9 min read
Add a release gate to Claude Code: stop shipping half-finished AI code
Build a Claude Code release gate: a shipper subagent that runs your real tests, typecheck, lint and build, then returns a SHIP or BLOCK verdict.
Blog
Notes on Claude Code and Codex.
Practical guides to Claude Code subagents, skills and slash commands, Codex CLI, and shipping AI-written code safely.
8 min read
Best free Claude Code agent collections (and what to watch for)
A Claude Code agents collection can save you hours. Here are the best free ones from wshobson and VoltAgent, plus pitfalls to check first.
9 min read
Claude Code skills vs subagents vs slash commands: when to use which
Claude Code skills vs subagents vs slash commands, compared side by side: what each one is, where it lives, and a checklist for picking the right one.
9 min read
Claude Code subagents: the complete guide (2026)
How Claude Code subagents work: the .claude/agents file format, scope, delegation, tool limits, model choice, and patterns that hold up in real projects.
9 min read
How to write a Claude Code slash command (with $ARGUMENTS)
Write a custom Claude Code slash command in .claude/commands: frontmatter, $ARGUMENTS and positional args, bash context, and four real examples.
9 min read
Using agents and skills in OpenAI Codex CLI (AGENTS.md, skills, prompts)
How Codex CLI agents work in practice: AGENTS.md for project rules, skills for roles and workflows, custom prompts for commands, with examples.