split-branch

split-branch is a skill for Claude Code from motlin/claude-code-plugins. It costs 34 tokens per session (628 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a branch with several commits into separate branches, each containing one commit.

In plain words
What is it for?
Use it to identify the branch's commits since a base branch, create descriptive branch names, and split the work into single-commit branches.
Why use it?
It makes individual changes easier to review, merge, or work on independently without changing the content of those commits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the git plugin — 12 skills shipped together

Good fit Use it to identify the branch's commits since a base branch, create descriptive branch names, and split the work into single-commit branches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/motlin/claude-code-plugins/split-branch
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 motlin/claude-code-plugins --skill split-branch
Clone the repo
git clone --depth 1 https://github.com/motlin/claude-code-plugins

Made for: Claude Code.

Or install git, the plugin that ships this one along with the rest of its 12 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 split-branch

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/split-branch"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/split-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 628 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 $0.00034 $0.00628
Opus 5.5 $0.00014 $0.00251
Sonnet 5.5 $0.00007 $0.00126
Haiku 4.5 $0.00003 $0.00063

Measured 9d ago against content hash e06ab6511953, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

split-branch 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 9d 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.

plugins/git/skills/split-branch/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Split Branch

Split the current branch into one branch per commit. Never delete, modify, or force-push the original branch or any existing branch.

Use the code:cli skill.

Base Branch and Commits

Use the base branch the user named. Otherwise, in order: the upstream tracking branch, then main or master, whichever exists. If none exists, ask.

git log --oneline --reverse <base-branch>..HEAD

With 0 commits there is nothing to split; with 1, splitting isn't useful. Say so and stop.

Branch Names

For each commit, derive a short kebab-case name (3-5 words) from its subject, using prefixes like add-, fix-, update-, remove-, refactor- where they fit. For example, "Fix null pointer in checkout" becomes fix-checkout-null-pointer.

Show the proposal:

Splitting branch `<current-branch>` into <N> branches:

- <short-sha> <commit-subject> → <semantic-branch-name>
- <short-sha> <commit-subject> → <semantic-branch-name>
...

Ask via AskUserQuestion:

  • "Proceed with these names" (recommended)
  • "Regenerate names"
  • "Use numbered naming" (<current-branch>-1, -2, etc.)
  • "Cancel"

Create the Branches

Work from oldest commit to newest. For each commit, check whether the target branch exists:

git rev-parse --verify <semantic-branch-name> 2>/dev/null

If it exists and its tip equals <commit-sha>, skip it. If it exists with a different tip, append a numeric suffix (e.g., add-user-model-2). Then:

git branch <semantic-branch-name> <base-branch>
git switch <semantic-branch-name>
git cherry-pick <commit-sha>

If a cherry-pick conflicts, tell the user which commit and branch, leave the branch conflicted, and continue with the rest. When done, return to the original branch with git switch <original-branch>.

Summary

List the preserved original branch, each new branch with its commit, skipped branches, and branches that need manual conflict resolution:

Successfully split `feature-auth` into 3 branches:

Original branch (preserved):
  feature-auth (3 commits)

New single-commit branches:
  ✓ add-user-model: abc1234 Add user model
  ✓ add-login-endpoint: def5678 Add login endpoint
  ⊘ add-session-handling: ghi9012 Add session handling (already exists, skipped)

2 branches created, 1 skipped.

Read the full file on GitHub · 78 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. 9d ago Changed e06ab6511953
  2. 22d ago Changed · -62 lines bed3ec889870
  3. 1mo ago First seen · 140 lines · 34 tokens per session scan A 1d8598ea6de5

Subscribe to this mod's changes

split-branch is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 628 once invoked, about $0.0001 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 2026-09-19.