Skip to main content

Getting Started

This section provides the entry point for adopting the methodology. The full onboarding process is documented in the setup guide; this section provides orientation.

Setup Guide: setup/SETUP-GUIDE.md in the s4u-methodology repository (link omitted from synced docs since the file lives outside the consuming repo's tree).

The setup guide is a 10-step interactive onboarding process. Each step reads the developer's existing configuration before proposing changes, shows a diff of what would change, and waits for approval before applying. Nothing is overwritten — all changes are additive, and the process can be reversed by restoring from the recommended backup.

Quick Start (3 Steps):

For developers who want to evaluate the methodology before committing to full setup:

  1. Install the Superpowers plugin: claude plugins install superpowers@superpowers-marketplace
  2. Run setup/bootstrap.sh <your-project-root> from this repo — it installs the corrected hooks (diff-aware Stop verification, lint-on-edit, pre-push gate, memory budget), the reviewer agents, the s4u skills, and the operating card.
  3. Read the operating card (docs/operating-card.md) — it is the ≤5K-token rule surface; this document is rationale and reference.

Adoption Tiers:

TierComponentsValue Provided
Core (non-negotiable)Required CI status checks on the default branch: full test suite (never -x first-failure abort), full lint (ruff check + ruff format --check, not rule subsets); CODEOWNERS-backed human review on safety paths; where the product has a user-facing safety surface, a deterministic safety-floor eval subset as a required check; the Brainstorm Gate including the safety-policy trigger (Section 3.1); the single-source rule (Section 4.5); silent-failure discipline R1-R3; worktree isolation for agent work; the testing standard (no-mocking default, migrated-schema oracle, live contract smoke)These are the gates with documented incident saves — code produced under them is trustworthy without relying on any individual's discipline
Recommended (strongly advised)Reviewer agent definitions, memory discipline (Section 6), the kit hook templates, generated STATE.md, the consolidation census cadence (Section 2.8)Development velocity and quality — proven valuable but divergence does not break integration
Project-specific (adopt with an ADR)Domain compliance architectures (e.g., Trust Relay's RLS and regulatory patterns — see the case studies in docs/showcase.md), a Docusaurus living-doc site, MCP server integrationsPowerful where the domain demands them; cargo-culting them into a project that doesn't is pure process weight

Permission mode is a security control, not a preference. Promptless agent action (dontAsk and equivalents) against anything that can reach production is a team-level decision with a stated default: plan mode or ask-permission for production-touching commands. The 2026-06-11 assessment (TA-06) found this classified as personal preference while another product's compliance architecture was "non-negotiable" — inverted priorities for a hospital-grade system.

The tier classification allows incremental adoption: start with Core (it is mostly one-time configuration — branch protection, CI flags, CODEOWNERS), add Recommended as value becomes apparent, and adopt Project-specific components only with a deviation ADR explaining why the domain needs them.