stacking-pull-requests

stacking-pull-requests is a skill for Claude Code, Codex from kamiazya/whiteboard. It costs 121 tokens per session (1,717 once invoked), scanned A, original, Apache-2.0.

A procedure for managing dependent GitHub pull requests as a stack, where each branch builds on the one below it. A stacked pull request separates a large change into ordered, reviewable layers.

In plain words
What is it for?
It is for installing and using the gh-stack extension, creating dependency-ordered branches, rebasing them, and merging the stack in the required order.
Why use it?
It keeps changes that must land in sequence organized while the main branch changes and the individual layers are reviewed.

Skill for Claude CodeCodex

Part of the whiteboard plugin — 19 skills, 18 agents, 3 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/kamiazya/whiteboard/stacking-pull-requests
Any agent
npx skills add kamiazya/whiteboard --skill stacking-pull-requests
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code, Codex.

Or install whiteboard, the plugin that ships this one along with the rest of its 19 skills, 18 agents, 3 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stacking-pull-requests

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamiazya/whiteboard/stacking-pull-requests.svg)](https://agentmods.dev/skills/kamiazya/whiteboard/stacking-pull-requests)
Your own site
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/stacking-pull-requests"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/stacking-pull-requests.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.01717
Opus 5 $0.00060 $0.00859
Sonnet 5 $0.00024 $0.00343
Haiku 4.5 $0.00012 $0.00172

Measured 5d ago against content hash 0d095461695c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

stacking-pull-requests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/stacking-pull-requests/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stacking pull requests

gh stack (GitHub's stacked pull requests, public preview since 2026-07-30) turns a chain of dependent branches into one reviewable stack: each PR shows only its own layer's diff, reviewers work in parallel, and merging is atomic up to whichever PR you pick.

Whether to stack at all is a dev-flow.md decision, not this skill's. This skill is the operating procedure once the answer is yes.

Prerequisite

gh extension install github/gh-stack

One-time per machine. gh stack --help lists every subcommand; the ones below are the whole day-to-day surface.

Stack order is not a choice here

This repo's dependency direction is already fixed by .claude/rules/architecture-map.md, and a stack must follow it — a lower layer cannot depend on a higher one:

model → codec / canvas-render / ports → workspace
             → server-core → mcp-server | apps/web

The composition roots (mcp-server, apps/web) are therefore always at the TOP of a stack, never the bottom. That is what makes "split the MCP, CLI and web parts into separate PRs" mechanical rather than a judgement call: the shared package goes first, the surface that consumes it goes above it.

Two consequences worth stating:

  • Each PR loads its own layer's review criteria. .claude/rules/package-*.md are path-scoped, so a model PR carries the Zod-discipline rules while an apps/web PR carries the accessibility and reachability ones. The per-layer review concerns follow the stack for free.
  • The bottom layers answer userReach with foundation:, and the named follow-up is the PR above. That is the strongest form of that sentinel — a reviewable reference instead of "wired later".

Creating a stack

Bottom-up, one branch per layer:

gh stack init render-scene-digest mcp-export-digest   # bottom first, then above it
gh stack view                                          # confirm the order

Work on the bottom branch, commit, then move up:

Read the full file on GitHub · 165 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 165 lines · 121 tokens per session scan A 0d095461695c

Subscribe to this mod's changes

stacking-pull-requests is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 121 tokens to every session and 1,717 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens