ss-create-branch

ss-create-branch is a skill for Claude Code, Codex from lbk-open/super-spec. It costs 62 tokens per session (2,121 once invoked), scanned A, original, Apache-2.0.

A workflow for creating and preparing a Git development branch from the latest remote default branch. It can also set up an isolated worktree, which is a separate working directory for one branch.

In plain words
What is it for?
Starting feature, bug-fix, or maintenance work from a description, ticket, or requirement link. It can optionally verify the existing code before development begins.
Why use it?
It gives new work a consistent branch name and a clean starting point. Pushing the branch and tracking its remote copy makes collaboration easier.

Skill for Claude CodeCodex

Part of the super-spec plugin — 20 skills shipped together

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/lbk-open/super-spec/ss-create-branch
Any agent
npx skills add lbk-open/super-spec --skill ss-create-branch
Clone the repo
git clone --depth 1 https://github.com/lbk-open/super-spec

Made for: Claude Code, Codex.

Or install super-spec, the plugin that ships this one along with the rest of its 20 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 ss-create-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-create-branch.svg)](https://agentmods.dev/skills/lbk-open/super-spec/ss-create-branch)
Your own site
<a href="https://agentmods.dev/skills/lbk-open/super-spec/ss-create-branch"><img src="https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-create-branch.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,121 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 5.1 $0.00062 $0.02121
Opus 5 $0.00031 $0.01060
Sonnet 5 $0.00012 $0.00424
Haiku 4.5 $0.00006 $0.00212

Measured 5d ago against content hash 0501dd86374f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ss-create-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 5d 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.

skills/ss-create-branch/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Development Branch

Create a named development branch from the latest remote default branch, decide whether to develop in an isolated git worktree (explicit request > repository default > ask the user), push the branch immediately, and set up upstream tracking.

Inputs

  • A branch name, a requirement link (issue/ticket/doc URL), or a plain-language description of the work. If none is given, ask.
  • Optional: --from <branch> to branch off something other than the remote default.
  • Optional: an explicit worktree preference (isolated worktree vs. develop in place) — if not given, follow Step 4's priority order below.
  • Optional: --verify-baseline to run the full test suite once after the worktree is ready, to confirm the baseline. Skipped by default because the branch starts as a zero-diff cut of the remote base, so its baseline already equals whatever CI last confirmed.

Step 1 — Determine the branch slug

Derive the slug (the name portion after the type prefix) from the input:

Input Example Slug
Plain text "add payment", "login fix 123" Lowercase, spaces → hyphens
A requirement/ticket link https://tracker.example.com/issues/10442755 If a numeric ID is visible in the URL, use it directly; otherwise fetch and summarize
A document link any URL to a spec/PRD Fetch its content with your document-reading tool and summarize to a 2–4 word English slug
Pasted markdown/text # Add User API\n... Extract the first heading/title and summarize to a 2–4 word English slug

Slug rules: lowercase letters, digits, and hyphens only — no spaces, underscores, or other punctuation.

Step 2 — Determine the branch type prefix

Supported prefixes: feat/, fix/, hotfix/, refactor/, docs/.

  • If the user's input already includes a prefix (e.g., fix/login-bug), use it as given.
  • If the input is a feature/requirement link, default to feat/; use fix/ if the requirement is clearly a defect.
  • If it's ambiguous, ask which prefix applies before proceeding.

Read the full file on GitHub · 156 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. 5d ago First seen · 156 lines · 62 tokens per session scan A 0501dd86374f

Subscribe to this mod's changes

ss-create-branch is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,121 once invoked, about $0.0003 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

phx-deps-audit

Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.

oliver-kriska/claude-elixir-phoenix · 58 tokens

release

CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.

oliver-kriska/claude-elixir-phoenix · 60 tokens

session-deep-dive

Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.

oliver-kriska/claude-elixir-phoenix · 40 tokens

brainstorm

Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.

oliver-kriska/claude-elixir-phoenix · 39 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

plugin-dev-workflow

Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.

oliver-kriska/claude-elixir-phoenix · 59 tokens