split

split is a command for Claude Code from pleaseai/claude-code-plugins. It costs 11 tokens per session (414 once invoked), scanned A, original, MIT.

A branch-splitting command that turns one branch into several smaller branches. A branch is a separate line of work in Git.

In plain words
What is it for?
Use it to split by existing commits, file paths, or selected sections of changed files. The resulting branches can form a stack of dependent changes.
Why use it?
It separates unrelated work that was accidentally combined, making each change easier to review and submit separately.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the graphite plugin — 3 skills, 16 commands shipped together

Good fit Use it to split by existing commits, file paths, or selected sections of changed files. The resulting branches can form a stack of dependent changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/pleaseai/claude-code-plugins/split
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.

agentmods badge for split

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/split"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/split.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 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 $0.00011 $0.00414
Opus 5 $0.00005 $0.00207
Sonnet 5 $0.00002 $0.00083
Haiku 4.5 $0.00001 $0.00041

Measured yesterday against content hash 3b9044900c2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

split 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/split.md · 30 lines

What it actually says

Divide the current branch into a stack of smaller branches. User input: $ARGUMENTS.

Modes

  • gt split --by-commit (-c) — split along existing commit boundaries. Each commit becomes its own branch. Only useful on a multi-commit branch.
  • gt split --by-file "<pathspec>" (-f) — peel off files matching the pathspec onto a new branch. Repeat -f for multiple patterns: gt split -f "*.json" -f "*.yaml".
  • gt split --by-hunk (-h) — interactive git add --patch-style hunk selection.

Steps

  1. Run gt ls and git log --oneline <trunk>.. so the user sees what's on the branch today.
  2. Decide the mode:
    • Multiple commits already, clean per-commit grouping → --by-commit.
    • Mixed files, easy to separate by path → --by-file.
    • Same files but distinct concerns → --by-hunk.
  3. Run gt split <mode>.
  4. Preserve the original branch name on one of the pieces if it already has a PR — GitHub PR branch names are immutable. Tell the user when this matters; Graphite usually prompts.
  5. After the split, run gt ls and consider gt submit --stack to open PRs for the new branches.

Notes

  • After splitting, the auto-restack runs for everything above the split point. Resolve conflicts the usual way.
  • If the user wants the opposite (combine branches), use /graphite:fold (into parent) or /graphite:squash (commits within one branch).
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 · 30 lines · 11 tokens per session scan A 3b9044900c2c

Subscribe to this mod's changes

split is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 414 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.