A Graphite command that creates a new Git branch above the current branch and records the current changes as one commit. Graphite tracks the branch as part of a stack of dependent branches.

Use it to start a stacked branch from working-tree changes, create an empty branch from another branch, and name the branch from a commit message.

It gives each logical change its own branch and commit, making a larger change easier to review in parts. It also preserves the order between dependent changes.

create — Command 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.

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/commands/pleaseai/claude-code-plugins/create/github.svg)](https://agentmods.dev/commands/pleaseai/claude-code-plugins/create)

Your own site

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

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 404 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	$0.00013	$0.00404
Opus 5	$0.00006	$0.00202
Sonnet 5	$0.00003	$0.00081
Haiku 4.5	$0.00001	$0.00040

Measured yesterday against content hash 2b90bac4f6c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

create 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/commands/create.md · 27 lines

What it actually says

Create a new Graphite-tracked branch on top of the current branch, carrying the working-tree changes as a single commit. User input: $ARGUMENTS.

Steps

Run git status --short to confirm there are changes to commit. If the tree is clean, ask the user whether they meant to run gt create --onto <branch> (create empty branch on top of another).
Run gt ls to show the current stack so the user can confirm where the new branch lands.
Build the command:
- If $ARGUMENTS looks like a commit message (contains spaces or :), use gt create -am "$ARGUMENTS" — Graphite derives the branch name from the message.
- If $ARGUMENTS is a single token, treat it as a branch name. Ask the user for a commit message, then run: gt create -am "<message>" $ARGUMENTS.
- If $ARGUMENTS is empty, ask the user for a commit message (or branch name) before proceeding.
Run the command and report the new branch and updated gt ls.

Key flags

-a, --all — stage every modified file (default for this command)
-m, --message <msg> — commit message (and source of the auto-generated branch name)
-p, --patch — interactive hunk staging instead of -a
--insert — insert this branch between the current branch and its children, restacking dependents
--onto <branch> — create on top of a different branch (useful with worktrees)
--ai — let Graphite suggest a branch name / message

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 · 27 lines · 13 tokens per session scan A 2b90bac4f6c9

Subscribe to this mod's changes

create is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 404 once invoked, about $0.0001 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.

Code review Commits Git and workflow

create

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Steps

Key flags

What this file has done since we first saw it

Other commands, from other repositories

review-diff

elegant-code-review

git

prp-commit

fix-comments

validate-pr-description