Charts & manuals
Guides
Long-form walkthroughs to help you get the most out of the Claude ecosystem. The first batch is on its way.
- MCP Servers
Debugging MCP Servers: Inspector, Packet Capture, and Failure Modes (2026)
MCP protocol-level debugging — drive servers with MCP Inspector, capture JSON-RPC traffic, stdio vs HTTP differences, five real bug reproductions, plus preventive observability and spec-upgrade (2026-07-28) troubleshooting.
- Skills & Commands
Claude Code in GitHub Actions: @claude Mentions, PR Reviews, and Scheduled Automation (2026)
Wire Claude Code into GitHub Actions — @claude mentions, PR reviews, cron triggers, auth and permissions, fork-PR secrets behavior, copy-pasteable workflow templates, plus four cost-operations levers and an org-level rollout governance checklist.
- MCP Servers
Deploying MCP Servers with Docker: Catalog, Gateway & Compose Orchestration (2026)
A 2026 guide to running MCP servers in Docker — the stdio-vs-container mismatch, the 300+ server MCP Catalog with signed images, the docker mcp CLI and Gateway (stdio/sse/streaming, auth, secrets), Claude Desktop and Claude Code wiring, Compose orchestration, and what the 2026-07-28 stateless spec means for K8s.
- MCP Servers
What Is the Model Context Protocol? From Concept to Your First MCP Server (2026)
A 2026 walkthrough of the Model Context Protocol (MCP) — what it solves, the Host/Client/Server triangle, the three primitives (tools/resources/prompts), stdio vs Streamable HTTP transports, the 2026 ecosystem in three layers (hosts, servers, directories), and five common misconceptions debunked.
- Skills & Commands
Claude Computer Use Deep Dive: Screenshots, Mouse, Keyboard, and Production Sandbox (2026)
Turn Claude into a visual agent that drives any GUI — the computer tool, model and tool versions (computer_20250124), 16 actions, a minimal screenshot-decide-act loop, token budgets, mandatory isolation, three production use cases, plus six visual-agent failure patterns (HiDPI coordinates, sandbox egress, sensitive actions) and an evaluation quality gate.
- Prompt Libraries
Claude Extended Thinking in Practice: Migrating from budget_tokens to Adaptive Thinking (2026)
A 2026 field guide to Claude extended thinking — budget_tokens rules and billing semantics, the adaptive-thinking model matrix (Fable/Mythos adaptive-only, 5-series default-on), effort levels low to max, output_config placement traps, caching interplay, and a migration decision framework.
- SDKs & Tooling
Building Autonomous Workflows With the Claude Agent SDK
How to embed the Claude Code agent loop in your own programs with the Claude Agent SDK — installation, a minimal async example, custom tools via MCP, loop control with tool limits and hooks, parallel subagent fan-out and hooks-driven audit trails, plus six anti-patterns that send agent loops off the rails and a full evaluation method.
- MCP Servers
MCP Transports Explained: stdio vs Streamable HTTP — Choosing the Right One (2026)
A 2026 walkthrough of MCP's two transports — stdio (local subprocess) and Streamable HTTP — covering JSON-RPC framing, the handshake, OAuth 2.1, session state, debuggability, and a selection matrix, plus five transport incident patterns and the full impact of the 2026-07-28 spec change (stateless MCP, Mcp-Session-Id removal).
- Skills & Commands
Claude Code Self-Hosted Environments: Run Cloud Sessions on Your Own Compute (2026)
A 2026 guide to Claude Code self-hosted environments — the Environment/Runner/Session model, outbound-only security boundary, quickstart commands, Kubernetes and Compose deployment with drain control, and why model traffic can't route through Bedrock or an LLM gateway.
- Prompt Libraries
Claude Prompt Engineering: Eight Core Patterns, Pitfalls, and Real-World Prompts (2026)
A field guide to the prompt patterns that hold up in real Claude projects — role prompting, few-shot, chain-of-thought, ReAct, self-consistency, XML structure, layered system prompts, self-critique — plus common anti-patterns for single-turn and multi-turn prompts, three annotated production prompts, and a full eval-pipeline framework for iterating prompts.
- MCP Servers
MCP Authorization: OAuth 2.1, CIMD, and Step-Up Flow Done Right (2026)
How MCP authorization works in the 2025-11-25 spec: Protected Resource Metadata discovery, Client ID Metadata Documents vs dynamic registration, RFC 8707 resource binding, and step-up authorization — plus symptom-driven OAuth debugging and three end-to-end integration walkthroughs. Updated Sep 2026.
