A GitHub pull request workflow that pushes the current branch when needed, checks for an existing pull request, and creates a title and description from the changes. A pull request is a request for others to review and merge code.

Use it to open a new pull request, submit a draft for review, update work for an existing pull request, or share a branch with reviewers.

It brings the steps for sending work for review into one workflow and helps prevent duplicate pull requests or submissions from an unsuitable branch.

creating-pr — Skill for Claude Code and Codex by joaquimscosta

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 joaquimscosta/arkhe-claude-plugins --skill creating-pr

Clone the repo

git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/creating-pr/github.svg)](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/creating-pr)

Your own site

<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/creating-pr"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/creating-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/creating-pr"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/creating-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,549 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00103	$0.03549
Opus 5.5	$0.00041	$0.01420
Sonnet 5.5	$0.00021	$0.00710
Haiku 4.5	$0.00010	$0.00355

Measured yesterday against content hash 835ff35a6bdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

creating-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 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.

plugins/git/skills/creating-pr/SKILL.md · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ CRITICAL CONSTRAINTS

YOU MUST NEVER add Claude Code attribution to pull requests.

❌ NO "🤖 Generated with [Claude Code]" in PR titles or descriptions
❌ NO "Co-Authored-By: Claude [email protected]" in PR content
❌ NO Claude Code attribution, footer, or branding of any kind

Pull requests are public code review documents and must remain clean and professional.

GitHub PR Creation Workflow

Execute GitHub Pull Request workflows with automatic repository detection, branch management, and intelligent PR content generation.

Usage

This skill is invoked when:

User runs /create-pr or /git:create-pr command
User requests to create a pull request
User asks to open a PR or push changes for review

How It Works

This skill handles the complete PR workflow:

Repository Detection - Detect current repository context (root or submodule)
Branch Validation - Verify not on protected branch, check for uncommitted changes
Branch Pushing - Ensure branch exists on remote
Existing PR Detection - Check if PR already exists for current branch
PR Content Generation - Create title and description from commits
PR Creation - Create or update PR using GitHub CLI

Supported Arguments

Parse arguments from user input:

No arguments: Auto-detect repository and create PR to main branch
<scope>: Direct PR for specific repository (root, submodule-name)
--draft: Create as draft PR
--base <branch>: Target branch (default: main)
Combinations: <scope> --draft, root --base staging, etc.

Prerequisites

GitHub CLI Required: Must have gh installed and authenticated

# Install GitHub CLI (if not installed)
# macOS: brew install gh
# Linux: See https://cli.github.com/

# Authenticate
gh auth login

PR Creation Workflow Steps

Step 1: Parse Arguments

Extract scope, draft flag, and base branch from user input:

Read the full file on GitHub · 460 lines

Files

What ships with it

3 files 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.

yesterday First seen · 460 lines · 103 tokens per session scan A 835ff35a6bdc

Subscribe to this mod's changes

creating-pr is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,549 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-16.

Code review Git and workflow ai-agents ai-developer-tools anthropic claude-code-agents claude-code-plugins

pr-creator

Create well-structured pull requests with proper descriptions and labels.

kivo360/OmoiOS · 11 tokens

dev-rc

The last gate before merge — QA, security audit, review and changelog, with objective pass conditions.

ToruAI/toru-claude-agents · 25 tokens

pr-autofix

When the user has PR review feedback to address, CI failures to fix, or wants to automatically resolve common PR issues. Use when the user says "fix the PR," "address review comments," "CI is failing," "fix the build," "autofix," "pr feedback," "resolve comments," "fix merge conflicts," or when a PR needs updates…

irfad7/claude-power-skills · 93 tokens

creating-pr