Prompts, evaluations, harnesses, case studies, code labs, and tips and tricks for using coding agents effectively as a power user on Claude, Codex, and friends.
The hooks system — nine lifecycle events, prompt-based and command-based hooks, a JSON I/O contract, and a self-referential loop pattern — turns Claude Code from a tool into a programmable platform.
How a three-level filesystem-based loading system lets agents carry dozens of capabilities while paying context cost only for what gets used.
Why a skill could not enforce 'rewrite-only' behavior in Codex, and how a TUI-level interceptor with grounded refinement and per-task profiles solves it instead.
A self-paced quiz with 112 questions to rehearse the judgment calls the certification actually tests for.
How Claude Code agent skills turn repeated instructions into reusable task knowledge that loads only when the task calls for it.
A practical decision guide for deploying MCP servers covering transport selection, who pays for the LLM calls, filesystem security, and the mental model behind the three primitives.
A reliability-first approach to choosing between predictable workflows and flexible agents, with four reusable patterns and concrete selection heuristics.
How Claude Code subagents actually work under the hood — context isolation as the core primitive, the description field as a hidden control mechanism, and the anti-patterns that waste tokens.
The system prompt has evolved from a conversational hint into a load-bearing piece of production architecture — and it demands the same discipline we apply to config files, database schemas, and deployment pipelines.
Systematic prompt evaluation with automated test generation, dual grading systems, and measurable score progression across iterations.
Prompt caching's constraints — one-hour TTL, four breakpoints, exact-match requirements, 1,024-token minimum — are not arbitrary limits. They are a design language that pushes toward specific architectural patterns.
What happens when custom tooling is built to observe how AI coding agents actually work? An experiment in understanding Claude Code through session-level observability.
When your platform has 2,000+ API endpoints across microservices and gateway layers, the surface is constantly changing. Documentation goes stale, new use cases reshape input and output schemas, and a spec-driven CLI turns API exploration into agent-ready discovery.
A production reference for three Claude features that meaningfully change how you build — manual cache breakpoints, auditable reasoning, and per-claim source tracking.
Production prompt engineering depends on iteration, edge-case design, refusal handling, and structured outputs that downstream systems can trust.
Delegation, description, discernment, and diligence turn AI use from one-off prompting into repeatable collaboration.
A concise reference for system prompts, user messages, prompt structure, and the prompt components worth reaching for first.
Four durable properties explain where generative AI is useful, where it fails, and how to calibrate trust before using it.
A test-driven prompt engineering system for extracting structured review data from HTML with fixture-backed validation and iterative model calibration.