The Warning My Agent Gave That I Never Saw
7 min read · claude-code
My agent warned me and I scrolled past it. The fix: a 250-line Claude Code mod that keeps the agent's open questions above the prompt.
Claude Code hooks guide: all 33 lifecycle events, exit code 2 blocking, PreToolUse examples, the stop_hook_active trap, and the patterns worth shipping.
Claude Code SKILL.md frontmatter reference: all 20 fields, the context: fork and agent pair, body templating, and the bugs you'll hit in practice.
ForgeCode vs Claude Code: ForgeCode scores 81.8% on TermBench 2.0 to Claude Code's 58%, but trails on ecosystem. Which CLI agent to pick in 2026.
Claude Code source leak, unpacked: what 512k lines reveal about the agent loop, 40+ built-in tools, 44 hidden feature flags, and Anthropic's roadmap.
AI agent protocols beyond MCP: a tour of A2A, ANP, Agora, Agent Protocol, and other agent communication standards, and what each one is for.
Rust smart pointers cheat sheet: Box, Rc, Arc, RefCell, Cell, Cow, Mutex, and RwLock, with examples and a table of when to use each one.
Database replication methods compared: statement-based, write-ahead log (WAL), logical log, and trigger-based replication, with the pros and cons of each.
Kotter's 8-step change model in practice: an engineering leader's take on each step, from creating urgency to anchoring change in team culture.