Navigation Explore Code Guide
Sitemap
Curated navigation for cc.bruniaux.com: 170 links across 19 sections. For every indexable URL, use the complete XML sitemap.
Start 5
- Guide portal Browse the curated guide map and current highlights.
- Quick Start Install Claude Code and complete a first task.
- Learning Paths Follow structured and role-aware learning routes.
- Quick Reference Use the daily command and configuration reference.
- AI Roles Choose a route based on responsibilities and career direction.
Build 8
- Agent Harness Engineering Design the reliability layer around an agent loop.
- Loop & Graph Engineering Build bounded loops and executable workflow graphs.
- Context Engineering Control context budgets, assembly, and measurement.
- Memory Systems Compare native, cross-session, and team-shared memory.
- Workflows Use runnable patterns for planning, delivery, and delegation.
- Methodologies Choose and combine disciplined development methods.
- MCP or CLI? Choose the smallest interface that fits the task.
- Examples Browse reusable agents, skills, hooks, and workflows.
Scale 11
- Security Navigate threat intelligence and hardening guidance.
- Enterprise Governance Define usage charters, approvals, and risk tiers.
- Observability Trace failures, reliability signals, cost, and recovery.
- Team Metrics Measure delivery and agent-specific outcomes.
- Team Adoption Plan rollout, shared practice, and trust calibration.
- AI FinOps Understand cost regimes, levers, and dated market prices.
- LLM Market Snapshot Compare source-checked API prices and subscription quotas.
- Subscription Strategy Compare seats, APIs, gateways, and self-hosting scenarios.
- AI Unit Economics Calculate task-level spend and accepted outcomes.
- Team Knowledge Choose between Markdown, live connectors, and RAG.
- API Gateway Govern routed traffic, budgets, and attribution.
Resources 11
- Resource Hub Browse the public collections and reference formats.
- Downloads Download PDF and EPUB editions.
- Cheat Sheets Browse printable recap cards by series.
- Ebooks Read the French and English long-form editions.
- Diagrams Browse architecture and workflow diagrams.
- Ecosystem Explore complementary tools and integrations.
- Compare Compare Claude Code with other coding tools.
- Glossary Look up Claude Code and agent-engineering terminology.
- FAQ Read direct answers to recurring questions.
- Guide MCP Server Install the guide as an MCP server.
- Related Projects Browse companion open-source projects.
Updates 3
Security 4
- Threat intelligence Attack techniques, campaigns, malicious skills, and sourced AgentSec events
- CVE database Search vulnerabilities, documented fixed versions, mitigations, and sources
- Sandbox security Isolation boundaries, silent failure modes, configuration, and runtime verification
- Security hardening Five-minute, workstation, and team controls with tools and checklists
AI cost 1
Lean and AI 1
Core Reference 13
- Ultimate Guide The complete chapter-by-chapter reference.
- Translations Verified status for English, French, Chinese, Ukrainian, and Latin American Spanish.
- Cheatsheet Essential commands and configuration on one page.
- Architecture Master loop, tool execution, context, and internal boundaries.
- Tools Reference Built-in tools, permissions, timeouts, and behaviors.
- Hooks & Events Reference Hook events, matchers, schemas, decisions, and timeouts.
- Settings Reference Confirmed settings and environment variables.
- Methodologies Development methodologies and combination patterns.
- Visual Reference Compact diagrams for core concepts.
- Known Issues Critical bugs and verified operational limits.
- Glossary Claude Code and agent-engineering terminology.
- Community Patterns Community-coined workflows and engineering patterns.
- Skill Design Patterns Architectural patterns for robust, efficient skills.
Agent Engineering 6
- Agent Harness Engineering Runtime reliability architecture around the model.
- Loop & Graph Engineering Bounded loops, executable graphs, durable state, and judgment.
- Agent Harness Landscape Evidence-backed map of runtimes and adjacent systems.
- Agentic Tools Detailed tool profiles and comparison matrix.
- Agent Evaluation Measure model-harness quality across repeated runs.
- Agentic Software Factories Operating model from one session to a governed factory.
Context, Memory & Economics 8
- Context Engineering Token budgets, modular context, ACE, and quality measurement.
