run-in-new-tab

run-in-new-tab is a command for coding agents from dapi/claude-code-marketplace. It costs 11 tokens per session (669 once invoked), scanned A, original, MIT.

A command workflow for launching a Claude Code session in a new Zellij tab or pane. It accepts either written instructions or a Markdown plan file.

In plain words
What is it for?
Running instructions directly, or executing a plan from a .md file, in a newly created Zellij tab or pane.
Why use it?
It gives a coding agent a separate terminal workspace and starts the session with the requested task already supplied.

Command

Part of the zellij-workflow plugin — 1 skill, 2 commands shipped together

Install

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.

agentmods
npx agentmods add commands/dapi/claude-code-marketplace/run-in-new-tab
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace

Or install zellij-workflow, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

Wrote 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.

agentmods badge for run-in-new-tab

README.md
[![agentmods](https://agentmods.dev/badge/commands/dapi/claude-code-marketplace/run-in-new-tab.svg)](https://agentmods.dev/commands/dapi/claude-code-marketplace/run-in-new-tab)
Your own site
<a href="https://agentmods.dev/commands/dapi/claude-code-marketplace/run-in-new-tab"><img src="https://agentmods.dev/badge/commands/dapi/claude-code-marketplace/run-in-new-tab.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00669
Opus 5 $0.00005 $0.00334
Sonnet 5 $0.00002 $0.00134
Haiku 4.5 $0.00001 $0.00067

Measured 5d ago against content hash a7dccbf11787, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

run-in-new-tab 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 5d 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.

zellij-workflow/commands/run-in-new-tab.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run in New Tab

Launch an interactive Claude Code session in a new zellij tab or pane.

Input

  • INSTRUCTIONS: $ARGUMENTS -- prompt text or path to a plan file

Steps

1. Determine tab name and prompt

If $ARGUMENTS is a file path (ends with .md), the prompt should be:

Execute the plan from <plan-file-path>. Use superpowers:executing-plans.

Otherwise use $ARGUMENTS directly as the prompt.

Generate a short tab name (1-2 words) from the content. Fallback: claude-<HH:MM>.

2. Write bash launch script

SCRIPT=$(mktemp /tmp/claude-tab-XXXXXX.sh)
cat > "$SCRIPT" << 'SCRIPT_EOF'
#!/bin/bash
cd '<PROJECT_DIR>'
PROMPT='<escaped prompt -- single quotes escaped as '"'"'>'
clear
echo "Launching claude with prompt: $PROMPT"
echo ""
exec claude --dangerously-skip-permissions "$PROMPT"
SCRIPT_EOF
chmod +x "$SCRIPT"

3. Create tab and launch

In a new tab (default):

TAB_NAME="<auto-generated>"

timeout 5 zellij action new-tab --name "$TAB_NAME" && \
sleep 0.3 && \
timeout 5 zellij action write-chars "bash '$SCRIPT'
" || {
  _rc=$?
  echo "Command failed. Diagnosing..."
  if [ -z "$ZELLIJ" ]; then echo "Not in zellij session"
  elif [ $_rc -eq 124 ]; then echo "Timed out -- zellij may be hanging"
  elif ! command -v claude &>/dev/null; then echo "claude not found in PATH"
  else echo "Unknown error (exit code: $_rc)"
  fi
  exit $_rc
}

In a new pane:

timeout 5 zellij run -- bash "$SCRIPT" || {
  _rc=$?
  echo "Command failed. Diagnosing..."
  if [ -z "$ZELLIJ" ]; then echo "Not in zellij session"
  elif [ $_rc -eq 124 ]; then echo "Timed out -- zellij may be hanging"
  elif ! command -v claude &>/dev/null; then echo "claude not found in PATH"
  else echo "Unknown error (exit code: $_rc)"
  fi
  exit $_rc
}

Examples

/run-in-new-tab Execute plan from docs/plans/skill-audit-plan.md. Use executing-plans.
/run-in-new-tab Refactor auth module following DRY principles
/run-in-new-tab Fix all failing tests in spec-reviewer plugin

Read the full file on GitHub · 94 lines

Changes

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.

  1. 5d ago First seen · 94 lines · 11 tokens per session scan A a7dccbf11787

Subscribe to this mod's changes

run-in-new-tab is a command published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 669 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 2026-08-30.