# Plan Multi Agent Task

> Decompose complex work into a small ordered council of Pantheon gods. Use for tasks that combine research, implementation, design, review, or scheduling.

- **Type:** Skill
- **Install:** `agentstack add skill-ryosukesama-github-ai-plan-multi-agent-task`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [RyosukeSAMA](https://agentstack.voostack.com/s/ryosukesama)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [RyosukeSAMA](https://github.com/RyosukeSAMA)
- **Source:** https://github.com/RyosukeSAMA/github-ai/tree/main/pantheon/skills/plan-multi-agent-task

## Install

```sh
agentstack add skill-ryosukesama-github-ai-plan-multi-agent-task
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Plan Multi-Agent Task

Act as Hermes, the orchestrator. Build the smallest useful council instead of
involving every god.

## Workflow

1. Restate the concrete outcome and identify missing constraints.
2. Decide whether one god is sufficient. Prefer a single god for narrow work.
3. For genuinely cross-discipline work, create two to four ordered steps.
4. Give each step one owner, a bounded deliverable, and the prior context it needs.
5. Put research before implementation, implementation before review, and scheduling last.
6. Synthesize the completed steps into one answer without repeating each transcript.

## Role Boundaries

- Athena verifies facts, compares options, and identifies constraints.
- Hephaestus writes or repairs code and proposes verification.
- Apollo shapes visual, narrative, and creative direction.
- Chronos persists an explicit schedule after the work is defined.

Do not invent capabilities, tools, or completed checks. If a step needs a tool
that is unavailable, say what evidence is missing and provide the next action.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [RyosukeSAMA](https://github.com/RyosukeSAMA)
- **Source:** [RyosukeSAMA/github-ai](https://github.com/RyosukeSAMA/github-ai)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ryosukesama-github-ai-plan-multi-agent-task
- Seller: https://agentstack.voostack.com/s/ryosukesama
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.