Andrey Markin
  • home
  • services
  • projects
  • blog
  • directory
    • Tool
    • Library
    • Repo
    • Article
    • XTweet
    • Guideline
  • courses
  • resume
  • about
  • contact
  • meet

Mark Life Ltd

  1. Home
  2. Directory
  3. Auto Pr
Meet

Mark Life Ltd

BG208147965

HomeContactPrivacyLLM-friendlyBlog RSSDirectory RSS
  1. Directory
  2. auto-pr
RepoAI CodingOpen Sourceagentscli

auto-pr

Local Node.js loop that turns GitHub issues into pull requests — label an issue `auto-pr` and a multi-step Claude pipeline (research → plan → implement → review) spawns Claude Code and opens a PR.

Added February 22, 2026Francisco Hermida
Visit repo

I run this on a VPS as a systemd service. Open a GitHub issue, slap the auto-pr label on it, and the loop picks it up, spawns Claude Code through the full pipeline (research → plan → implement → review), and opens a PR back to the repo. The artifacts (research notes, plan, review) get committed alongside the PR branch, which is half the value — even when the PR isn't perfect, you learn something about your own codebase.

See Mark-Life/telegram-claude for examples of issues I've processed this way.

Update (May 13, 2026): Anthropic announced that this kind of headless Claude Code usage will be billed as API usage rather than counted against the Claude Code subscription, starting June 15, 2026. Worth factoring in before pointing this at a large issue backlog.

Related

  • netxjs-monorepoOpinionated Next.js + Turborepo starter with Biome linting, TypeScript, shadcn/ui, and pre-loaded Claude Code agent skills and hooks.
  • MediabunnyTypeScript library for reading, writing, and converting media files directly in the browser — like FFmpeg, but for the web. Zero dependencies, tree-shakable, and hardware-accelerated via the WebCodecs API.
  • deepsecAI-powered vulnerability scanner that uses coding agents to perform deep security analysis of codebases — regex-based candidate matching followed by LLM-driven investigation, with support for distributed execution and PR diff review.
  • Learn Harness EngineeringA 12-lecture curriculum on building effective harnesses that enable AI agents to complete complex tasks reliably — covering architecture, state management, session continuity, and observability patterns.