance/SKILL.md · Design and review caller-facing names and contracts: functions, tools, commands, CLI flags, parameters, config keys…
git:20260816.05745f8 · audit A · 13 stars
marketplace-test SKILL.md skill
ahundt/autorun · plugins/autorun/skills/marketplace-test/SKILL.md · Use when the user asks to "test the marketplace plugins", "run marketplace tests", "check every installed plugin", or…
git:20260816.640f782 · audit A · 13 stars

Every file in ahundt/autorun

Browse by kind, by grade A, or by owner.