create-pr

create-pr is a skill for Claude Code, Codex from mthines/agent-skills. It costs 188 tokens per session (7,174 once invoked), scanned A, original, MIT.

A tool for preparing a GitHub pull request, which is a request to merge code into a project. It writes the description, pushes the branch, opens a draft, and runs a review-and-fix cycle.

In plain words
What is it for?
It creates one pull request or proposes several smaller dependency-ordered requests, then can review comments, apply fixes, simplify the changes, and update the description.
Why use it?
It reduces the work of explaining a change, getting it ready for review, and handling feedback before finalizing the request.

Skill for Claude CodeCodex

Part of the mthines-agent-skills plugin — 54 skills, 4 agents shipped together

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

Made for: Claude Code, Codex.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 54 skills, 4 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 create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/mthines/agent-skills/create-pr.svg)](https://agentmods.dev/skills/mthines/agent-skills/create-pr)
Your own site
<a href="https://agentmods.dev/skills/mthines/agent-skills/create-pr"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/create-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,174 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 $0.00188 $0.07174
Opus 5 $0.00094 $0.03587
Sonnet 5 $0.00038 $0.01435
Haiku 4.5 $0.00019 $0.00717

Measured 2d ago against content hash 797ffcef47f0, 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 2d 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.

skills/delivery/create-pr/SKILL.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Pull Request Description

Generate a short, narrative PR description that tells reviewers why this change exists and what to expect when they open the diff. Reviewers skim. If the description is long, they skip it. Respect their time.

Modes

Parse $ARGUMENTS. --split selects an alternate workflow. The post-draft quality step (Step 6.5) runs the full review + simplify loop by default; the --no-* / --quick flags below scale it down. All flags compose with the default and split workflows.

Mode / Flag Trigger Behaviour
default No flag One PR for the whole branch. After opening the draft PR (Step 6), Step 6.5 runs Skill("review-loop", "<pr-url> --no-ci") — up to 5 iterations of pr-reviewerimplement-suggestionpolish simplify, converging until every review thread is resolved (fix or reply) and refreshing the PR description.
split --split, -s, or first positional token split Analyse the branch diff, propose 2–4 dependency-ordered draft PRs (hard cap 5), execute only after user approval. Jump to the Split Mode section after the description-contract step.
no-review --no-review Step 6.5 drops the pr-reviewer pass from the loop → runs only polish simplify once.
no-simplify --no-simplify Step 6.5 drops the simplify pass from the loop → runs only pr-reviewer (one-shot, no apply).
quick --quick Step 6.5 runs only the light mechanical pass → Skill("polish", "quick") (no pr-reviewer, no structural refactors).
no-quality --no-quality anywhere in arguments Skip Step 6.5 entirely and the Step 6.7 external-bot feedback loop. Wins over every other quality flag.
no-feedback --no-feedback anywhere in arguments Skip the default-on external-bot feedback loop (Step 6.7). Composes with everything. Does not skip the review-loop step.
no-preview-spec --no-preview-spec anywhere in arguments Skip the default-on UI verification spec authoring (Step 6.4). Composes with everything.

Read the full file on GitHub · 496 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.

  1. 2d ago Changed · +17 lines · -72 tokens per session 797ffcef47f0
  2. 5d ago First seen · 479 lines · 260 tokens per session scan A 6616f153c6bb

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository mthines/agent-skills (12 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 7,174 once invoked, about $0.0009 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

ego-browser

Skill "ego-browser" from citrolabs/ego-lite, covering ego-browser, quick start, common helpers, task spaces and control handoff.

citrolabs/ego-lite · 210 tokens

temporal-developer

Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or…

temporalio/skill-temporal-developer · 161 tokens

x-algorithm

Write X (Twitter) posts that the For You algorithm actually rewards. Grounded in the open-sourced X recommendation system — the Grok-based transformer ranker, Phoenix retrieval, Thunder in-network store, and Grox content-understanding pipeline. Use when the user wants to write a post, thread, reply, or quote; plan a…

carson2222/skills · 152 tokens

opencode-memory

Browse local OpenCode history: sessions, messages, plans, prompt history, and prior decisions. Use when the user says history, previous session, last time, remember, recall, plans, prior work, or when resuming/debugging repeated work where earlier OpenCode context may help. Do not use for fresh tasks or when current…

carson2222/skills · 77 tokens

creating-explainers

Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…

analyticalmonk/explain-this · 98 tokens

custom-icons

Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.

JKc66/custom-icons-skill · 57 tokens