create-pr

A pull-request helper that prepares a GitHub pull request from the current feature branch, linking it to an issue when possible and describing the changes and tests.

In plain words
What is it for?
Use it after committing work to check the branch, identify changed project areas, and create a pull request with a structured body and test plan.
Why use it?
It removes the need to inspect the branch manually and write a consistent pull-request description by hand.

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/makigjuro/cloudstack-ai-plugins/create-pr
Any agent
npx skills add makigjuro/cloudstack-ai-plugins --skill create-pr
Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,003 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 $0.00046 $0.01003
Opus 5 $0.00023 $0.00502
Sonnet 5 $0.00009 $0.00201
Haiku 4.5 $0.00005 $0.00100

Measured yesterday against content hash 68c124338ed3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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/dev-workflow/skills/create-pr/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Pull Request

Create a pull request for the current branch with a structured description.

Configuration

Read cloudstack.json from the project root at the start of execution. Extract relevant fields:

  • REPO_OWNER / REPO_NAME = repository.owner / repository.name (default: detect from git remote -v)
  • SOLUTION = backend.solutionPath (default: find *.sln)
  • FRONTEND_PATH = frontend.path (default: web)
  • CHARTS_PATH = infrastructure.chartsPath (default: deploy/charts)
  • TF_PATH = infrastructure.terraformPath (default: infra/terraform/modules)

If cloudstack.json does not exist, auto-detect by scanning the project structure and parsing the GitHub remote URL.

Arguments

  • {issue} -- GitHub issue number to link (optional). If not provided, attempt to extract from the branch name.

Prerequisites

  • You must be on a feature branch (not main)
  • All changes should be committed (warn if working tree is dirty)
  • Branch should have at least one commit ahead of main

Process

  1. Gather context:

    • git status -- check for uncommitted changes, warn if dirty.
    • git log origin/main..HEAD --oneline -- list all commits on this branch.
    • git diff origin/main...HEAD --stat -- summary of changed files.
    • Extract issue number from branch name or argument.
  2. Analyze changes:

    • Identify which layers were modified (Domain, Application, Infrastructure, Host, Frontend, Tests).
    • Detect affected services by checking paths against known service directories:
      git diff origin/main...HEAD --name-only | grep -oP 'src/\K[^/]+' | sort -u
      
    • Detect what was added vs changed vs removed from the diff stat.
    • Check if documentation may need updating (new endpoints, entities, or events).
  3. Push and create PR:

    • Push the branch to origin with -u flag.
    • Create the PR using MCP.

PR Body Format

## Summary
{1-3 bullet points describing what this PR does}

Closes #{issue-number}

## Affected Services
{List only services that were actually modified}

## Changes
- **Domain:** {changes or "No changes"}
- **Application:** {changes or "No changes"}
- **Infrastructure:** {changes or "No changes"}
- **Endpoints:** {changes or "No changes"}
- **Frontend:** {changes or "No changes"}
- **Tests:** {changes or "No changes"}

## Test Plan
- [ ] Unit tests pass
- [ ] Integration tests pass (if applicable)
- [ ] Frontend lint clean (if applicable)
- [ ] Frontend type-check clean (if applicable)
- [ ] Helm lint clean (if applicable)
- [ ] Terraform validate clean (if applicable)
- [ ] Architecture check passes
- [ ] {Any feature-specific manual verification steps}

Generated with [Claude Code](https://claude.com/claude-code)

Read the full file on GitHub · 119 lines

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 · 119 lines · 46 tokens per session scan A 68c124338ed3

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,003 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 2026-08-31.

Related

Other skills, from other repositories