A guide to Graphite's command-line workflow for stacked pull requests, where each branch builds on the previous one and usually maps to one pull request. It covers creating, submitting, synchronising, and rearranging these branch stacks.

Use it to create stacked branches, submit a stack, restack it after changes, or split and combine work in a Graphite repository.

It provides the commands and rules needed to update related branches without losing Graphite's record of how they depend on one another.

graphite — Skill for Claude Code by pleaseai

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 pleaseai/claude-code-plugins --skill graphite

Clone the repo

git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pleaseai/claude-code-plugins/graphite/github.svg)](https://agentmods.dev/skills/pleaseai/claude-code-plugins/graphite)

Your own site

<a href="https://agentmods.dev/skills/pleaseai/claude-code-plugins/graphite"><img src="https://agentmods.dev/badge/skills/pleaseai/claude-code-plugins/graphite/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pleaseai/claude-code-plugins/graphite"><img src="https://agentmods.dev/badge/skills/pleaseai/claude-code-plugins/graphite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,334 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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.02334
Opus 5	$0.00054	$0.01167
Sonnet 5	$0.00022	$0.00467
Haiku 4.5	$0.00011	$0.00233

Measured yesterday against content hash 727b432681bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

graphite 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/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graphite CLI (`gt`) — Stacked PR Workflow

Invoke the CLI as gt (not graphite). A stack is a chain of branches where each builds on its parent and maps to one PR.

When the user is in a Graphite repo (.git/.graphite_repo_config present) or mentions stacked PRs / gt / Graphite, prefer gt over raw git for branch creation, rebasing, and pushes. Plain git still works for staging, diffing, logs, and inspection.

Core mental model

One commit per branch. Stack additional changes by creating new branches on top, not new commits on the same branch.
Trunk is main (or whatever gt init selected). Stacks are rooted on trunk.
gt knows the parent of every tracked branch. It uses that metadata to restack automatically when ancestors change.
Do not use raw git rebase to move tracked branches. It can wipe Graphite metadata. Use gt modify, gt restack, or gt move instead.

The golden path: create → submit

# Make changes, then:
gt create -am "feat: add activity feed API"   # stage all, commit, new branch
# More changes for the next layer:
gt create -am "feat: render feed in UI"       # creates branch on top of previous
gt submit --stack                              # push all branches, open PRs

gt create [name] creates a branch from the current HEAD with the staged changes already committed. With -a it stages all changes; with -m "..." it sets the commit message; combined -am "..." is the common form.
gt c is the alias for gt create.
gt submit pushes the current branch and downstack; gt submit --stack (alias gt ss) pushes every branch in the current stack and opens/updates PRs for each.

Viewing the stack

gt log         # full tree with branches, PRs, worktree paths
gt ls          # compact view (alias for `gt log short`)

The filled circle (◉) marks the current branch. Always run gt ls before any restack/move operation to confirm parent relationships.

Navigating the stack

Read the full file on GitHub · 197 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.

yesterday First seen · 197 lines · 108 tokens per session scan A 727b432681bb

Subscribe to this mod's changes

graphite is a skill published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,334 once invoked, about $0.0005 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.

Git and workflow

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