new-branch-and-pr

new-branch-and-pr is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 41 tokens per session (1,375 once invoked), scanned A, original, Apache-2.0.

A workflow for putting selected work on a clean branch and opening one pull request. A branch is a separate line of code changes, and a pull request asks others to review and merge it.

In plain words
What is it for?
Use it when finished work must be committed, pushed to a new focused branch, and submitted as a pull request.
Why use it?
It keeps unrelated work out of the submission and shows the remote changes before publishing them. It does not force-push or alter other remote branches.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Part of the odin-git plugin — 46 skills shipped together

Good fit Use it when finished work must be committed, pushed to a new focused branch, and submitted as a pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/new-branch-and-pr
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.

Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill new-branch-and-pr
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-git, the plugin that ships this one along with the rest of its 46 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 new-branch-and-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for new-branch-and-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/new-branch-and-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.01375
Opus 5 $0.00020 $0.00687
Sonnet 5 $0.00008 $0.00275
Haiku 4.5 $0.00004 $0.00137

Measured 5d ago against content hash 8d4cac6c5bee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

new-branch-and-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 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.

plugins/odin-git/skills/new-branch-and-pr/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New branch and PR

Contract

Field Bound contract
Trigger A human explicitly asks to ship work through a clean branch and pull request.
Authority Remote: pushes one branch and opens one pull request; requires explicit human invocation. Creates a local branch and commits first; preview the remote, base, head branch, included changes, and publishing consequence before the remote mutation.
Side effect Creates one focused branch, commits its intended changes, pushes that branch, and opens one pull request without mutating unrelated work or other remote branches.
Done The intended changes are committed on the focused branch and the remote operation is confirmed by a pull-request URL.

Inputs

Required: the repository containing the work, the intended changes to publish, and the pull-request base branch. The target remote must be supplied or unambiguously established by repository configuration. A branch name, commit message, pull-request title, and pull-request body are optional; when omitted, derive them only from the inspected change and repository state. Publishing credentials must already be available in the execution environment; never request, print, copy, or persist credential values.

Procedure

  1. Inspect the repository status, current branch, configured remotes, intended base, and diff. Stop if the repository, base, target remote, or intended change set is missing or ambiguous. Done when: the repository root, current branch, remote list, base branch, and diff are all read and recorded, or a missing or ambiguous input is named and the stop is reported.
  2. Bound the publication to the intended changes. Exclude unrelated tracked, staged, and untracked work; stop if separating it would overwrite or discard any work. Done when: the bounded change set contains only the intended changes, and no unrelated tracked, staged, or untracked work is included, or an unsafe separation is named and the stop is reported.
  3. Choose the supplied branch name or derive a concise name from the bounded change. Confirm that creating and publishing it will not overwrite an existing local or remote branch; stop on a conflicting branch rather than force-update it. Done when: a branch name is chosen that does not match any existing local or remote branch, or a conflict is named and the stop is reported.
  4. Create the new branch from the intended base while preserving the bounded changes. Stage only those changes, review the staged diff, and stop if it contains secrets, generated debris, unrelated files, or changes outside the bounded scope. Done when: the new branch is created from the intended base, the staged diff contains exactly the bounded changes, and no secrets, debris, or out-of-scope files are present, or a contamination finding is named and the stop is reported.
  5. Inspect the repository manifest and continuous-integration configuration for commands that directly exercise the included files. Run the narrowest deterministic command that covers the bounded change from the repository root. Record the exact command, exit result, and relevant output; if no covering command exists or the required runtime is unavailable, record that fact and do not claim the check ran. Done when: the exact check command and its exit result are recorded, or the absence of a covering command or runtime is recorded as a fact rather than assumed.
  6. Commit the staged change with the supplied message or one derived from the reviewed diff. Confirm the commit contains exactly the bounded files and no unrelated changes. Done when: the commit is created and git show --stat <commit> lists exactly the bounded files and no others.
  7. Before any remote mutation, present a preview naming the remote, base branch, new head branch, commit, included files, pull-request title, and the consequences that the branch will be pushed and a pull request will be created. Proceed only because this skill was explicitly invoked by a human; if the requested target differs from the validated preview, stop and report the mismatch. Done when: the preview is presented to the user and the user confirms it matches their intent, or a mismatch between the requested target and the preview is named and the stop is reported.
  8. Push only the new branch without force, then open one pull request from that branch to the validated base. Use supplied pull-request text or derive factual text from the commit and checks actually observed; never invent test results, issue links, reviewers, or deployment claims. Done when: the branch is pushed to the remote and one pull request is opened returning a URL, or the push or PR creation failed and the error is recorded.
  9. Read the created pull request's remote response and confirm its base, head, and URL. Return the branch, commit, push result, pull-request URL, and check evidence. Done when: the remote PR response confirms the base branch, head branch, and URL match what was pushed, and all five values are returned, or a mismatch is named and the stop is reported.

Read the full file on GitHub · 46 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. 5d ago First seen · 46 lines · 41 tokens per session scan A 8d4cac6c5bee

Subscribe to this mod's changes

new-branch-and-pr is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,375 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 2026-09-06.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens