A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.
# Add to your Claude Code skills
git clone https://github.com/bassimeledath/dispatchDispatch 10x's Claude Code's effective context window size. Instead of filling your session with implementation, /dispatch turns it into a lightweight orchestrator — work fans out to background agents, each with their own full context window.
Without dispatch: You ask Claude to review code, refactor a module, write tests, and update docs. Each task fills the context window. By task 3, Claude is losing track. By task 5, you're starting a new session.
With dispatch: You describe all 5 tasks. Workers execute in parallel with fresh contexts. Your main session stays lean. Questions surface to you when needed — no polling, no context lost.
/dispatch use sonnet to find better design patterns for the auth module
Dispatch inverts the usual model: the main session becomes a mediator, not the thinker. It writes a checklist and hands it off. The actual implementation — reading code, reasoning about edge cases, writing tests — happens in fresh worker contexts that each get their own full window. Your main session's context is preserved for orchestration.
With claude --background, multiple terminals, or fire-and-forget agent runners — you are the orchestrator. You track what's running, check on progress, notice failures, and context-switch between outputs.
With dispatch, the AI dispatcher tracks all workers, surfaces questions, reports completions, handles errors, and offers recovery. Your job reduces to: (a) describe what you want, (b) answer questions when asked.
When a /dispatch worker gets stuck, it doesn't silently fail or hallucinate. It — the dispatcher surfaces it to you, you answer, and the worker continues . No restart, no re-explaining, no lost work.
No comments yet. Be the first to share your thoughts!
Worker is asking: "requirements.txt doesn't exist. What feature should I implement?"
> Add a /health endpoint that returns JSON with uptime and version.
Answer sent. Worker is continuing.
The moment a worker is dispatched, your session is immediately free. Dispatch another task. Ask a question. Write code. Workers run in parallel and results arrive as they complete.
Mix models per task. Claude for deep reasoning, GPT for broad generation, Gemini for speed. Reference any model by name — if it's not in your config, /dispatch auto-discovers and adds it. If multiple models are named in one prompt, dispatch uses the last one mentioned. If no model is specified, dispatch confirms your default before proceeding.
/dispatch use opus to review this PR for edge cases
/dispatch use gemini to refactor the config parser — it's getting unwieldy
Requires Claude Code as your host session. Dispatch is a skill that runs inside Claude Code — the host plans tasks and spawns workers. Other CLIs like Cursor and Codex work as workers only (background agents that execute subtasks).
npx skills add bassimeledath/dispatch -g # user-level (all projects)
npx skills add bassimeledath/dispatch # project-level (team-shared)
/dispatch task descriptionExample — pre-launch sweep for a fullstack SaaS app:
/dispatch we launch Thursday, need a full pre-launch sweep:
1) security audit the auth flow (JWT, sessions, password reset) and the
stripe payment integration. use opus, do it in a worktree
2) performance - load test the top 5 API endpoints, find N+1 queries,
check db indexes on users/orders/products tables. sonnet in a worktree
3) frontend audit - accessibility (WCAG 2.1 AA), bundle size, flag any
components missing error boundaries. dispatch sonnet
4) generate OpenAPI specs for every endpoint that's missing one. use gemini
5) error handling audit - find uncaught exceptions, missing try/catch,
inconsistent error response formats across all API routes. sonnet, worktree
ask me if anything is unclear. security is highest priority - flag
anything critical immediately
Dispatch reads the prompt, creates 5 plans, and fans out:
All 5 workers dispatched with their monitors. Here's the summary:
Security (worktree):
● security-audit — Opus 4-6 (worktree): Full auth + payment security review
Performance (worktree):
● perf-audit — Sonnet 4-6 (worktree): API load testing + DB index review
Frontend (single worker):
● frontend-audit — Sonnet 4-6: Accessibility, bundle size, error boundaries
Docs (single worker):
● api-docs — Gemini 2.5 Flash: Generate missing OpenAPI specs
Error handling (worktree):
● error-handling — Sonnet 4-6 (worktree): Uncaught exceptions + error format audit
All running in background. Five workers, three models, three worktrees —
your session wrote five checklists and is idle. Dispatch more work or say
"status" anytime.
Run /dispatch with no arguments at the beginning of a session to pre-load your config:
/dispatch
This reads ~/.dispatch/config.yaml into the dispatcher's context so subsequent dispatches are faster and don't need confirmation prompts. It's a good habit to add as a Claude Code memory so you remember to do it each session:
"Run /dispatch at the start of each session to warm up the config."
On first run, /dispatch auto-detects your CLIs (claude, agent, codex), discovers available models, and generates ~/.dispatch/config.yaml. No manual config needed.
Three sections in ~/.dispatch/config.yaml:
Backends — CLI commands for each provider:
backends:
claude:
command: >
env -u CLAUDE_CODE_ENTRYPOINT -u CLAUDECODE
claude -p --dangerously-skip-permissions
cursor:
command: >
agent -p --force --workspace "$(pwd)"
codex:
command: >
codex exec --full-auto -C "$(pwd)"
Models — one line each, mapped to a backend:
models:
opus: { backend: claude }
sonnet: { backend: claude }
gpt-5.3-codex: { backend: codex }
gemini-3.1-pro: { backend: cursor }
Aliases — named shortcuts with optional role prompts:
aliases:
security-reviewer:
model: opus
prompt: >
You are a security-focused reviewer. Prioritize OWASP Top 10.
Host (required):
claude)Workers (optional — for multi-model dispatch):
agent)codex)Skills CLI (recommended):
npx skills update
This updates all installed skills to their latest versions. Run npx skills check first to see what's changed.
Symlinked to a local clone? If your .claude/skills/dispatch is a symlink to a local git checkout, just pull:
cd /path/to/your/dispatch && git pull
Changes are picked up immediately — Claude Code hot-reloads skills from disk.
The dispatcher reads your config, creates a checklist plan, then spawns a background worker and monitor. The worker executes each item and checks it off. If it needs clarification, it writes a question to the IPC directory — the monitor detects it and notifies the dispatcher, which surfaces it to you and relays your answer back, all without the worker losing context.
MIT