DevFlow

DevFlow — agentic coding that ships on real codebases

AI coding agents dazzle on a demo repo, then stall on a real ticket in a large production codebase. DevFlow is the Claude Code plugin that closes that gap — it carries one feature request all the way to a complete, tested, reviewed, documented pull request, so you do the final review and merge, not the cleanup.

Quick start

[!TIP] Just ask your agent. Paste this into Claude Code and it handles steps 1 and 2 for you — the install, the setup, and the PATH dependencies /plugin install doesn't cover. Then ship your first PR with step 3.

Read https://github.com/The01Geek/devflow-autopilot#quick-start and install DevFlow and its dependencies.

1. Install (two commands — run in order; works in any shell):

claude plugin marketplace add The01Geek/devflow-autopilot
claude plugin install devflow@devflow-marketplace

2. Set up — launch Claude Code and scaffold your config:

claude /devflow:init   # launches Claude Code and scaffolds your config

3. Ship a PR — turn a feature request into a reviewed, documented pull request:

/devflow:create-issue <user_story>
/devflow:implement <issue_number>

The local tier runs with zero configuration — every value already has a built-in default. /devflow:init is recommended: it keeps the plugin auto-updated and writes a .devflow/config.json you can tweak. See Installing & updating for the full options (the zero-dependency install, PyYAML, the cloud tier) and Requirements for the handful of tools it expects on your PATH.

Why DevFlow

• Ships the whole PR, not a fragment — grounded in your architecture and patterns, with the tests the change actually needs, on production code. How it's different →
• Review that fixes what it finds — and audits itself — the review-and-fix loop applies fixes and re-reviews until it approves, then a structurally-independent shadow pass re-checks the approval. Skills and agents →
• Docs stay in sync — internal docs, external docs, and release notes kept aligned with the code in the same run.
• It learns every week — a retrospective loop reads the trail of merged PRs and files human-reviewed issues that prevent the next recurring failure.
• Zero-config to start — the local tier runs entirely inside Claude Code with no infrastructure; an optional cloud tier runs it autonomously on GitHub.

▶ See the full loop in the interactive one-pager →

How it's different

The thesis isn't code generation — it's disciplined, auditable AI software delivery at production scale. A single LLM pass is variable; DevFlow's architecture is built around not trusting any single pass.