branch-feature

A workflow for creating a new Git feature branch from a configured base branch, such as develop, using the repository’s naming rules.

In plain words
What is it for?
Use it when starting a feature or other development task in Git. Provide the branch name and it creates the appropriately named branch from the selected base.
Why use it?
It removes the need to remember branch names, starting points, and protected branches. It also uses the repository configuration when available.

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/devstride/claude-plugin/branch-feature
Any agent
npx skills add devstride/claude-plugin --skill branch-feature
Clone the repo
git clone --depth 1 https://github.com/devstride/claude-plugin

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 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 $0.00014 $0.00755
Opus 5 $0.00007 $0.00378
Sonnet 5 $0.00003 $0.00151
Haiku 4.5 $0.00001 $0.00076

Measured yesterday against content hash d58bc0ef7a45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

branch-feature 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 yesterday.

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/branch-feature/SKILL.md · 38 lines

What it actually says

Human output. Read ${CLAUDE_PLUGIN_ROOT}/skills/build-item/references/plain-language-output.md once per top-level run; composed skills reuse it. Apply it to every message.

Create a new feature branch with the following workflow:

Branch name argument: $ARGUMENTS

Repo config. The base branch, branch-naming pattern, and protected-branch list this skill uses live in .claude/ds-config.json at the repo root (baseBranch, integrationBranch, branchNaming, protectedBranches). Load it first and treat it as authoritative: wherever a step below names a concrete branch or naming rule, substitute the matching config value. The literals shown inline are the plugin's shipped defaults, kept for readability — if the file disagrees, the file wins. If the file is absent, fall back to the inline literals and say so.

Working base. Resolve the branch to base off of in this precedence: (1) an explicit base the CALLER passed you — the build-item loop derives a working base (by default the story's epic integration branch, <prefix>/<MM-DD-YY>/<epic-number>-<epic-title-slug>; plain develop when the item has no Epic) and tells you to "branch off <name>"; that wins over config. (2) Otherwise integrationBranch if it is set (non-null) in the config. (3) Otherwise baseBranch. When the working base is an integration branch (epic-derived or explicit — see the config's _integrationBranch_readme), it must already exist on the remote (build-item step 0 creates the epic branch before invoking this skill); if git checkout of it fails, STOP and tell the caller to create it off baseBranch first rather than silently falling back to develop. Everywhere a step below says "develop", read "the working base".

  1. Check for uncommitted changes with git status --porcelain. If the tree is dirty, STOP and ask whether to stash or commit first — do not carry changes onto the working base.
  2. Save the current branch name (git rev-parse --abbrev-ref HEAD) for reference.
  3. Run git checkout <working base> then git pull to sync with remote.
  4. Create a new branch with the naming convention:
    • Format: <user-prefix>/<MM-DD-YY>/<branch-name>
    • Derive <user-prefix> from the local git identity: first name from git config user.name, lowercased (e.g. "Jane Doe" → jane). If empty or ambiguous, ask the user what prefix they want.
    • Use today's date in MM-DD-YY format.
    • Use the provided argument as the branch-name suffix.
    • Example: "Jane Doe" → jane/03-14-26/new-feature
  5. Push the new branch and set upstream: git push -u origin <new-branch-name>

IMPORTANT:

  • If no branch name argument is provided, ask the user for one.
  • The previous branch is NOT deleted automatically — keep it until its PR merges. If the user explicitly asks, delete it with git branch -d <previous-branch> (offer -D only if they confirm, and never delete develop/master or an active integrationBranch).
  • Confirm the branch was created and pushed; report the full new branch name.
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. yesterday First seen · 38 lines · 14 tokens per session scan A d58bc0ef7a45

Subscribe to this mod's changes

branch-feature is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 755 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 2026-08-31.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens