github.split_branch_in_PRs

A guide for splitting the changes on a Git branch into several small pull requests, which are proposed code changes for review and merging. It focuses on keeping each request cohesive and easier to review.

In plain words
What is it for?
Use it to inspect differences from the main branch and propose a safe grouping of the current changes into separate pull requests.
Why use it?
It helps reduce review complexity and lower the chance that a large set of changes will break tests or be difficult to merge.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/causify-ai/helpers/github.split_branch_in_prs
Any agent
npx skills add causify-ai/helpers --skill github.split_branch_in_prs
Clone the repo
git clone --depth 1 https://github.com/causify-ai/helpers

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.00721
Opus 5 $0.00008 $0.00360
Sonnet 5 $0.00003 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 2d ago against content hash 252e7eef2794, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github.split_branch_in_PRs 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.

.claude/skills/github.split_branch_in_PRs/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

  • Propose how to split the changes between current HEAD of the branch and origin/master into small PRs to minimize:

    • The review complexity
    • The risk of breaking the unit tests
  • If the task is not perfectly clear or complex, you MUST not perform it, but ask for clarifications and create a plan for review

    • Create a plan.md with 5 bullet points explaining what the plan is

Workflow

Step 1: Read rules

  • Read rules about:
    • Coding: .claude/skills/coding.rules.md
    • Unit tests: .claude/skills/testing.rules.md

Step 2: Read the changes in the current Git client

  • Obtain the files that need to be merged with:

    git diff --name-status origin/master HEAD
    ...
    
  • Analyze the difference between the current client and master (or origin/master):

    git diff master...HEAD --name-only
    # or if master is not available locally:
    git diff origin/master...HEAD --name-only
    

Step 3: Propose PRs

  • Propose a set of PRs that decompose the changes in the current Git client, so that there are coherent and tightly coupled changes

  • Prefer PRs that have the changes to an entire file instead of having to split changes in a file across multiple PRs

  • Make sure that changes to files and their testing files are in the same PR

  • Merge low risk / complexity PRs so that there are fewer PRs even if the content of the resulting PR is the sum of multiple simpler ones

    • In this case, the description is multiple bullets explain what each smaller unit does

Step 4: Order the PRs

  • Start with the PRs that have low risk and touch most files

Step 5: Create pytest Command

  • For each PR create:
    • A file pr<NUM>.files.txt with the files changed, e.g.,
      .claude/skills
      .claude/templates
      .claude/notify.sh
      .claude/settings.local.json
      
    • A file pr<NUM>.pytest.sh with the pytest command to run to exercise the changes by running the tests in all the modified files and make sure the PR is running successfully, e.g.,
      #!/bin/bash
      pytest_log \
        dev_scripts_helpers/coding_tools/test \
        dev_scripts_helpers/dockerize/test \
        linters2/test \
        $@
      
    • Make this script executable with chmod +x pr<NUM>.pytest.sh

Read the full file on GitHub · 90 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. 2d ago First seen · 90 lines · 16 tokens per session scan A 252e7eef2794

Subscribe to this mod's changes

github.split_branch_in_PRs is a skill published in the GitHub repository causify-ai/helpers (145 stars, last pushed 2d ago), licensed Apache-2.0. It adds 16 tokens to every session and 721 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens