In one line: Select tools by model capability and development phase, not by habit — this section is the decision matrix.
The methodology integrates plugins, MCP servers, and skills into a unified stack. Tool selection is capability-based.
Capability Assessment
Before selecting tools, assess the AI model's capabilities:
| Capability | How to Assess | Threshold |
|---|
| Context window | Check model documentation | Large (>200K), Medium (50-200K), Small (<50K) |
| Internal reasoning | Does the model have thinking/reasoning blocks? | Yes / No |
| Tool reliability | Can the model use tools (Read, Edit, Bash) without errors? | Reliable / Unreliable |
| Multi-step planning | Can the model decompose and execute 5+ step plans? | Yes / Needs guidance |
| Code understanding | Can the model read a 500-line file and modify precisely? | Full context / Needs navigation |
Code Navigation
| Capability | Recommendation |
|---|
| Large context (>200K) | Read files directly. Serena optional for complex refactoring. |
| Medium context (50-200K) | Serena recommended for find_symbol and get_symbols_overview. |
| Small context (<50K) | Serena required. Use codebase-memory-mcp for persistent code graph. |
Reasoning Support
| Capability | Recommendation |
|---|
| Internal reasoning (thinking blocks) | No external reasoning tool needed. |
| No internal reasoning | Sequential Thinking MCP for structured multi-step reasoning. |
| Audit trail required | Store reasoning chains in database fields, not external tools. |
Code Quality
| Layer | Tool | When |
|---|
| Real-time | TypeScript LSP, Pyright LSP | During implementation |
| Pre-commit | ruff (lint), pyright (types), tsc (TypeScript) | Every commit |
| Security | Aikido plugin (SAST, secrets) | During development |
| PR review | code-review plugin (5 Sonnet agents) | Before merging |
| PR security | claude-code-security-review GitHub Action | On every PR |
| Post-merge | code-simplifier (bloat detection) | After major features |
Brainstorm Phase
| Tool | Purpose | Capability Requirement |
|---|
| Visual companion (browser) | Mockups, diagrams | Any |
| Terminal discussion | Conceptual choices | Any |
| Architecture index lookup | Understand existing code | Any |
No code navigation tools needed — problem exploration doesn't need code access.
Design Phase
| Tool | Purpose | Capability Requirement |
|---|
| Architecture index | Find relevant doc pages | Any |
Serena get_symbols_overview | Understand existing interfaces | Medium/small context |
| Read tool | Read existing files directly | Large context |
Plan Phase
| Tool | Purpose | Capability Requirement |
|---|
Architecture index tests: field | Identify test files | Any |
Architecture index component_map | Map files to tasks | Any |
Implement Phase
| Tool | Purpose | Capability Requirement |
|---|
| Read / Edit / Bash | Direct file manipulation | Large context, reliable tools |
Serena find_symbol / replace_symbol_body | Precise symbol editing | Medium/small context |
| TypeScript LSP | Frontend type checking | Any (if available) |
| Context7 | Library documentation lookup | Any (prevents hallucinated APIs) |
| Temporal MCP | Workflow debugging | Projects using Temporal |
| Neo4j MCP | Graph queries | Projects using Neo4j |
Review Phase
| Tool | Purpose | Capability Requirement |
|---|
| code-review plugin | Multi-agent PR review | Any (uses Sonnet agents) |
| Domain-specific review agents | Compliance, security, API, migration | Project-specific |
| CodeRabbit | External AI review perspective | Optional (free tier) |
Verify Phase
| Tool | Purpose | Capability Requirement |
|---|
| Stop hook | Verify quality checks ran | Any |
Architecture index tests: | Verify RIGHT tests ran | Any |
| ruff / pyright / tsc | Lint + type check | Any |
| Aikido | Security scan | Any (if configured) |
Plugin Stack Reference
Essential (install for every project)
| Plugin | Install Command | Purpose |
|---|
| Superpowers | /plugin superpowers | Lifecycle skills |
| code-review | /plugin code-review | Multi-agent PR review |
| code-simplifier | /plugin code-simplifier | Code bloat detection |
Recommended (install based on stack)
| Plugin | Install Command | When |
|---|
| typescript-lsp | /plugin typescript-lsp | Frontend projects |
| pyright-lsp | /plugin pyright-lsp | Python projects |
| Serena | /plugin serena | Large codebases, medium/small context models |
| Server | Package | When |
|---|
| Context7 | Built-in | All projects (library docs) |
| Temporal MCP | temporal-mcp | Projects using Temporal |
| Neo4j MCP | @johnymontana/neo4j-mcp | Projects using Neo4j |
| codebase-memory-mcp | codebase-memory-mcp | Large codebases, token optimization |
| Sequential Thinking | sequential-thinking | Low-reasoning models, audit trail requirements |
AGENTS.md
The Linux Foundation's Agentic AI Foundation standard. A symlink to CLAUDE.md provides cross-tool compatibility:
ln -sf CLAUDE.md AGENTS.md
Read by: Cursor, Copilot, Codex, Gemini CLI, Jules, VS Code, and 60K+ projects.
Adoption Tier Impact
| Tier | Plugins | MCP Servers |
|---|
| Core | Superpowers, code-review | Context7 |
| Recommended | + code-simplifier, LSP plugins | + stack-specific (Temporal, Neo4j) |
| Full | + Serena, Aikido | + codebase-memory-mcp |
Competitive Landscape (March 2026)
| Methodology/Framework | Strengths | S4U Advantage |
|---|
| EY.ai PDLC | Enterprise scale, 80x speed claims | More developer-focused, regulatory integration |
| Xebia ACE | Fully agentic, persona-driven | Memory system, quality gates, compliance |
| Microsoft AI-Native | Good planning, 6 AI agents | Architecture-as-Code, documentation-first |
| Addy Osmani Workflow | Practical, AI-on-AI reviews | Formalized methodology, not individual tips |
| AGENTS.md Standard | Cross-tool, 60K+ projects | S4U is compatible via symlink |
S4U is the only published methodology combining: memory systems + subagent patterns + quality gates + regulatory compliance + Architecture-as-Code + capability-based tool prescription.