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.
npx agentmods add commands/motlin/claude-code-plugins/split-branchgit clone --depth 1 https://github.com/motlin/claude-code-pluginsWhat 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 | $0.00014 | $0.01058 |
| Opus 5 | $0.00007 | $0.00529 |
| Sonnet 5 | $0.00003 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Split the current branch into multiple branches, each containing a single commit.
ALWAYS use the code:cli skill.
Context
- Current branch: !
git branch --show-current - All local branches: !
git branch --list - Remote tracking info: !
git for-each-ref --format='%(refname:short) -> %(upstream:short)' refs/heads/
Arguments
The user passed in: $ARGUMENTS
If the user specified a base branch, use that. Otherwise, detect the base branch:
- Check if there's an upstream tracking branch
- Fall back to
mainormaster(whichever exists) - If neither exists, ask the user to specify
Task
Step 1: Identify Commits to Split
Run: git log --oneline --reverse <base-branch>..HEAD
This shows all commits on the current branch that aren't on the base branch.
If there are 0 commits, inform the user there's nothing to split and stop. If there is 1 commit, inform the user there's only one commit so splitting isn't useful, and stop.
Step 2: Generate Semantic Branch Names
For each commit, generate a descriptive branch name based on the commit content:
- Analyze the commit message subject line
- Create a short kebab-case name (3-5 words max) that captures what the commit does
- Use conventional prefixes when appropriate:
add-,fix-,update-,remove-,refactor- - Avoid generic names - be specific about what changed
Examples of good semantic names:
- "Add user authentication model" →
add-user-auth-model - "Fix null pointer in checkout" →
fix-checkout-null-pointer - "Update API rate limiting" →
update-api-rate-limits
Show the user a numbered list with the proposed branch names:
Splitting branch `<current-branch>` into <N> branches:
1. <short-sha> <commit-subject> → <semantic-branch-name>
2. <short-sha> <commit-subject> → <semantic-branch-name>
...
Ask for confirmation before proceeding. Use the AskUserQuestion tool with options:
- "Proceed with these names" (recommended)
- "Regenerate names" (generate alternative names)
- "Use numbered naming" (fall back to -1, -2, etc.)
- "Cancel"
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.
- 2d ago First seen · 138 lines · 14 tokens per session scan A ed63b4be5797
split-branch is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,058 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.