mav-stacked-prs

mav-stacked-prs is a skill for Claude Code from thermiteau/maverick. It costs 54 tokens per session (1,692 once invoked), scanned A, original, Apache-2.0.

A guide for stacked pull requests, where one branch and pull request are built on top of another unmerged pull request. It also explains how to move the dependent pull request back to the normal base branch after the first one merges.

In plain words
What is it for?
Use it when a story depends on an unfinished sibling story, to decide whether to stack branches and to retarget the dependent pull request safely after its parent lands.
Why use it?
It helps teams work on dependent changes without waiting for earlier work to merge. The retargeting step prevents the dependent changes from becoming detached or merged incorrectly.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the maverick plugin — 41 skills, 5 agents, 5 hooks shipped together

Good fit Use it when a story depends on an unfinished sibling story, to decide whether to stack branches and to retarget the dependent pull request safely after its parent lands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thermiteau/maverick/mav-stacked-prs
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.

Any agent
npx skills add thermiteau/maverick --skill mav-stacked-prs
Clone the repo
git clone --depth 1 https://github.com/thermiteau/maverick

Made for: Claude Code.

Or install maverick, the plugin that ships this one along with the rest of its 41 skills, 5 agents, 5 hooks.

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 mav-stacked-prs

README.md
[![agentmods](https://agentmods.dev/badge/skills/thermiteau/maverick/mav-stacked-prs/github.svg)](https://agentmods.dev/skills/thermiteau/maverick/mav-stacked-prs)
Your own site
<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-stacked-prs"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-stacked-prs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mav-stacked-prs

Your own site · 80×15
<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-stacked-prs"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-stacked-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,692 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00054 $0.01692
Opus 5 $0.00027 $0.00846
Sonnet 5 $0.00011 $0.00338
Haiku 4.5 $0.00005 $0.00169

Measured 11d ago against content hash e49d56e60214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mav-stacked-prs 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 11d 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.

skills/mav-stacked-prs/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stacked PRs

When story B depends on story A and A's PR isn't merged yet, B branches from A's branch and opens a PR whose base is feat/A-… rather than the story base branch. This is a stacked PR. It lets B progress without waiting for A to merge, and is essential for throughput inside an epic.

Stacking is safe when it is paired with a retarget guard that moves B's PR base back to the story base as soon as A lands. Without the retarget guard, a specific merge-order sequence can orphan B's commits — see the failure mode at the bottom of this document.

Resolve the story base once at the start of any stacking operation:

STORY_BASE=$(uv run maverick git-workflow story-base)

When to stack, when not to

digraph stack_decide {
    "Depends on sibling story?" [shape=diamond];
    "Sibling PR open but unmerged?" [shape=diamond];
    "Stack — branch from sibling" [shape=box];
    "Default — branch from $STORY_BASE" [shape=box];

    "Depends on sibling story?" -> "Sibling PR open but unmerged?" [label="yes"];
    "Depends on sibling story?" -> "Default — branch from $STORY_BASE" [label="no"];
    "Sibling PR open but unmerged?" -> "Stack — branch from sibling" [label="yes"];
    "Sibling PR open but unmerged?" -> "Default — branch from $STORY_BASE" [label="no — sibling already merged"];
}
Situation Stack? Why
No cross-story deps No Default branch is fine
Sibling already merged No Branch from default — clean base
Sibling PR open, you need its code to compile/test Yes Stack on the sibling branch
Sibling PR open, you only need it logically but don't import Yes Stack anyway — guards against logical surprises
Sibling PR ejected (labelled needs-human) No — block instead You should have been excluded from the wave

Creating a stacked branch

Fetch the sibling branch before branching off it — another instance may have pushed further commits:

git fetch origin feat/140-bootstrap-provider
git worktree add .maverick/worktrees/feat__142-admin-guard \
    -b feat/142-admin-guard-bootstrap \
    origin/feat/140-bootstrap-provider

Read the full file on GitHub · 173 lines

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. 11d ago First seen · 173 lines · 54 tokens per session scan A e49d56e60214

Subscribe to this mod's changes

mav-stacked-prs is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,692 once invoked, about $0.0003 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 2026-08-30.