- Memory Systems Native, cross-session, and team-shared memory.
- Team Knowledge Infrastructure Markdown, live connectors, and RAG at team scale.
- Local vs Cloud Inference Hardware, rental, API, throughput, and TCO boundaries.
- AI FinOps Section entry point: three cost regimes, the FinOps loop, and the lever map.
- LLM Market Snapshot Source-checked API prices, subscription quotas, and data location, dated Sep 30, 2026.
- AI Unit Economics Accepted-task cost, three-level routing, cache effects, progressive spend controls, and break-even.
- Subscription Strategy Seats, Enterprise usage, gateways, and self-hosting scenarios.
Security & Governance 6
- Security Hardening Threat model, MCP vetting, and prompt-injection defenses.
- Sandbox Isolation Local and cloud isolation trade-offs.
- Native Sandbox Claude Code sandbox configuration and limits.
- Production Safety Guardrails, review gates, rollback, and recovery.
- Data Privacy Data flows, retention, and privacy controls.
- Enterprise Governance Usage charters, approval workflows, and risk tiers.
Operations & Team Adoption 6
- DevOps & SRE Infrastructure diagnosis and incident response.
- Observability Traces, reliability signals, cost, and recovery metrics.
- API Gateway Routing, progressive spend policy, terminal budgets, allowlists, and attribution.
- AI Traceability Attribution, disclosure, audit trails, and compliance.
- Team Metrics DORA, SPACE, Core 4, and agent-specific signals.
- Adoption Approaches Rollout strategies, trust calibration, and evidence.
Ecosystem & Tools 9
- Mistral Large 4 Dated launch evidence, API prices, benchmarks, and deployment limits.
- AI Ecosystem Complementary AI tools and multi-provider workflows.
- MCP Servers Ecosystem Validated MCP servers and production configuration.
- MCP vs CLI Choose the smallest tool interface for the job.
- Third-Party Tools GUIs, TUIs, config managers, and token trackers.
- Context Engineering Tools Compression, RAG, gateways, and LLMOps tooling.
- Remarkable AI Power-user patterns and noteworthy projects.
- Practitioner Insights Attributed video, conference, and academic evidence.
- AI Executive Agents Virtual C-suites, board simulators, and governance limits.
Roles & Learning 6
- AI Roles Role definitions, routing, and the interactive quiz.
- Learning with AI Build skills without outsourcing understanding.
- For Product Managers Specs, review, and prototyping for PMs.
- For Tech Leads Shared config, rollout, and safety for leads.
- For CTOs Business case, governance, and adoption metrics.
- For CIOs & CEOs Executive brief and decision boundaries.
Workflows 14
- All Workflows Browse the complete workflow index.
- TDD with Claude Test-driven development with an agent.
- Spec-First Intent, specification, plan, and implementation gates.
- Plan-Driven Use planning as an explicit control boundary.
- Agent Teams Multi-agent coordination and worktree isolation.
- Dynamic Workflows Deterministic orchestration, fan-out, and resume.
- Monitor & Safe Delegation Event ingestion, verification, and gated handoff.
- Team AI Instructions Scale shared instructions across developers and tools.
- Production Reliability Escalation, circuit breakers, and graceful degradation.
- Review code with a repeatable multi-provider workflow Use independent providers, fixed review criteria, and a human acceptance gate.
- AI-Assisted Open Source Contributions Project policy, reproduction, author understanding, verification evidence and maintainer follow-up.
- Multi-Provider Code Review Independent review across providers and evidence sources.
- Cross-Session Messaging Discover and communicate between independent sessions.
- Search Tools Mastery Combine lexical, semantic, and structural search.
