A tool for handing a task to a new Claude session in its own Git worktree, which is a separate working copy of a repository, and its own branch. The task can be opened in a Rex tab or herdr workspace with permissions set in advance.

It is for sending a change to its own branch and pull request, including writing the new session's context and granting the access it needs.

It lets the current session continue while another session works independently, reducing branch conflicts and interruptions.

dispatch — Skill for Claude Code by bendrucker/claude

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.

Any agent

npx skills add bendrucker/claude --skill dispatch

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install dispatch, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/dispatch/github.svg)](https://agentmods.dev/skills/bendrucker/claude/dispatch)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/dispatch"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/dispatch/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/dispatch"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/dispatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,463 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.01463
Opus 5.5	$0.00037	$0.00585
Sonnet 5.5	$0.00018	$0.00293
Haiku 4.5	$0.00009	$0.00146

Measured 4d ago against content hash 7449cc67eb02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dispatch 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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/dispatch.test.ts, scripts/dispatch.ts, scripts/ledger.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dispatch/skills/dispatch/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatch

Start a separate Claude session that takes a task through to its own PR while this session keeps working, or follows up on a branch or PR that already exists. The script checks the branch out in a worktree with wt, writes the session's .claude/settings.local.json, and launches claude --name <name> <prompt> in the multiplexer hosting this session.

Write the Prompt

Write the prompt to a file under tmp/ from what this conversation already knows. The dispatched session starts with no context from this one, so state the goal, what is already ruled out, and the completion criterion, and name any files this conversation has already found. It reads the repository itself, so go straight from the request to the prompt without exploring the code first. Keep it under 128KB. For larger material, point the session at a file. The script appends this session's name, its Rex block or herdr pane, and the address another machine uses for this one. The dispatched session sends its replies with SendMessage to that name.

Flags

--help, run for this session:

!bun ${CLAUDE_SKILL_DIR}/scripts/dispatch.ts --help

Grant Permissions

Pass the permissions the task needs with --allow, --sandbox-write, and --settings-json so the session runs without prompting for them. The script merges them into the worktree's .claude/settings.local.json, keeping existing keys and skipping array entries already present. It refuses to write when that file is not git-ignored.

Pick the Multiplexer

Pick by how much the task needs the user along the way:

bg, a claude --bg session with no terminal: a small, self-contained change with a clear completion criterion, few questions, and little for the user to read before the PR. Pass --mux bg.
A tab (rex or herdr): exploratory work, or work that needs decisions, reading, or review as it goes.

--help above names the tab multiplexer --mux defaults to. When the task calls for a tab and --help says to pass --mux instead, ask the user with AskUserQuestion whether to use rex or herdr.

Read the full file on GitHub · 78 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

4d ago Changed · +3 lines 7449cc67eb02
6d ago Changed · +1 lines 51f02683cbc0
7d ago Changed · -2 lines 4a1fa3b406c1
10d ago Changed 090f471808b5
11d ago First seen · 76 lines · 92 tokens per session scan A 0a7524e02349

Subscribe to this mod's changes

dispatch is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,463 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-30.

Building agents Claude Code Commits Git and workflow claude-code-plugin

dispatch next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dispatchbendrucker/claude	Skill	18	today	MIT	A	92	Claude Code
branch-and-worktree-workflowcbrock84/headcount	Skill	2.6k	22d ago	MIT	A	70	Claude Code
unslop-commitMohamedAbdallah-14/unslop	Skill	183	yesterday	MIT	A	139	Claude Code
evolve-lite:unpublishAgentToolkit/altk-evolve	Skill	136	today	Apache-2.0	A	23	Claude Code, Codex
commitsuxrobGM/jobpilot	Skill	111	today	MIT	A	38	Claude Code
signing-preflightavelikiy/great_cto	Skill	113	today	MIT	A	105	Claude Code
releasegtapps/hermitd	Skill	84	today	MIT	A	104	Claude Code, Codex