discover

name	Discover
description	Build the project profile through guided conversation — the grounding document every later phase reads. Establishes the mode and, for content projects, the work-unit registry.
argument-hint	[--refine] [--scan]

Discover — Build the Project Profile

A guided, conversational intake that produces .genesis/discovery/context.md — the single grounding document every later phase reads. Entry point of the pipeline; no prior approval required.

Inputs

• .genesis/project-state.md (the mode)
• .genesis/constitution/index.md (if it exists)
• The mode-specific template: discovery-greenfield.md / discovery-brownfield.md / discovery-lowfield.md
• An existing .genesis/discovery/context.md when --refine

Process

1. Read project-state.md; extract the mode. Branch all behavior on it.
2. If discovery already exists and --refine was not passed, ask redo-or-refine.
3. Run the mode-specific guided conversation (below).
4. Write .genesis/discovery/context.md and ask the user to confirm.

Greenfield — interview (7 areas)

Project Identity · Scope & Features · Constraints · Technology Preferences · Organizational Standards · Integration Points · Quality Expectations.

Brownfield — interview + scan + gap analysis

Greenfield's areas, plus:

• Codebase scan: languages/extensions, directory structure, test infrastructure, dependency health, CI/config, recent history (git log --oneline -50), documentation state.
• Human context: history, practices, pain points, tech debt, what works, improvement priorities.
• Gap analysis: classify each area Missing / Partial / Present, with a priority-ordered convergence plan.

Lowfield — interview + content scan + unit registry

Conversation (7 areas): Your Domain · Information Architecture · Workflow Stages (each becomes a pipeline stage) · Quality Standards · Progressive Reveal (sequential-discovery domains only) · Reference Materials · Tools & Formats. Then teach how the pipeline maps onto the domain and define the custom stages.

Unit registry (--scan to seed from existing files): map content files to unit IDs using a naming convention (propose, confirm), ask which stage each unit has reached, and write units.json:

{
  "feature": "<feature-name>",
  "convention": { "prefix": "U", "digits": 3, "separator": ": ", "example": "U001: Sample Title" },
  "units": [
    { "id": "U001", "title": "Chapter 1: The Beginning",
      "status": "in-progress", "currentStage": "dev-edit",
      "entryStage": "dev-edit", "aliases": [], "notes": "Imported from chapters/ch-01.md" }
  ]
}

Units with no content yet are status: pending; imported units are in-progress with currentStage/entryStage set.

Output

• .genesis/discovery/context.md — the structured profile. Brownfield appends scan results + gap analysis; lowfield appends content-type definitions, workflow descriptions, and a unit-registry summary.
• .genesis/features/<feature>/units.json (lowfield only).

Next step

Run /genesis-constitute.

Natural language triggers

- "discover"
- "tell genesis about my project"
- "profile this project"