An analysis of the recent Claude Code source code leak, focusing on architectural patterns rather than just security drama. The article explores how a massive TypeScript codebase reveals sophisticated design choices for building reliable agentic systems. It covers memory management strategies like skeptical verification and semantic consolidation, efficient tool orchestration through permission gates and prompt cache sharing, and multi-agent coordination models that optimize token costs.
- Three-layer memory systems using indexes to prevent context entropy
- Background processes for autonomous memory pruning and merging
- Granular permission gating and large result offloading in tool architecture
- Cost-effective multi-agent communication via prompt cache sharing
- Risk classification tiers for safe autonomous operations
- Three-layer memory systems using indexes to prevent context entropy
- Background processes for autonomous memory pruning and merging
- Granular permission gating and large result offloading in tool architecture
- Cost-effective multi-agent communication via prompt cache sharing
- Risk classification tiers for safe autonomous operations
This article explores the concept of harness engineering, arguing that a functional AI agent is defined not just by its underlying model, but by the scaffolding built around it—including prompts, tools, sandboxes, and feedback loops. The author suggests shifting focus from picking the smartest model to designing robust systems that turn raw models into reliable agents. By treating mistakes as signals for new constraints rather than simple failures, engineers can create a ratchet effect that continuously improves agent performance through better configuration.
Main topics:
- Defining an agent as the combination of a model and its harness
- Reframing model errors as configuration or skill issues
- Using failure history to implement permanent rules via hooks and documentation
- Core primitives including filesystems, bash execution, sandboxes, and memory management
- Managing context rot through compaction and tool offloading
- Achieving long-horizon work through planning, verification, and agent splits
Main topics:
- Defining an agent as the combination of a model and its harness
- Reframing model errors as configuration or skill issues
- Using failure history to implement permanent rules via hooks and documentation
- Core primitives including filesystems, bash execution, sandboxes, and memory management
- Managing context rot through compaction and tool offloading
- Achieving long-horizon work through planning, verification, and agent splits
In this article, Neal Ford and Mark Richards explore the concept of "Architecture as Code," a method of documenting software architecture through code to create rapid feedback loops.
While originally intended to help human architects maintain structural integrity and coupling, the concept has become vital in the era of agentic AI.
By defining architectural constraints deterministically, architects can provide essential guardrails for AI agents, ensuring generated code adheres to principles like cyclomatic complexity and cohesion.
While originally intended to help human architects maintain structural integrity and coupling, the concept has become vital in the era of agentic AI.
By defining architectural constraints deterministically, architects can provide essential guardrails for AI agents, ensuring generated code adheres to principles like cyclomatic complexity and cohesion.
graphify is an AI coding assistant skill that transforms codebases, documents, and images into a structured, queryable knowledge graph. By utilizing deterministic AST parsing via tree-sitter for code and multimodal LLM capabilities for unstructured data like PDFs and screenshots, it creates a comprehensive map of concepts and relationships. This allows developers to understand complex architectures faster and find the "why" behind design decisions. A key advantage is its massive reduction in token usage per query compared to reading raw files, making it highly efficient for large-scale projects. The tool supports 19 programming languages and integrates seamlessly with platforms like Claude Code and Codex, providing an interactive, persistent, and highly organized way to navigate any codebase or research corpus.
This handbook provides a comprehensive introduction to Claude Code, Anthropic's AI-powered software development agent. It details how Claude Code differs from traditional autocomplete tools, functioning as an agent that reads, reasons about, and modifies codebases with user direction. The guide covers installation, initial setup, advanced workflows, integrations, and autonomous loops. It's aimed at developers, founders, and anyone seeking to leverage AI in software creation, emphasizing building real applications, accelerating feature development, and maintaining codebases efficiently. The handbook also highlights the importance of prompt discipline, planning, and understanding the underlying model to maximize Claude Code's capabilities.
A practical guide to Architecture Decision Records (ADRs) covering what they are, why they're important, how to use them, tools for managing them, writing good ones, when to use them, and organizing them.
