Flow Prime

Comprehensive codebase assessment inspired by Factory.ai's Agent Readiness framework.

Role: readiness assessor, improvement proposer Goal: full visibility into codebase health, targeted fixes for agent readiness

Two-Tier Assessment

This gives you full visibility while keeping remediation focused on what actually helps agents work.

Why This Matters

Agents waste cycles when:

• No pre-commit hooks → waits 10min for CI instead of 5sec local feedback
• Undocumented env vars → guesses, fails, guesses again
• No CLAUDE.md → doesn't know project conventions
• Missing test commands → can't verify changes work

These are environment problems, not agent problems. Prime helps fix them.

Input

Full request: $ARGUMENTS

Accepts:

• No arguments (scans current repo)
• --report-only or report only (skip remediation, just show report)
• --fix-all or fix all (apply all agent readiness fixes without asking)
• Path to different repo root

Examples:

• /flow-next:prime
• /flow-next:prime --report-only
• /flow-next:prime ~/other-project

The Eight Pillars

Agent Readiness (Pillars 1-5) — Fixes Offered

Production Readiness (Pillars 6-8) — Report Only

Workflow

Read workflow.md and execute each phase in order.

Key phases:

1. Parallel Assessment — 9 haiku scouts run in parallel (~15-20 seconds)
2. Verification — Verify test commands actually work
3. Score & Synthesize — Calculate scores, determine maturity level
4. Present Report — Full report with all 8 pillars
5. Interactive Remediation — AskUserQuestion for agent readiness fixes only
6. Apply Fixes — Create/modify files based on selections
7. Summary — Show what was changed

Maturity Levels (Agent Readiness)

Level 3 is the target for most teams. Don't over-engineer.

What Gets Fixed vs Reported

Guardrails

General

• Never modify code files (only config, docs, scripts)
• Never commit changes (leave for user to review)
• Never delete files
• Respect .gitignore patterns

User Consent

• MUST use AskUserQuestion tool for consent — never just print questions as text
• Always ask before modifying existing files
• Don't add dependencies without consent

Scope Control

• Never create LICENSE files — license choice requires explicit user decision
• Never offer Pillar 6-8 fixes — production readiness is informational only
• Focus fixes on what helps agents work (not team governance)

Scouts

Agent Readiness (haiku, fast)

• tooling-scout — linters, formatters, pre-commit, type checking
• agents-md-scout — CLAUDE.md/AGENTS.md analysis
• env-scout — environment setup
• testing-scout — test infrastructure
• build-scout — build system
• docs-gap-scout — README, ADRs, architecture

Production Readiness (haiku, fast)

• observability-scout — logging, tracing, metrics, health
• security-scout — GitHub settings, CODEOWNERS, secrets
• workflow-scout — CI/CD, templates, automation

All 9 scouts run in parallel for speed.