# Feature Flow — Full-Cycle Agentic Feature Delivery

> Hire us to transform your engineering organization into an agentic team — full-cycle AI delivery embedded into your culture, tooling, and people.

## Commands

Seven commands cover the full delivery lifecycle:

- `/feature:init` — Bootstrap workspace: directories, branch, .current state file
- `/feature:research` — 9-phase product discovery with resume from breakpoint (optional)
- `/feature:prd` — Generate PRD via structured discovery with 25-check validation gate
- `/feature:epic` — Split PRD into 2–5 INVEST epics using 9 proven patterns (optional)
- `/feature:arch` — Full architecture with wave agents, ADRs, and 48-check gate
- `/feature:tasks` — Vertical slice tasks plus mandatory wiring, integration, and docs tasks
- `/feature:impl` — 7-phase TDD loop per task: test → implement → review → commit

## Quality Gates

- PRD Validation: 25 checks, grade GOOD+ — fail action: iterate on PRD
- Epic Sizing: 2–5 epics, 100% FR coverage — fail action: warn at 6–7, block at 8+
- Architecture: FR 90%, NFR 90%, Quality 80% — fail action: max 3 fix iterations
- Build / Test: Zero errors, RED → GREEN state — fail action: retry implementer (budget: 3)
- Review: Zero issues ≥80 across 4 agents — fail action: split fix (max 2 cycles)

## Principles

1. Vertical slices — each task delivers handler + service + storage + test together
2. Subagent isolation — every agent starts with a fresh context window
3. Test writer isolation — the test-writing agent never sees implementation files
4. Split fix pattern — test fixer and code fixer never touch each other's files
5. Two-run architecture — design and ADRs in Run 1, human approves, assembly in Run 2
6. 100% traceability — every requirement traces from PRD through architecture to tests
7. Resume from breakpoint — each phase checks for existing artifacts before running
8. Parallel where independent — 4 reviewers, N component agents, 6 NFR agents

## Engagement Flow

### 01. Assessment (2–4 weeks)
We audit your current codebase, team setup, and delivery process to map where agentic development fits and what it will take to make it work.

### 02. Environment Setup (2 weeks)
We configure the pipeline for your stack — language, build commands, test runners, domain guides, and commit conventions — so agents operate in your context.

### 03. POC (4–6 weeks)
We deliver one full feature end-to-end: discovery, architecture, vertical-slice tasks, TDD implementation, and review. You see exactly what the output looks like.

### 04. Transformation (8+ weeks)
We embed the pipeline into your team's workflow, train your engineers on the framework, and run multiple features in parallel until agentic delivery is self-sustaining.

## Compatible Tools

Works alongside: Claude Code, Codex, Goose, Pi, Opencode, Warp, Cursor, Windsurf, GitHub Copilot.

## Links

- [Home](/)
- [Plain text for LLMs](/llms.txt)