AI coding agents have a context problem. The tools solving it fall into four categories: context packers, code graphs, memory systems, and runtime observability. Each solves one piece. None versions the intelligence. None proves anything. None learns without poisoning itself over time. This article explores the landscape and argues that content-addressed code graphs with cryptographic proofs are the missing foundation.
Git proved that content-addressing file contents gives you integrity, history, efficient equality, and distributed collaboration for free. The same architecture applied to code relationships gives you something new: versioned intelligence that you can diff, cache, prove, and trust over time.
I needed AI agents to reliably rename symbols, find references, and check diagnostics without silent failures. The existing MCP-LSP tools were stateless, feature-poor, and untested. So I built agent-lsp: a persistent runtime with 50 tools, 20 provider-agnostic skills, speculative execution, and an audit trail for every AI-driven edit.
Agents accumulate autonomous behaviors over time - ‘always do X before Y’, ‘if you see Z then do W’. These instructions eat context budget, drift across invocations, and can’t be observed or tested. How to recognize when an autonomous behavior is a skill waiting to be extracted, and the layered model that makes the boundary clear.
Claude Code agents write code fast. Too fast to catch quality issues in real-time. Here’s how to build validation directly into agent workflows using hooks and team coordination - micro validation after every file write, macro validation before completion, and independent review from validator agents.
Most developers cargo-cult their SSH config from Stack Overflow. This is the setup I actually run: three GitHub identities on one machine, persistent control sockets, conditional git configs that auto-select the right key, and pinned known_hosts. No third-party tools.
Part 2: A comprehensive reference covering every glob pattern from basic wildcards to advanced features like brace expansion and extended globs. Learn the rules that apply everywhere.
Glob patterns are everywhere - .gitignore, shell wildcards, build configs - yet most developers learn them by accident through copy-paste. Here’s why glob deserves explicit teaching.
More features always lead to more sprawl. The longer it goes on, the harder it is to bring back under control. Here’s how to treat your README like a landing page - with hooks, not walls of text.
Start on Mac, continue on Linux–same Claude conversation. Plus integrated AWS/Rust/Go/Python tools, extensible hooks, multi-vault secrets, and modular architecture. A framework, not just dotfiles.
I work on OSS projects, client work, and employer projects. Each needs different Claude Code configuration. Here’s how I stopped manually editing CLAUDE.md every time I switched contexts.