agentmods.dev

stacked-prs

stacked-prs is a skill for Claude Code from bengous/claude-code-plugins. It costs 114 tokens per session (2,898 once invoked), scanned A, original, MIT.

A GitHub workflow for stacked pull requests, where each branch and pull request builds on the one below it. It uses the GitHub CLI to create, update, sync, repair, and land the stack.

In plain words
What is it for?
Use it to split a large change into dependent pull requests, push and submit the stack, update branch bases, create per-layer worktrees, and land the stack together.
Why use it?
Large changes can be hard to review when they arrive as one pull request. Stacking keeps each change as a smaller reviewable diff while preserving their order.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the github-flow plugin — 8 skills shipped together

not rated 6repo changed 21d ago A scan 114 tokens original MIT

Good fit Use it to split a large change into dependent pull requests, push and submit the stack, update branch bases, create per-layer worktrees, and land the stack together.

Compare 6 skills from other repositories ↓
View source ↗ bengous/claude-code-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bengous/claude-code-plugins
Claude Code
/plugin install github-flow

Made for: Claude Code.

Or install github-flow, the plugin that ships this one along with the rest of its 8 skills.

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 stacked-prs

README.md
[![agentmods](https://agentmods.dev/badge/skills/bengous/claude-code-plugins/stacked-prs/github.svg)](https://agentmods.dev/skills/bengous/claude-code-plugins/stacked-prs)
Your own site
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/stacked-prs"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/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 stacked-prs

Your own site · 80×15
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/stacked-prs"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/stacked-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,898 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 $0.00114 $0.02898
Opus 5.5 $0.00046 $0.01159
Sonnet 5.5 $0.00023 $0.00580
Haiku 4.5 $0.00011 $0.00290

Measured 21d ago against content hash d15bde336cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 21d 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.

github-flow/skills/stacked-prs/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stacked PRs with gh stack

A stack is a chain of branches above the trunk, one PR per branch, each PR based on the branch below it. Each PR shows only its own diff. Nothing merges before the end: the stack lands in one operation, bottom to top. Local tracking lives in .git/gh-stack (never versioned); the stack object lives on GitHub.

trunk
 └── layer-1      PR → trunk
      └── layer-2 PR → layer-1
           └── …  PR → previous layer

The cycle

Command Effect
gh stack init [branches…] [--base <trunk>] Creates the stack. Adopts existing branches, bottom to top.
gh stack add <branch> -m "msg" [-A|-u] Branches from the current top and commits what is staged. -A stages everything, untracked included; -u tracked files only.
gh stack submit [--auto] [--open] Pushes everything, creates the missing PRs with the right base, updates existing bases, creates or updates the GitHub stack.
gh stack push Pushes active branches, --force-with-lease branch by branch, not atomic: a rejected branch does not cancel the others. Skips merged and queued branches. Opens no PR.
gh stack view [--short|--json] State: ✓ merged, ◎ queued, ○ open, ⚠ needs rebase.
gh stack sync [--prune] Fetches, reconciles with GitHub, fast-forwards the trunk, cascade-rebases, pushes atomically with --force-with-lease. Creates no PR.
gh stack rebase [--downstack|--upstack|--no-trunk] Cascade rebase: each layer receives the tip of the previous one, after a trunk fetch unless --no-trunk. --continue after conflicts, --abort restores everything.
gh stack merge [n] [--merge|--squash|--rebase] [--yes] Atomic landing, all or nothing, up to the chosen PR. One method for the whole operation, never per PR. --squash squashes each PR into one commit, not the stack into one: three layers land as three commits, each suffixed (#N). --rebase keeps every commit of every layer, in order. With a merge queue, the stack joins the queue and lands when the queue processes it.
gh stack checkout <n|PR|URL|branch> Fetches a stack from GitHub, even one never tracked locally.
gh stack modify TUI: drop, fold, insert, reorder, rename, applied together on confirm. Then submit when PRs are affected.
gh stack link <n|branch> <branch…> Stacks without local tracking; pushes the branches and opens the missing PRs. n first appends to the top of stack n. Two arguments minimum: it cannot create a one-PR stack.
gh stack unstack [--local] Undoes the stack on GitHub, locally, or both.
up, down, top, bottom, trunk, switch Navigation inside the stack.

Read the full file on GitHub · 109 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. 21d ago Changed d15bde336cef
  2. 23d ago Changed c5190a5ea5e2
  3. 1mo ago Changed 3ed15fe8c9cd
  4. 2mo ago First seen · 109 lines · 114 tokens per session scan A b8985f0befc2

Subscribe to this mod's changes

stacked-prs is a skill published in the GitHub repository bengous/claude-code-plugins (6 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 2,898 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-12.

Claude CodeCommitsGit and workflowautomationdeveloper-toolsworkflow
Related

stacked-prs compared with skills from other repositories

stacked-prs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
stacked-prsbengous/claude-code-pluginsSkill6yesterdayMITA114Claude Code
development-workflowathola/claude-night-marketSkill350yesterdayMITA20Claude Code
git-workflowvstorm-co/pydantic-deepagentsSkill1.1k12d agoMITA17Claude Code, Codex
stepwise-task-executionmakifbaysal/tasktrooperSkill122todayApache-2.0A33Claude Code, Codex
incremental-commitsmakifbaysal/tasktrooperSkill122todayApache-2.0A31Claude Code, Codex
ship-itsmallnest/goal-workflowSkill3001mo agoMITA96Claude Code
git-expertpersonamanagmentlayer/pclSkill4416d agoApache-2.0A57Claude Code