stack-branch

stack-branch is a skill for Claude Code, Codex from flurdy/agent-skills. It costs 32 tokens per session (786 once invoked), scanned A, original, MIT.

A workflow for creating a Git branch, a separate line of development, on top of another pull request that has not been merged yet. The new work therefore includes the parent branch's changes.

In plain words
What is it for?
Use it when a feature or fix relies on code from an unfinished pull request and needs its own ticket-based branch.
Why use it?
It lets dependent work begin before earlier work reaches the main branch and ties the new branch to a Jira ticket, a project-tracking issue.

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/flurdy/agent-skills/stack-branch
Any agent
npx skills add flurdy/agent-skills --skill stack-branch
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code, Codex.

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 stack-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/stack-branch.svg)](https://agentmods.dev/skills/flurdy/agent-skills/stack-branch)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/stack-branch"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/stack-branch.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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 $0.00032 $0.00786
Opus 5 $0.00016 $0.00393
Sonnet 5 $0.00006 $0.00157
Haiku 4.5 $0.00003 $0.00079

Measured 3d ago against content hash d436e1b11d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stack-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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gh-pr-create.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/stack-branch/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Stacked Branch

Create a new branch based on an existing PR branch (not main) for dependent work.

Usage

/stack-branch AB-456
/stack-branch AB-456 feature/parent-branch    # Explicit parent

Instructions

1. Get the Jira Ticket

The first argument is the Jira ticket number for the new work.

Use the /jira-ticket skill or the Jira MCP tools directly to get ticket details:

mcp__jira__jira_get with:
  path: /rest/api/3/issue/{ticketNumber}
  jq: "{key: key, summary: fields.summary, issuetype: fields.issuetype.name}"

2. Identify Parent Branch

If parent branch not specified:

# Check if currently on a feature branch
git branch --show-current

If on a feature branch (not main), offer to use it as the parent. Otherwise, ask the user which branch to stack on.

3. Ensure Parent is Up to Date

# Fetch the parent branch
git fetch origin {parent-branch}

# Check out and update local copy
git checkout {parent-branch}
git pull origin {parent-branch}

4. Create Branch Name

Map the Jira issue type to conventional commit prefix:

Issue Type Prefix
Story feat
Task feat
Bug fix
Improvement feat
Spike chore
Sub-task inherit from parent

Create branch name:

{prefix}/{TICKET}-{summary-in-kebab-case}

Example: feat/AB-456-add-caching-layer

5. Create the Branch

git checkout -b {new-branch-name}

6. Push and Set Upstream

git push -u origin {new-branch-name}

7. Inform User

Tell the user:

  • Created branch {new-branch-name} based on {parent-branch}
  • When creating a PR, target {parent-branch} not main
  • When {parent-branch} is merged, use /rebase-merged-parent to rebase onto main

8. Optional: Create Draft PR

Ask if the user wants to create a draft PR now:

Check for a repo-specific PR template at .github/pull-request-template.md or .github/pull_request_template.md. If found, use that format. If not, ask user for confirmation on generating the body ourselves.

Read the full file on GitHub · 122 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 122 lines · 32 tokens per session scan A d436e1b11d4f

Subscribe to this mod's changes

stack-branch is a skill published in the GitHub repository flurdy/agent-skills (7 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 786 once invoked, about $0.0002 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 2026-08-31.

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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