---
title: "stacked-planning"
description: "Plans and lands work that spans several pull requests as ordered stacks, with a PR size gate and a stack overlap check"
canonical: https://agentpluginsdirectory.com/plugins/stacked-planning
last-updated: 2026-09-28
---

# stacked-planning
Plans and lands work that spans several pull requests as ordered stacks, with a PR size gate and a stack overlap check
- Slug: stacked-planning
- Publisher: wmxscott
- Repository: https://github.com/wmxscott/ai-toolkit
- Manifest: plugins/stacked-planning/plugin.json
- License: MIT
- Category (editorial): other
- Skills: 4 (authoring-stacked-plans, implementing-stacked-plans, landing-changes, stacked-planning)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-13
- Repository last pushed: 2026-09-27
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/stacked-planning
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What stacked-planning does, in the publisher's words

> [!WARNING] > Experimental. The skills, the plan format and the gates' configuration may still change in ways that break existing plans and configs. Expect rough edges, and review what the agent plans and lands before relying on it.

Plans and lands work that is too big for one pull request. The work is split into stacks of small PRs, each stack a linear chain, written down as a plan before the first PR. The agent then implements the plan one PR at a time, with every PR checked against a size gate and, when two stacks run at once, an overlap gate.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/wmxscott/ai-toolkit/HEAD/plugins/stacked-planning/README.md

## Skills

- authoring-stacked-plans: Use when work is already known to span more than one pull request and has to be decomposed into an ordered stack of them, when a change has passed the PR size cap and is still growing, or when a stack is nearing a fourth PR with no written plan. Covers the decomposition and the plan artifact record…
- implementing-stacked-plans: Use when a plan in docs/plans/ already defines its work as stacks of PRs and the user asks to implement, execute, or continue it, or names one of its stacks or phases, orchestrates one subagent per PR in its own worktree, reviewing and landing each before dispatching the next. Orchestration above t…
- landing-changes: Use when starting work on a branch or worktree, when about to commit, when opening a pull request, or while a pull request's checks are still running, the branch, worktree and PR discipline every change goes through. Mechanics only: it does not judge whether the work is done, review the change, or…
- stacked-planning: Use only when work will land as more than one pull request and it is genuinely unclear whether to write the stacked plan or execute one that already exists, a router between authoring-stacked-plans and implementing-stacked-plans. Not a general entry point for planning or design, and not for a chang…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.