Cheat Sheets: Technical series 22
- T01: Essential Commands Keyboard shortcuts & indispensable slash commands
- T02: Non-Interactive & Headless Mode Using Claude Code without human interaction: scripts, CI, pipes
- T03: Permission Modes Tool access control, from safest to most permissive
- T04: Permissions: Glob Patterns & Whitelist Precisely controlling accessible tools with glob patterns
- T05: Configuration Hierarchy Where to configure what, from global to local
- T06: Settings.json: Complete Structure All configuration keys and their scope
- T07: CLAUDE.md Best Practices Writing effective instructions that Claude reads every session
- T08: Auto-Memories: When and How The automatic memory system vs manual CLAUDE.md
- T09: Workspace Hygiene Keeping context clean by blocking what Claude should not read
- T10: Multi-Machine Config & Backup Syncing your Claude Code configuration across multiple machines
- T11: Search Tools Decision Tree Choosing between Glob, Grep, Read, Agent and Bash based on context
- T12: MCP Servers Overview The extension protocol and essential servers
- T13: Context7 & Sequential MCP Official documentation and multi-step reasoning within reach of a prompt
- T14: Grepai: Semantic Search Finding code by intent, not by regex
- T15: MCP Secrets Management Managing MCP server credentials without exposing them
- T16: Native Sandbox: Architecture How Claude Code isolates its operations at the OS level
- T17: Sandbox: Native vs Docker Choosing the right isolation level for your context
- T18: Models & Thinking Modes Choosing the right model and the right level of reasoning
- T19: Context Window: 200K vs 1M When to switch to the extended context window and at what cost
- T20: Token Optimization Reducing token consumption without losing quality
- T21: Fast Mode & API Breaking Changes Fast mode and the major API changes you need to know
- T22: Third-Party Tools The essential complementary tools in the ecosystem
Cheat Sheets: Methodology series 22
- M01: Daily Workflow The optimal routine for a productive development session
- M02: Context Management Managing the context window for efficient sessions
- M03: Sessions & Continuity Resuming a session right where you left off
- M04: Compact vs Clear When to summarize and when to reset the context
- M05: Plan Mode Let Claude plan before acting
- M06: Task Management System Organize Claude's work with the Tasks API
- M07: TodoWrite vs Tasks API The old and new task management systems
- M08: Custom Agents Create specialized sub-agents to delegate tasks
- M09: Slash Commands Manually triggered skills via /name (CC 2.1.3)
- M10: Skills Reusable skill modules with embedded resources
- M11: Hooks: Events & System Automatically react to Claude Code actions
- M12: Hooks: Concrete Patterns Practical hook examples to automate your workflow
- M13: Worktrees Work in parallel on multiple branches without switching directories
- M14: Plan-Validate-Execute Pipeline The production 3-command workflow: research, validation, execution to a merged PR
- M15: TDD / BDD / SDD Workflows Structured development methodologies with Claude Code
- M16: Multi-Agent: Topology & Orchestration Architecting agent teams for complex tasks
- M17: Multi-Agent: Communication & Trust Passing context between agents and managing trust levels
- M18: Event-Driven Agents Triggering agents automatically from GitHub, Linear, Jira
- M19: GitHub Actions + Claude Code Integrating Claude Code into GitHub CI/CD pipelines
- M20: CI/CD & Production Security Using Claude Code in production with the right security guarantees
- M21: Methodical Debugging Structured approach to diagnosing and resolving errors
- M22: Observability: JSONL & jq Auditing and analyzing Claude Code activity through logs
Cheat Sheets: Design series 14
- C01: Trust Calibration & Mental Model How to think about your relationship with Claude to get the most out of it
- C02: Prompting Basics for Claude Code The principles that make the difference between a good and a bad prompt
- C03: XML Prompting & Semantic Anchors Structuring complex prompts for reproducible results
- C04: Skills, Plugins & Agents Choosing the right extension mechanism for the task
- C05: Memory Stack (4 levels) Where the information Claude uses lives and how to manage it
- C06: Configuration Decision Guide Which configuration mechanism to use based on the situation
- C07: Team Conventions at Scale Synchronizing Claude Code practices across a team of 5+ developers
- C08: Attack Surface & Threats Understanding the attack vectors specific to Claude Code
- C09: Prompt Injection: Defenses Protecting Claude Code when processing untrusted external content
- C10: AI Traceability Tracking AI contributions in code and commits
- C11: Subscription vs API: Cost Patterns Understanding when each billing model is advantageous
- C12: Agent SDK & IDE Integrations Integrating Claude Code into Xcode, VS Code, and other environments
- C13: Common Mistakes Frequent pitfalls and how to avoid them
- C14: Agent Harness Map Choose a runtime, repository contract, or orchestrator