Claude Code: Visual Diagrams
49 interactive Mermaid diagrams organized in 12 thematic files. Each diagram includes a Mermaid version (rendered natively on GitHub) and an ASCII fallback.
For ASCII-only diagrams and a printable visual reference → visual-reference.md
Visual Palette
All diagrams use the consistent Bold Guy palette:
| Color | Hex | Usage |
|---|---|---|
| Warm Beige | #F5E6D3 | User actions, input nodes |
| Orange Brûlé | #E87E2F | Key decisions, Claude actions |
| Soft Green | #7BC47F | Success paths, recommendations |
| Alert Red | #E85D5D | Danger, anti-patterns, risks |
| Neutral Gray | #B8B8B8 | Infrastructure, passive elements |
| Light Blue | #6DB3F2 | Information, documentation refs |
Mermaid Conventions
| Shape | Syntax | Meaning |
|---|---|---|
| Rounded rect | (text) | Process step, action |
| Diamond | \{text\} | Decision point |
| Stadium | ([text]) | Start / End terminal |
| Hexagon | <code v-pre>{{text}}</code> | External system or API |
| Subroutine | [[text]] | Internal Claude Code component |
| Cylinder | [(text)] | Data store, persistent state |
Navigation
| File | Diagrams | Topics |
|---|---|---|
| 01-foundations.md | 4 | 4-layer model, workflow pipeline, decision tree, permission modes |
| 02-context-and-sessions.md | 4 | Context zones, memory hierarchy, session teleportation, fresh context |
| 03-configuration-system.md | 4 | Config precedence, skills vs commands vs agents, agent lifecycle, hooks |
| 04-architecture-internals.md | 4 | Master loop, tool categories, system prompt assembly, sub-agent isolation |
| 05-mcp-ecosystem.md | 4 | MCP ecosystem map, MCP architecture, rug pull attack, config hierarchy |
| 06-development-workflows.md | 5 | TDD cycle, spec-first pipeline, plan-driven, iterative refinement, AI fluency paths |
| 07-multi-agent-patterns.md | 6 | Agent topologies, worktrees, dual-instance, horizontal scaling, decision matrix, cross-session messaging |
| 08-security-and-production.md | 4 | 3-layer defense, sandbox decision, verification paradox, CI/CD pipeline |
| 09-cost-and-optimization.md | 4 | Model selection, cost optimization, subscription tiers, token reduction |
| 10-adoption-and-learning.md | 3 | Onboarding paths, UVAL protocol, trust calibration |
| 11-context-engineering.md | 4 | 3-layer context system, adherence degradation, modular architecture, rule placement |
| 12-enterprise-governance.md | 3 | Governance risk tiers, MCP approval workflow, data classification |
| Total | 49 |
Navigate by Use Case
"I'm new to Claude Code, where do I start?"
- Quick Decision Tree: Should I use Claude Code?
- 9-Step Workflow Pipeline: How does it work?
- Permission Modes: What are the safety modes?
- Onboarding Paths: Which path fits me?
"I want to understand the architecture"
- The Master Loop: Core execution engine
- System Prompt Assembly: How context is built
- 4-Layer Context System: The transformation model
- Tool Categories: What tools are available
"I'm worried about security"
- MCP Rug Pull Attack: The main threat vector
- 3-Layer Defense: How to protect yourself
- Sandbox Decision Tree: When to sandbox
- Verification Paradox: Don't trust Claude to verify itself
"I want to reduce my token costs"
- Model Selection Decision Flow: Pick the right model
- Cost Optimization Tree: Systematic cost reduction
- Token Reduction Pipeline: RTK + session hygiene
- Context Management Zones: Manage context size
"I want to use multiple agents"
- Agent Teams Topology: 3 orchestration patterns
- Multi-Instance Decision Matrix: Which pattern to use?
- Git Worktree Multi-Instance: Parallel isolation
- Sub-Agent Context Isolation: How agents are isolated
- Cross-Session Messaging: How independent sessions discover and message each other
"I want to set up MCP servers"
- MCP Ecosystem Map: What servers exist
- MCP Architecture: How it works
- MCP Config Hierarchy: Where configs live
"I want to govern Claude Code across my team"
- Governance Risk Tiers: Which control level fits your context?
- MCP Governance Workflow: Approval pipeline for MCP servers
- Data Classification Rules: What Claude can and cannot access
"I want to improve Claude's context adherence"
- Rule Placement Decision Tree: Where does this rule go?
- 3-Layer Context System: Global / Project / Session
- Context Budget & Adherence: Why rules stop being followed
- Modular Architecture: Path-scoping as the fix
Back to guide/README.md | ASCII diagrams → visual-reference.md