pr-create

pr-create is a command for Claude Code from ckorhonen/claude-skills. It costs 12 tokens per session (386 once invoked), scanned A, original, MIT.

A command that commits local changes, pushes the current Git branch, and opens a pull request (PR) on GitHub for the repository’s default branch.

In plain words
What is it for?
Use it when you have completed a change and want to prepare it for review on GitHub, with a summary of the changes and a short PR description.
Why use it?
It removes the repeated manual steps of checking the branch, saving changes, pushing them, reviewing the diff, and creating the PR.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-skills plugin — 62 skills, 4 commands, 7 agents shipped together

Good fit Use it when you have completed a change and want to prepare it for review on GitHub, with a summary of the changes and a short PR description.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ckorhonen/claude-skills/pr-create
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.

Clone the repo
git clone --depth 1 https://github.com/ckorhonen/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

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 pr-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/ckorhonen/claude-skills/pr-create/github.svg)](https://agentmods.dev/commands/ckorhonen/claude-skills/pr-create)
Your own site
<a href="https://agentmods.dev/commands/ckorhonen/claude-skills/pr-create"><img src="https://agentmods.dev/badge/commands/ckorhonen/claude-skills/pr-create/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 pr-create

Your own site · 80×15
<a href="https://agentmods.dev/commands/ckorhonen/claude-skills/pr-create"><img src="https://agentmods.dev/badge/commands/ckorhonen/claude-skills/pr-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00386
Opus 5 $0.00006 $0.00193
Sonnet 5 $0.00002 $0.00077
Haiku 4.5 $0.00001 $0.00039

Measured 8d ago against content hash 5d433a2163b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pr-create 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 8d 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.

commands/pr-create.md · 44 lines

What it actually says

Create Pull Request

Current State

  • Branch: !git branch --show-current
  • Default branch: !gh repo view --json defaultBranchRef -q '.defaultBranchRef.name' 2>/dev/null || echo "main"
  • Git status: !git status --short

Instructions

Create a pull request by following these steps exactly:

1. Prerequisites Check

  • Verify we're not on the default branch (error if we are)
  • Verify gh auth status succeeds

2. Handle Uncommitted Changes

  • If there are uncommitted changes (shown above), commit them
  • Follow any commit message instructions: $ARGUMENTS
  • If no uncommitted changes, skip to step 3

3. Push to Origin

  • Check if upstream branch exists with git rev-parse --abbrev-ref @{u} 2>/dev/null
  • If no upstream: run git push -u origin HEAD
  • If upstream exists: run git push

4. Review PR Diff

  • Run git diff origin/<default-branch>...HEAD to see all changes that will be in the PR
  • Summarize the changes

5. Create the PR

  • Use gh pr create --base <default-branch>
  • Title: Keep under 80 characters, be descriptive
  • Description: Keep under 5 sentences summarizing the changes
  • If the user gave specific instructions in $ARGUMENTS about the PR, follow them

Error Handling

If any step fails, stop immediately and ask the user for help. Do not continue to the next step.

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. 8d ago First seen · 44 lines · 12 tokens per session scan A 5d433a2163b4

Subscribe to this mod's changes

pr-create is a command published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 386 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 2026-08-30.