- Skills & Commands
The Complete Claude Code Guide: From First Install to Daily Workflow (2026)
A 2026 walkthrough of Claude Code — installing the CLI, /init project seeding, CLAUDE.md memory strategy, four permission modes (default/acceptEdits/plan/bypassPermissions), MCP server integration, six most-used commands, CI/Docker production deployment, plus context-management pitfalls and three full task walkthroughs.
- Plugins & Agents
Claude Code vs Cursor vs Aider vs Cline vs Continue: A Practical Comparison
An honest comparison of five AI coding tools on the axes that matter — where they live, how autonomous they are, model choice, open-source status, and MCP support — without declaring a universal winner. Includes a scenario-to-tool decision matrix and three tested migration paths (Cursor / Cline / Aider → Claude Code) with dual-run rollout advice.
- SDKs & Tooling
Claude Agent SDK Deep Dive: From First query() to Multi-Agent Orchestration (2026)
A 2026 field guide to the Claude Agent SDK — the same agent loop that powers Claude Code, exposed as Python and TypeScript libraries. Covers the query() async-generator API, every ClaudeAgentOptions field, MCP server wiring, hooks + audit trails, multi-agent fan-out orchestration with asyncio.gather, five production guardrails (idempotency / cost / secrets / determinism / evaluation), and the three official deployment shapes (managed-agents-observe, self-hosted sandbox, worker dispatch).
- Skills & Commands
Claude Code Statusline: The stdin JSON Protocol and Reusable Script Templates (2026)
A 2026 guide to the Claude Code statusline — the statusLine setting, the full stdin JSON protocol (model, context_window, cost, rate_limits), three copy-paste bash templates, event-driven refresh timing, and the five fastest fixes for a blank status line.
- Tutorials & GuidesMonthly update
ClaudeMap Monthly Update — August 2026
The first monthly update: 85 resources charted in August (official MCP servers from MongoDB, Redis, Sentry, Cloudflare, AWS, and Docker), 16 guides live, and site improvements including privacy/terms pages and richer detail pages.
- SDKs & Tooling
Claude Prompt Caching Deep Dive: 10x Cheaper Claude API Calls (2026)
A 2026 deep dive on Claude API Prompt Caching — four-tier pricing, cache_control breakpoint strategy, 5-min vs 1-hour TTL trade-offs, stacking with Batch API, multimodal caching (image / PDF blocks), and the five most common failure modes (below-threshold input, breakpoint change, TTL expiry, model namespace mismatch, mis-placed cache_control).
- Skills & Commands
Claude Code Hooks and Subagents: Deterministic Automation and Parallel Work
How to run scripts at Claude Code lifecycle events with hooks (PreToolUse, PostToolUse, Stop) and spin up specialized parallel agents with subagents — plus underused events (SessionStart, SubagentStop, PreCompact) for state injection and audit, and fine-grained subagent frontmatter (disallowedTools, permissionMode, maxTurns) for production safety.
- SDKs & Tooling
Getting Started With the Claude API: Your First Call, Streaming, and Tool Use
A beginner-friendly walkthrough of the Claude API — getting an API key, your first messages.create call in Python and TypeScript, streaming responses, wiring up tool use, plus production patterns for error handling, rate limits with exponential backoff, and stacking prompt caching + the Batch API to cut costs by ~80%.
- Skills & Commands
Claude Code Subagents Deep Dive: Parallel Research, Restricted Tools, Nested Tasks (2026)
A 2026 deep dive on Claude Code subagents — five scope layers (managed / CLI flag / project / user / plugin), the full frontmatter field set, built-in agent trade-offs, context isolation, SendMessage resume reuse, nesting depth and concurrency limits, and the 2026 worktree + background combination pitfall.
- MCP Servers
Configuring MCP Servers in Claude Desktop and Claude Code (2026)
A 2026 guide to the MCP server config format — where Claude Desktop and Claude Code read their config, layered precedence (MDM / project / user), stdio vs HTTP shapes, working examples for filesystem / GitHub / Postgres servers, OAuth scope drift debugging, and a 7-step troubleshooting checklist.
- Skills & Commands
Claude Code Skills: SKILL.md, Plugins, and Subagents — A Complete Guide (2026)
How Claude Code skills work in 2026: the SKILL.md frontmatter, progressive disclosure, debugging skill triggers, packaging as plugins, and a real PR-review walkthrough with hooks and subagents.