capitalthought

Multipov Plan — AI skill for Claude Code

AI community

Run a multi-agent design-doc review on $ARGUMENTS (path to a markdown design doc, typically docs/plans/YYYY-MM-DD-topic-design.md) via the multipov.ai MCP server.

How to install Multipov Plan

Installs to ~/.claude/skills/capitalthought-multipov-docs-multipov-plan/SKILL.md

Terminal

mkdir -p ~/.claude/skills/capitalthought-multipov-docs-multipov-plan && curl -fsSL https://raw.githubusercontent.com/capitalthought/multipov-docs/HEAD/skills/multipov-plan.md -o ~/.claude/skills/capitalthought-multipov-docs-multipov-plan/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Multipov Plan does

Run a multi-agent design-doc review on `$ARGUMENTS` (path to a markdown design doc, typically `docs/plans/YYYY-MM-DD-topic-design.md`) via the multipov.ai MCP server.

This is the **plan** sibling of `/multipov-code` — use it BEFORE you write any code, to pressure-test the architecture while fixes are still cheap.

Architecture (as of 2026-04-13)

This skill **calls the multipov.ai MCP server** — it no longer dispatches local reviewer agents, doesn't shell out to `llm-review.ts`, doesn't

Alternatives in AI

Fusion Plan — OMC interview (interactive) → 3-round Opus 4.8 + GPT-5.5 fusion deepening → concise .omc/plans/ output → revie 468 ★
Load AI Docs — Load documentation from their respective websites into local markdown files our agents can use as context 296 ★
LLM Wiki Compiler — Claude Code plugin that compiles markdown knowledge files into a topic-based wiki 224 ★