Skip to main content

Tool Ecosystem

The methodology integrates plugins, MCP servers, and skills into a unified tool stack. Tool selection is capability-based (see appendix-i-tool-selection.md).

Capability Assessment

Before selecting tools, assess the AI model's capabilities:

CapabilityHow to AssessThreshold
Context windowCheck model documentationLarge (>200K), Medium (50-200K), Small (<50K)
Internal reasoningDoes the model have thinking/reasoning blocks?Yes / No
Tool reliabilityCan the model use tools (Read, Edit, Bash) without errors?Reliable / Unreliable
Multi-step planningCan the model decompose and execute 5+ step plans?Yes / Needs guidance
Code understandingCan the model read a 500-line file and modify precisely?Full context / Needs navigation

Tool Recommendations by Capability

Code Navigation

CapabilityRecommendation
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

CapabilityRecommendation
Internal reasoning (thinking blocks)No external reasoning tool needed.
No internal reasoningSequential Thinking MCP for structured multi-step reasoning.
Audit trail requiredStore reasoning chains in database fields, not external tools.

Code Quality

LayerToolWhen
Real-timeTypeScript LSP, Pyright LSPDuring implementation
Pre-commitruff (lint), pyright (types), tsc (TypeScript)Every commit
SecurityAikido plugin (SAST, secrets)During development
PR reviewcode-review plugin (5 Sonnet agents)Before merging
PR securityclaude-code-security-review GitHub ActionOn every PR
Post-mergecode-simplifier (bloat detection)After major features

Tool Recommendations by Development Phase

Brainstorm Phase

ToolPurposeCapability Requirement
Visual companion (browser)Mockups, diagramsAny
Terminal discussionConceptual choicesAny
Architecture index lookupUnderstand existing codeAny

No code navigation tools needed — problem exploration doesn't need code access.

Design Phase

ToolPurposeCapability Requirement
Architecture indexFind relevant doc pagesAny
Serena get_symbols_overviewUnderstand existing interfacesMedium/small context
Read toolRead existing files directlyLarge context

Plan Phase

ToolPurposeCapability Requirement
Architecture index tests: fieldIdentify test filesAny
Architecture index component_mapMap files to tasksAny

Implement Phase

ToolPurposeCapability Requirement
Read / Edit / BashDirect file manipulationLarge context, reliable tools
Serena find_symbol / replace_symbol_bodyPrecise symbol editingMedium/small context
TypeScript LSPFrontend type checkingAny (if available)
Context7Library documentation lookupAny (prevents hallucinated APIs)
Temporal MCPWorkflow debuggingProjects using Temporal
Neo4j MCPGraph queriesProjects using Neo4j

Review Phase

ToolPurposeCapability Requirement
code-review pluginMulti-agent PR reviewAny (uses Sonnet agents)
Domain-specific review agentsCompliance, security, API, migrationProject-specific
CodeRabbitExternal AI review perspectiveOptional (free tier)

Verify Phase

ToolPurposeCapability Requirement
Stop hookVerify quality checks ranAny
Architecture index tests:Verify RIGHT tests ranAny
ruff / pyright / tscLint + type checkAny
AikidoSecurity scanAny (if configured)

Plugin Stack Reference

Essential (install for every project)

PluginInstall CommandPurpose
Superpowers/plugin superpowersLifecycle skills
code-review/plugin code-reviewMulti-agent PR review
code-simplifier/plugin code-simplifierCode bloat detection
PluginInstall CommandWhen
typescript-lsp/plugin typescript-lspFrontend projects
pyright-lsp/plugin pyright-lspPython projects
Serena/plugin serenaLarge codebases, medium/small context models

MCP Servers (configure based on stack)

ServerPackageWhen
Context7Built-inAll projects (library docs)
Temporal MCPtemporal-mcpProjects using Temporal
Neo4j MCP@johnymontana/neo4j-mcpProjects using Neo4j
codebase-memory-mcpcodebase-memory-mcpLarge codebases, token optimization

Cross-Tool Compatibility

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

TierPluginsMCP Servers
CoreSuperpowers, code-reviewContext7
Recommended+ code-simplifier, LSP plugins+ stack-specific (Temporal, Neo4j)
Full+ Serena, Aikido+ codebase-memory-mcp

Competitive Landscape (March 2026)

Methodology/FrameworkStrengthsS4U Advantage
EY.ai PDLCEnterprise scale, 80x speed claimsMore developer-focused, regulatory integration
Xebia ACEFully agentic, persona-drivenMemory system, quality gates, compliance
Microsoft AI-NativeGood planning, 6 AI agentsArchitecture-as-Code, documentation-first
Addy Osmani WorkflowPractical, AI-on-AI reviewsFormalized methodology, not individual tips
AGENTS.md StandardCross-tool, 60K+ projectsS4U 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.

Essential Plugins

PluginPurposeInstall
SuperpowersLifecycle skills (brainstorm, plan, execute, review)/plugin superpowers
code-reviewMulti-agent PR review (5 parallel Sonnet agents)/plugin code-review
code-simplifierCode bloat detection (3 review agents)/plugin code-simplifier
PluginPurposeWhen
typescript-lspReal-time TypeScript diagnosticsFrontend projects
pyright-lspReal-time Python type diagnosticsPython projects
SerenaSymbol-level code navigationMedium/small context models, complex refactoring

MCP Servers

ServerPurposeWhen
Context7Up-to-date library documentationAll projects
Temporal MCPNatural-language workflow managementTemporal-based projects
Neo4j MCPGraph database queries via natural languageNeo4j-based projects
Sequential ThinkingStructured reasoning captureLow-reasoning models, audit trail requirements

Cross-Tool Compatibility

AGENTS.md (symlinked to CLAUDE.md) provides cross-tool compatibility with Cursor, Copilot, Codex, Gemini CLI, and 60K+ projects under the Linux Foundation's Agentic AI Foundation standard.

ln -sf CLAUDE.md AGENTS.md