create-pr

A workflow for creating or updating a GitHub pull request from the current branch. It generates a structured description with a diagram, file walkthrough, and links to relevant design documents.

In plain words
What is it for?
Opening a pull request against a base branch, updating an existing pull request, summarizing implementation changes, and documenting how the changed files fit together.
Why use it?
Writing a complete pull-request description requires collecting commits, changed files, design context, and the purpose of the change. This organizes that information into a shared format.

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/smana/cloud-native-ref/create-pr
Any agent
npx skills add Smana/cloud-native-ref --skill create-pr
Clone the repo
git clone --depth 1 https://github.com/Smana/cloud-native-ref

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,079 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 $0.00035 $0.01079
Opus 5 $0.00017 $0.00540
Sonnet 5 $0.00007 $0.00216
Haiku 4.5 $0.00003 $0.00108

Measured 3d ago against content hash e3471e6da796, 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 3d 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.

.claude/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 PR Skill

Generate and create/update a comprehensive PR using the shared body template.

Mode detection

Parse $ARGUMENTS:

  • Starts with --update or -u followed by a number → Update Mode on that PR.
  • Anything else → Create Mode (argument is the base branch; default main).

Create Mode

1. Gather diff information (parallel)

git log origin/${BASE:-main}..HEAD --oneline
git diff origin/${BASE:-main}...HEAD --stat
git diff origin/${BASE:-main}...HEAD

2. Detect the design context

Changed paths → change type:

Path pattern Change type
infrastructure/base/crossplane/configuration-aws/configuration-packages.yaml (composition package pin) composition
opentofu/**/*.tf, terramate.tm.hcl infrastructure
*networkpolicy*, *rbac*, openbao/**, *cilium*policy* security
Multiple top-level dirs + HelmRelease/Kustomization platform

Find the design document behind these changes, if one exists. Non-trivial work goes through the Superpowers flow (see CLAUDE.mdDevelopment Workflow), which commits a design and a plan on the branch:

git diff origin/${BASE:-main}...HEAD --name-only \
  | grep -oE 'docs/superpowers/(specs|plans)/[0-9]{4}-[0-9]{2}-[0-9]{2}-[a-z0-9-]+\.md' \
  | sort -u

When a design is detected, include the Design block:

## 📋 Design

Design: [`<date>-<topic>-design.md`](../blob/main/docs/superpowers/specs/<date>-<topic>-design.md)
Plan: [`<date>-<topic>-plan.md`](../blob/main/docs/superpowers/plans/<date>-<topic>-plan.md)

<one line: which part of the plan this PR delivers>

If the design doc itself changed materially in a PR that also implements it, say so in the summary — a design moving during implementation usually signals scope creep worth calling out.

If the changes look substantial (a new composition, a new OpenTofu stack, a security-model change) and no design doc is present, include the Design Recommendation warning block from the template.

Read the full file on GitHub · 119 lines

Files

What ships with it

2 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.

  1. 3d ago First seen · 119 lines · 35 tokens per session scan A e3471e6da796

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository Smana/cloud-native-ref (99 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,079 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 2026-08-30.

Related

Other skills, from other repositories

database-schema-designer

Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.

meshery/meshery · 49 tokens

gepetto

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

meshery/meshery · 35 tokens

gnhf

Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.

meshery/meshery · 55 tokens

gen-test

Generate idiomatic tests for Go packages and handlers in the Meshery project.

meshery/meshery · 18 tokens

superplane-dashboard-and-widgets

Implements and configures SuperPlane canvas consoles (markdown, node, table, board, chart, number, scorecard panels), widget data sources, CEL/templates, table row trigger actions, and console YAML. Use when editing console UI, panelTypes, useWidgetData, WidgetTable, WidgetBoard, canvasconsoleyml…

superplanehq/superplane · 90 tokens

superplane-changelog

When generating a SuperPlane changelog from merged commits. Use for "what's new" summaries with new integrations, new components/triggers, improvements, security updates, and bug fixes. Output is user-focused markdown in tmp/.

superplanehq/superplane · 50 tokens