graphite-merge-queue

graphite-merge-queue is a skill for Claude Code from pleaseai/claude-code-plugins. It costs 140 tokens per session (3,332 once invoked), scanned A, original, MIT.

A command set for operating Graphite's merge queue, which waits for required checks and then merges approved pull requests. It uses a label to add or remove pull requests from the queue and handles chains of related pull requests.

In plain words
What is it for?
Use it to enqueue or remove pull requests, monitor the queue, and manage merge ordering for Graphite stacks.
Why use it?
It makes queue status and queue membership explicit, reducing manual steps when merging stacked changes after checks pass.

Skill for Claude Code

Written for Claude Code: user-invocable 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 graphite plugin — 3 skills, 16 commands shipped together

Good fit Use it to enqueue or remove pull requests, monitor the queue, and manage merge ordering for Graphite stacks.

Compare 6 skills from other repositories ↓
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 pleaseai/claude-code-plugins
Claude Code
/plugin install graphite

Made for: Claude Code.

Or install graphite, the plugin that ships this one along with the rest of its 3 skills, 16 commands.

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 graphite-merge-queue

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pleaseai/claude-code-plugins/graphite-merge-queue"><img src="https://agentmods.dev/badge/skills/pleaseai/claude-code-plugins/graphite-merge-queue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,332 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 $0.00140 $0.03332
Opus 5 $0.00070 $0.01666
Sonnet 5 $0.00028 $0.00666
Haiku 4.5 $0.00014 $0.00333

Measured yesterday against content hash abbb88159f96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

graphite-merge-queue 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 yesterday.

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.

plugins/graphite/skills/graphite-merge-queue/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graphite Merge Queue — Label-Based Enqueueing

This skill covers the runtime operation of Graphite's merge queue: adding/removing the merge label, reading queue config from .please/config.yml, and reasoning about stacked-PR enqueue cascade behavior.

For one-time setup (enabling the queue, configuring branch protection, choosing rebase vs squash), use the graphite-setup skill instead.

Source docs (cite when proposing actions):

Mental model

  • The merge queue takes ownership of the merge once a PR is enqueued. Graphite rebases the PR onto trunk, reruns required CI, and merges only after CI passes.
  • One label = one queue ticket. Adding the configured merge label to a PR enqueues it. Removing the label dequeues it. There is no separate /queue command on Graphite's side — the label IS the queue API.
  • merge when ready: if the label is applied before the PR is approved or CI passes, Graphite enables "merge when ready" and queues automatically when the PR becomes mergeable.
  • Stacks cascade. Labeling a PR mid-stack also labels its descendants (upstack), and Graphite separately enqueues all ancestors (downstack) as queue dependencies — you cannot merge a parent without its children getting queued, and you cannot merge a child until its ancestors land. Removing the label cascades upstack in the same way (descendants drop out of the queue); downstack ancestors are unaffected.

Graphite stack terminology. Downstack = toward trunk (ancestors). Upstack = away from trunk (descendants). Label propagation cascades upstack; queue dependencies pull in downstack ancestors.

  • Fast-track is single-PR only. It does not apply to stacks. It still requires a rebase + CI rerun — it just jumps the queue position.
  • A Graphite account is required. If the user labeling the PR has no Graphite account, the queue removes the label and prompts for account creation. Treat that as "labeled by the wrong user," not a queue bug.

Read the full file on GitHub · 182 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. yesterday First seen · 182 lines · 140 tokens per session scan A abbb88159f96

Subscribe to this mod's changes

graphite-merge-queue is a skill published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 3,332 once invoked, about $0.0007 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 2026-09-07.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens