Why I Built a Claude Code Playbook for WordPress
I keep my Claude Code rules for WordPress in one public GitHub repo, and every machine I use pulls it at the start of the next session. I built it because my rules kept drifting between projects and costing tokens I didn't need to spend. This post covers why I made the AI Dev Standards & Playbook , what's in it, and how it changed the way I work with Claude Code. TL;DR One repo holds my coding…
Matt Hummel created a Claude Code playbook for WordPress to address the issue of coding rules drifting between projects and costing extra tokens. His playbook is stored in a single public GitHub repo, which gets pulled at the start of each new Claude Code session. The repo contains coding standards, SEO rules, writing voice, reference docs, slash commands, a reviewer agent, and a deploy kit.
One core rule in the 0.9 KB playbook ensures that Claude Code loads only the essential information for each session, rather than loading all 60 KB of rules every time. This way, Claude Code only loads the necessary context when working on specific files or using certain skills. For example, WordPress rules apply to PHP files, while SEO rules apply to Blade templates.
Skills are folders within the repo with a SKILL.md file that Claude Code loads when needed, such as when drafting a blog post about a specific topic or adding an ACF field. Commands are only loaded when typed by the user, allowing for repeatable workflows. Project specific facts, commands, and hard no's are stored in each project's own CLAUDE.md file, ensuring that client-specific information is kept separate from the general playbook.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
