create-pr

A procedure for creating a GitHub pull request, which asks others to review and merge a branch's code changes.

In plain words
What is it for?
Use it when you need to turn the current branch's changes into a submitted pull request that follows project standards.
Why use it?
It organizes branch naming, staged-change checks, code simplification, commits, documentation, and the pull-request details.

Skill for Claude CodeCodex

Part of the github-dev plugin — 6 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/fcakyon/claude-codex-settings/create-pr
Any agent
npx skills add fcakyon/claude-codex-settings --skill create-pr
Clone the repo
git clone --depth 1 https://github.com/fcakyon/claude-codex-settings

Made for: Claude Code, Codex.

Or install github-dev, the plugin that ships this one along with the rest of its 6 skills, 4 agents.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,270 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00049 $0.01270
Opus 5 $0.00024 $0.00635
Sonnet 5 $0.00010 $0.00254
Haiku 4.5 $0.00005 $0.00127

Measured 3d ago against content hash 97303d465ceb, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Capture both shots at the same window size so the pair is comparable. Release assets serve as `application/octet-stream`, so `curl -sI` looks wrong even when fine. Open the PR and confirm the images render.
plugins/github-dev/skills/create-pr/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PR

Complete workflow for creating pull requests following project standards.

When explicitly invoked with extra text, treat that text as additional context for branch naming, commit context, and PR title and body generation. Compress it into a short plain-language branch name rather than copying the full text.

Process

First, run the /simplify skill on the staged diff and apply its findings before committing. Docs-only diffs are a no-op.

  1. Preferred execution

    • If subagents are available, use github-dev:pr-creator for the full workflow.
    • Pass along any extra invocation text plus session findings and motivation as additional context.
    • Otherwise follow the manual steps below.
  2. Verify staged changes exist with git diff --cached --name-only

  3. Branch setup

    • If on main/master, create a short branch first: feature/short-topic, fix/short-topic, or docs/short-topic
    • Keep the branch suffix to 2-4 short words
    • Avoid long, overly specific, or sentence-like branch names
    • Use github-dev:commit-creator subagent to handle staged changes if needed, and pass session findings and motivation into the commit context
  4. Documentation check

    • Update README.md or docs based on changes compared to target branch
    • For config/API changes, use mcp__tavily__tavily_search to verify info and include sources
  5. Analyze all commits

    • Use git diff <base-branch>...HEAD to review complete changeset
    • PR message must describe all commits, not just latest
    • Focus on what changed from reviewer perspective
  6. Create PR

    • Use gh for GitHub operations and git only for local branch management
    • Use github-dev:pr-creator or gh pr create with parameters:
      • -t (title): a short human headline, capital first letter, no fix: or feat: prefix. Lead with the outcome in plain words, one idea not a list of everything the branch touched. Punchy beats exhaustive. A title is a headline, not a summary. Robotic: Align Claude Code install commands to the CLI form and tidy humanize docs Cooler: Put Claude Code on the same install CLI as everything else
      • -b (body): write it like a sharp teammate would, not a changelog. See PR Body Guidelines below.
      • -a @me (self-assign)
      • -r <reviewer>: Only add if the user explicitly asks OR recent PRs by this author have reviewers. Check with: gh pr list --repo <owner>/<repo> --author @me --limit 5 --json reviewRequests If recent PRs have no reviewers, skip -r entirely.

Read the full file on GitHub · 104 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. 3d ago First seen · 104 lines · 49 tokens per session scan A 97303d465ceb

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,117 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 1,270 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

github-pr-workflow

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

paperclipai/paperclip · 39 tokens

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Cline, Aider, Cursor exports, Hermes Agent, OpenCode, OpenClaw, Pi, Oh My Pi, Kimi CLI, Copilot-style logs, or generic JSON/JSONL traces for cost, tokens, tool failures, latency…

luoyuctl/agenttrace · 99 tokens

dsh-plugin-publisher

Publish a validated DSH plugin package (@deepseek-ai/dsh- or @lovstudio/dsh-) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin. 触发:发布插件 / 上架插件 / release dsh 插件。.

lovstudio/skills · 82 tokens

deep-research

Use when the user needs multi-source research with citation tracking, evidence persistence, structured report generation, or an implementation landscape that includes GitHub and other open-source forges. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends"…

lovstudio/skills · 101 tokens

lov-env-management

统一管理平台、账号与多组 API Key,维护有效期和启用状态,安全同步到 zsh 或用户会话环境,并提供脱敏 Dashboard;用户说“管理环境变量”“rotate API keys”时使用。.

lovstudio/skills · 53 tokens

lov-gh-access

Open a private GitHub repo to external clients or contractors without making it public. Accepts a mixed list of GitHub usernames and/or email addresses, resolves each to a GitHub account (falling back to an email invitation when the user has no discoverable account yet), and invites them as collaborators with a chosen…

lovstudio/skills · 151 tokens