github.create_child_pr

A guide for preparing instructions for a follow-up GitHub pull request, called a child PR. A pull request is a proposed set of repository changes for review and merging.

In plain words
What is it for?
Use it to create a numbered branch, copy the planned files, write a commit message, and define a test script for the next PR.
Why use it?
A multi-step change needs repeatable branch, file-copying, commit, and test instructions. This organizes those steps into files that another developer can follow.

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

Made for: Claude Code, Codex.

Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 887 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 $0.00007 $0.00887
Opus 5 $0.00003 $0.00443
Sonnet 5 $0.00001 $0.00177
Haiku 4.5 $0.00001 $0.00089

Measured 2d ago against content hash a1d2e1bef12b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github.create_child_pr 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.create_child_pr/SKILL.md · 94 lines

What it actually says

  • You are in a Git branch

    • E.g., HelpersTask1273_Get_Mac_tests_to_pass
  • Find which one is the next branch available

    • E.g.,
    > i git_branch_next_name
    12:01:47 - INFO  hgit.py _get_branch_next_name_via_github_api:124       Found highest number '3' in all branches, next is '4'
    branch_next_name='HelpersTask1273_Get_Mac_tests_to_pass_4'
    
  • Create a file pr_merge.txt with the instructions to:

    • Create a branch HelpersTask1273_Get_Mac_tests_to_pass_4
    • Copy the files needed to merge PR2 from github_PR_plan.md from the current branch to the target branch
    • Create a file pr_commit_msg.txt with the description of what the PR does
    • Create a file pr_pytest.sh with the tests to run to check the behavior of the PR
    • Make sure there are comments for each phase and that each command is correct
> export SRC_BRANCH=HelpersTask1273_Get_Mac_tests_to_pass
> export DST_BRANCH=HelpersTask1273_Get_Mac_tests_to_pass_6

> git checkout master
> git pull

> i git_branch_create -b $DST_BRANCH
> git checkout -b $DST_BRANCH

> cat > pr_commit_msg.txt << 'EOF'
Unit Test Infrastructure: Purification, Introspection, Numpy, and Base Updates

- Adds new test purification module (hunit_test_purification.py)
- Updates test infrastructure with new utility functions
- Improves introspection module for better test support
- Fixes numpy test compatibility issues
- Updates base unit test module for macOS compatibility
- All changes are related to test utilities and infrastructure improvements
- Well-isolated changes to testing subsystem
EOF

# Copy the files through branches.
> helpers_root/dev_scripts_helpers/git/git_sync_between_branches.sh --src_branch $SRC_BRANCH --dst_branch $DST_BRANCH --files "$FILES"

# Copy the files from another dir.
> export SRC_DIR=/Users/saggese/src/csfy1
> export DST_DIR=/Users/saggese/src/notes1
> export SUB_DIR=helpers_root
> diff_to_vimdiff.py --dir1 $SRC_DIR/$SUB_DIR/ --dir2 ./$SUB_DIR/

> echo "$FILES" | tr ' ' '\n' > /tmp/file_list.txt
> more /tmp/file_list.txt
helpers/hunit_test_purification.py
helpers/test/test_hunit_test_purification.py
helpers/test/test_hintrospection.py
helpers/test/test_hnumpy.py
helpers/test/test_hunit_test.py
> rsync -avR --files-from=/tmp/file_list.txt $SRC_DIR/$SUB_DIR/ $DST_DIR/$SUB_DIR/
> rsync -av $SRC_DIR/$SUB_DIR/ $DST_DIR/$SUB_DIR/

> git add $FILES
> git commit -am pr_commit_msg.txt

> cat > pr_pytest.sh << 'EOF'
pytest \
    helpers/test/test_hunit_test_purification.py \
    helpers/test/test_hintrospection.py \
    helpers/test/test_hnumpy.py \
    helpers/test/test_hunit_test.py \
    -v
EOF

> chmod +x pr_pytest.sh

> FILES="helpers/hunit_test_purification.py helpers/test/test_hunit_test_purification.py helpers/test/test_hintrospection.py helpers/test/test_hnumpy.py helpers/test/test_hunit_test.py"

> export CSFY_DOCKER_ENGINE="docker"; i docker_cmd --stage=local -v 1.6.0 --cmd "./pr_pytest.sh 2>&1 | tee build1.txt"

> export CSFY_DOCKER_ENGINE="docker"; ./pr_pytest.sh 2>&1 | tee build2.txt

> export CSFY_DOCKER_ENGINE="apple"; ./pr_pytest.sh 2>&1 | tee build3.txt

> i gh_create_pr --no-draft

> i gh_watch

> pr_pytest.sh
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 · 94 lines · 7 tokens per session scan A a1d2e1bef12b

Subscribe to this mod's changes

github.create_child_pr is a skill published in the GitHub repository causify-ai/helpers (145 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7 tokens to every session and 887 once invoked, about $0.0000 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens