# Multi Agent Coding

Use when the user needs a coding task done - code written, changed, fixed, tested or...

- Repository: https://github.com/EverMind-AI/Raven (5958 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add EverMind-AI/Raven --skill multi-agent-coding -g -a claude-code -y`
Codex: `npx skills add EverMind-AI/Raven --skill multi-agent-coding -g -a codex -y`
Cursor: `npx skills add EverMind-AI/Raven --skill multi-agent-coding -g -a cursor -y`
Gemini CLI: `npx skills add EverMind-AI/Raven --skill multi-agent-coding -g -a gemini-cli -y`

## Description

Use when the user needs a coding task done - code written, changed, fixed, tested or reviewed - through its follow-ups, and when a coding agent reports its quota or usage limit used up.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Coding with sub-agents

## 1. A coding agent for the work

Coding work goes to a coding agent on the roster: the one the user named, otherwise one
the `## Delegation` section says owns coding, otherwise one whose description says it
writes or edits code. When a Worker Table is bound, `subagent` takes worker labels
instead: pick the worker whose brief covers the coding work. When none does, tell the user
and ask how to go on rather than writing the code yourself or sending it to an agent
outside the enum.

## 2. One instance per task

An instance is one conversation with one agent, named by the `instance` handle.

- A new task gets a new instance, never an earlier task's handle, which would carry that
  task's context into it. That holds for a task built on a finished one, such as docs for
  a finished feature: it starts fresh, with the earlier task's output file (section 3).
- A follow-up on an unfinished task - a correction, a bug in what it did, "keep going" -
  goes to that task's instance: same `subagent`, same `instance`, a new `node_id`. The
  agent keeps its context, so the prompt carries the new request in the user's words.
- Send a follow-up only once the instance's running dispatch has returned: sent sooner, it
  can start a separate conversation without that context.

## 3. Results by file

When a task needs what another produced, put that task's output file in its prompt -
`{{ <node_id>.output_path }}` of its last dispatch - instead of retelling the result. The
file is the agent's report, not the code, so also say where the code is (section 4).

## 4. A worktree per task in a shared project

The rest: https://github.com/EverMind-AI/Raven/blob/HEAD/raven/memory_engine/skills/multi-agent-coding/SKILL.md