create-pr-flow

create-pr-flow is a skill for Claude Code from avi1234/claude-team-plugins. It costs 15 tokens per session (349 once invoked), scanned A, original, MIT.

A pull-request workflow that checks a branch, runs the project's required checks, commits and pushes changes, opens or finds a pull request, and monitors CI.

In plain words
What is it for?
Preparing changes for review, creating a pull request, waiting for automated tests, and reporting the final status.
Why use it?
It gathers the repeated steps of preparing and verifying a pull request into one process that stops when a check fails.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the team1-plugin plugin — 3 skills, 1 hook 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/avi1234/claude-team-plugins/create-pr-flow
Any agent
npx skills add avi1234/claude-team-plugins --skill create-pr-flow
Clone the repo
git clone --depth 1 https://github.com/avi1234/claude-team-plugins

Made for: Claude Code.

Or install team1-plugin, the plugin that ships this one along with the rest of its 3 skills, 1 hook.

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-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/avi1234/claude-team-plugins/create-pr-flow.svg)](https://agentmods.dev/skills/avi1234/claude-team-plugins/create-pr-flow)
Your own site
<a href="https://agentmods.dev/skills/avi1234/claude-team-plugins/create-pr-flow"><img src="https://agentmods.dev/badge/skills/avi1234/claude-team-plugins/create-pr-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 349 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 5.1 $0.00015 $0.00349
Opus 5 $0.00008 $0.00175
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 5d ago against content hash a35e158cfb47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-pr-flow 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 5d 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.

team1-plugin/skills/create-pr-flow/SKILL.md · 46 lines

What it actually says

You are helping me with a complete PR workflow. Follow these steps:

1. Check Branch Safety

  • Get current branch
  • If "main" or "master", STOP with error

2. Run Definition of Done

  1. {YOUR_LINT_COMMAND}
  2. {YOUR_BUILD_COMMAND}
  3. {YOUR_TEST_COMMAND}
  4. {YOUR_FORMAT_COMMAND}

If any check fails, STOP and report the error. Do not proceed.

3. Commit and Push

  • Stage all changes
  • Generate meaningful commit message from staged diff
  • Commit and push to remote

4. Create or Find PR

  • Check if PR exists for current branch
  • If no PR:
    • Extract ticket from branch name (e.g., {YOUR_TICKET_PREFIX}-12345)
    • Use $ARGUMENTS as title if provided, otherwise generate: <ticket>: <summary>
    • Generate PR body with summary and key modifications
    • Create PR and extract PR number

5. Check CI

  • Check pipeline status for current repo + branch
  • If running: poll 60s intervals, max 15 attempts (display "waiting...")
  • If failed: show logs, ask for fixes, commit/push after confirmation, re-check
  • If success: report "CI passed"

6. Show Final Status

  • Display PR URL, state, and CI status

Notes

  • Stop on any command failure and report error
  • Keep me informed at each 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. 5d ago First seen · 46 lines · 15 tokens per session scan A a35e158cfb47

Subscribe to this mod's changes

create-pr-flow is a skill published in the GitHub repository avi1234/claude-team-plugins (5 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 349 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 2026-08-31.