Claude Dispatcher — Development skill for Claude Code
Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.
How to install Claude Dispatcher
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Innovology/claude-dispatcher and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Dispatcher does
Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.
Alternatives in Development
- Zoetrope — Watch a Claude Code session as a live flow graph, in your terminal or your browser 584 ★
- Device Control Agent — You are an autonomous macOS agent with full control of this device via two CLI tools: - steer — GUI automation 250 ★
- Mulmoterminal — Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs 187 ★
README
Claude Dispatcher
**A terminal cockpit for running a factory of Claude Code sessions across all your repos.** Dispatch work to many repositories at once, then see — at a glance, on one screen — what's working, what shipped, and the one thing that's actually blocked waiting on you.
It sits **above** your repos, not inside any one of them. Every dispatcher is a real `claude` session in its own tmux; the cockpit is a fast, keyboard-driven viewer over all of them.

Why
You can run ten Claude Code sessions. You can't watch ten terminals. The cockpit collapses the whole fleet into one triage surface: it surfaces the blocked and the finished, keeps the busy ones out of your way, and hands the terminal straight to tmux when you want to jump in.
- One screen, the whole factory — dispatchers, PRs, deploys, backlog, usage and velocity across every repo and product.
- Real data, live — dispatch records +
git+gh+ Linear + Azure Boards, refreshed on an fsnotify watch and a poll. Nothing is mocked. - Keyboard-first — six lenses on the number keys, one key per action, a
:command palette, and?for the map. - Done means live — a feature stays open until it's actually deployed, not merely merged.
- Tokens, not dollars — built for a Claude subscription; usage speaks in tokens and effort.
Six lenses
Switch with the number keys. Each lens is a different question about the same factory.
| lens | the question it answers | |
|---|---|---|
1 |
triage | what is blocked, claims done, or waiting on me right now? |
2 |
products | how is each product (many repos) doing? enter opens one |
3 |
backlog | GitHub Issues · Linear · Azure Boards, in one list |
4 |
usage | 5-hour and weekly consumption vs my learned limits |
5 |
decisions | ADRs, and the decision sections written in each repo's own markdown |
6 |
* |
Related Skills
Ccd Worker
Use when this session is running as a ccd worker or dispatcher (CCD_HANDLE is set and you were told to act as
Dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atom
Mows Harness
A layered, self-hosted Claude Code harness: config + skills, unattended watchdogs, VPS web cockpit (Caddy/oaut
Makoto
When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deed
Contribution Fleet
Launch N opensource-contributor runs in parallel across different repos. Each run gets its own state directory
Fleet Init
Scan a repos directory and generate (or update) spring-fleet.config.json for the fleet.
Related Agents
Fleet Auditor
Use this agent for read-only sweeps across many repos at once — answering "which projects have X / are missing
Fleet Explorer
Topology-aware code explorer for a fleet of multi-repo Spring Boot microservices. Traces a request or feature
Regression Sentinel
Watch evaluation metrics over time for trends and regressions. Unlike verification-judge (validates single wor