Flow

Overview

Flow packages a battle-tested workflow for shipping software with Claude Code. It wires up ten slash commands, eight specialized agents, and a handful of hooks so every session starts, runs, and ships consistently — while staying stack-agnostic by reading project specifics from a per-repo config.md.

Key features

1. 01

   Ten slash commands covering the full session lifecycle: init, start, continue, pause, push, plus autonomous autopilot

2. 02

   Eight specialized agents (investigator, architect, coder, reviewer, scout, issuer, websearch, ci-check) coordinated by a main orchestrator

3. 03

   Autopilot: an autonomous multi-sprint loop that spawns a non-overlapping agent team, deep-reviews, ships, and self-generates work via audit

4. 04

   Project-agnostic: dev/lint/test/build commands come from your repo's .claude/config.md

5. 05

   Deterministic shell helpers + a fast-by-default Stop hook with a one-shot build/test gate at deliberate push points

6. 06

   Issue tracking that adapts to your backend (GitHub Issues, Linear, or local files)

7. 07

   Deep-review mode that fans out parallel reviewers and loops fixes until clean

8. 08

   Secret guards on reads, writes, and shell; auto-saved cross-session memory; doc drift-check at pause

Use cases

• — Solo developers who want a repeatable AI workflow across many repos
• — Small teams standardizing how they ship features with Claude Code
• — Codebases that want consistent reviews, issue hygiene, and CI checks before push
• — Anyone tired of re-explaining their stack to Claude on every session