start-branch

A Git workflow for creating and switching to a new branch, which is a separate line of work in a code repository. It chooses a name based on the task and can start from the current position or a named base branch.

In plain words
What is it for?
Creating branches such as feat/user-authentication or fix/cart-total-calculation, including branches based on main, dev, master, or stage.
Why use it?
It avoids manually choosing branch names and checking out the wrong starting point when beginning a feature, fix, or other task.

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/dkmqflx/git-workflow-plugin/start-branch
Any agent
npx skills add dkmqflx/git-workflow-plugin --skill start-branch
Clone the repo
git clone --depth 1 https://github.com/dkmqflx/git-workflow-plugin

Made for: Claude Code, Codex.

Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 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 $0.00145 $0.00602
Opus 5 $0.00072 $0.00301
Sonnet 5 $0.00029 $0.00120
Haiku 4.5 $0.00015 $0.00060

Measured 2d ago against content hash 5ff16fb37feb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-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.

plugins/git-workflow/skills/start-branch/SKILL.md · 53 lines

What it actually says

Start Branch

Generate an appropriate branch name for the task and switch to it — from the current position, or from a named base branch.

When to apply

Starting work on a new feature, fix, or task directly in the current directory. Do not apply for worktree (separate checkout directory) — that is /worktree.

Branch naming convention

Format: <type>/<short-description>

Type When to use
feat/ New feature or capability
fix/ Bug fix
chore/ Maintenance, config, dependency updates
refactor/ Restructuring without behavior change
docs/ Documentation only
test/ Test additions or changes

Description rules: lowercase, hyphen-separated, 2–5 words, describes WHAT (not HOW).

Examples: feat/user-authentication, fix/cart-total-calculation, chore/update-eslint-config, refactor/extract-payment-service

Steps

  1. Determine the base:
    • If the user named a specific branch (e.g. dev, master, main, stage), that is the base branch.
    • Otherwise, the base is the current position — no checkout needed before branching.
  2. Derive the branch name from the user's task description using the convention above. If no task description was given (bare /start-branch), ask one short question first.
  3. If a base branch was named, switch to it and pull latest, then branch from it:
    git checkout <base branch> && git pull
    git checkout -b <branch-name>
    
    Otherwise, branch directly from the current position:
    git checkout -b <branch-name>
    
  4. Confirm in one line: Switched to new branch: <branch-name> (append (from <base branch>) if a base was named)
  5. Begin the user's task.
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 · 53 lines · 145 tokens per session scan A 5ff16fb37feb

Subscribe to this mod's changes

start-branch is a skill published in the GitHub repository dkmqflx/git-workflow-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 602 once invoked, about $0.0007 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

lov-app-generator

Use when the user asks for "App生成器", "生成 Web App", "生成 Tauri App", "生成原生 macOS App", "Finder Quick Action", "只创建 web", or to standardize an existing app with branding, CI/CD, native integration, and Lovinsp where applicable.

lovstudio/skills · 66 tokens

lov-maintain-partners

Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…

lovstudio/skills · 294 tokens

dsh-plugin-publisher

Publish a validated DSH plugin package (@deepseek-ai/dsh- or @lovstudio/dsh-) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin. 触发:发布插件 / 上架插件 / release dsh 插件。.

lovstudio/skills · 82 tokens

lov-human-writing

用作者性账本、篇章审计和 30 项中文表层度量改进稿件,保留真实判断并定位过度解释、 单线因果和强行收束。Use when users say“去 AI 味”“保留我的判断”或 "humanize this Chinese draft".

lovstudio/skills · 71 tokens

lov-any2deck

Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation"…

lovstudio/skills · 110 tokens

lov-bp

Orchestrate a complete investor BP workflow or route to one focused module: source-backed outline, PPTX/PDF production, or evidence/content/visual polishing. Use when the user wants to create a business plan end to end, combine BP stages, continue from an existing BP workspace, or is unsure which BP skill to use.…

lovstudio/skills · 109 tokens