# efficient-dispatch

A skill that keeps judgement work on the strong model, sends mechanical subagent tasks to a named cheaper model, and checks the routing against your own logs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 121
- Author: Necmttn
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Necmttn/ax/tree/HEAD/skills/efficient-dispatch/SKILL.md
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/skills/efficient-dispatch

## What it does

Two splits matter here. The main model orchestrates and reviews; subagents take the mechanical load. The one that moves your bill is the tier of each dispatch. Well-specified implementation, bulk edits and search go out with an explicit `model: sonnet`, pure locate work with haiku. Anything that needs judgement — review, design, audit — stays on the strong model, because a cheap reviewer misses real bugs.

Forget the `model:` field on an implement dispatch and it silently inherits the expensive one. The route-dispatch hook only advises; Claude hooks cannot force a model onto a subagent dispatch, they just inject context. So explicit `model:` on every call is the actual enforcement. The routing table lives at `~/.ax/hooks/routing-table.json` and is rebuilt with `ax dispatches compile-routing`.

Context isolation is the other reason to dispatch. A screenshot read into the main thread stays in the window and gets re-sent on every later turn. When you want a verdict rather than the bytes, a subagent returns text and the image dies with its context. Tight visual iteration — look, tweak, look again — is the case where this loses: the round-trips cost more than they save. The skill targets subagent-heavy work and stays out of single-shot questions and small tasks with no dispatching.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Necmttn/ax --skill efficient-dispatch -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/efficient-dispatch/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/efficient-dispatch/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Necmttn/ax --skill efficient-dispatch -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/efficient-dispatch/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Necmttn/ax --skill efficient-dispatch -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/efficient-dispatch/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Necmttn/ax efficient-dispatch
```

2. **Manually: put the files in place**
- File: `.github/skills/efficient-dispatch/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Necmttn/ax --skill efficient-dispatch -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Necmttn/ax --path skills/efficient-dispatch
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/efficient-dispatch/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add Necmttn/ax --skill efficient-dispatch -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Necmttn/ax/tree/HEAD/skills/efficient-dispatch/SKILL.md

## When to use it
- cut token spend on bulk mechanical edits
- send a mechanical task to a cheaper model
- keep review on the strong model without losing bugs
- move screenshot reading out of the main context
- see how spend splits between the main loop and subagents

## Example prompts
- Split this into independent slices and run them as sonnet subagents, keep the review yourself
- Run `ax dispatches --candidates` and show me where I forgot to set a model
- Read the screenshots in `screens/` and return a text verdict on what misses the spec

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [necmttn/ax](https://affpapa.org/en/nevibecode/by/necmttn/ax.md) — 3 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md