agentleFS
ehsanenalooehsanenaloo/wordpress-devkit/docs/llms.txt

wordpress-devkit

llms.txt0 starsChanged 34 days agoMITView on GitHub

WordPress engineering workflows for Claude and Codex. An instruction pack, not a WordPress runtime.

The file

Files
llms.txt
# WordPress DevKit

> WordPress engineering workflows for Claude and Codex. An instruction pack, not a WordPress runtime.

## User guides

- [Your first review](guides/quick-start.html): Go from a new project to a bounded review with evidence.
- [Install for your agent](guides/installation.html): Choose Claude plugin loading or complete manual skills.
- [Discover the environment](guides/doctor-and-reports.html): Run Doctor, read its report and compare evidence over time.
- [Turn a finding into a fix](guides/review-to-fix.html): Confirm the failing path, scope the change and verify the result.
- [Prepare a WordPress release](guides/release-checklist.html): Sequence migration, testing, packaging and rollback review.
- [Questions & troubleshooting](guides/faq.html): Understand activation, updates, evidence and common installation errors.

## Specialist guides

- [Site audit & onboarding](guides/site-audit-and-onboarding.html): Map an unfamiliar WordPress project before choosing a specialist review.
- [Security review](guides/security-review.html): Trace authorization and untrusted data through reachable WordPress code.
- [Performance review](guides/performance-review.html): Investigate queries, hooks and caching with measured workload context.
- [Plugin development](guides/plugin-development.html): Review plugin architecture, lifecycle and WordPress integration boundaries.
- [Theme development](guides/theme-development.html): Work with classic, hybrid, child and block themes without losing saved customizations.
- [Gutenberg blocks](guides/block-development.html): Review metadata, editor behavior and existing saved-content compatibility.
- [WooCommerce extensions](guides/woocommerce-dev.html): Review orders, checkout, payments and jobs with explicit store context.
- [REST API development](guides/rest-api-development.html): Review route permissions, request validation and response contracts.
- [Headless & WPGraphQL](guides/headless-and-wpgraphql.html): Review schemas, preview flows and content invalidation across frontend boundaries.
- [ACF & content modeling](guides/acf-and-content-modeling.html): Choose stable content structures and inspect field-group drift.
- [Admin interfaces](guides/admin-ui-development.html): Review settings screens, capabilities and focused asset loading.
- [Interface design](guides/ui-design.html): Design WordPress layouts with responsive, visual and interaction evidence.
- [Accessibility implementation](guides/accessibility-review.html): Inspect keyboard, focus, semantics and interactive behavior.
- [WCAG evidence review](guides/wcag-review.html): Map applicable WCAG 2.1/2.2 A and AA criteria to representative evidence.
- [Migration & upgrades](guides/migration-upgrade-review.html): Review versioned schema/data changes and interrupted execution.
- [WP-CLI & operations](guides/wpcli-and-ops.html): Plan targeted maintenance with dry-run, checkpoints and failure reporting.
- [PHPStan adoption](guides/phpstan-review.html): Inspect static-analysis configuration, WordPress stubs and baseline discipline.
- [WordPress Playground](guides/playground-development.html): Prepare reproducible demos and inspect Blueprint trust boundaries.
- [Testing strategy](guides/test-strategy.html): Choose useful unit, integration and browser coverage for real risks.
- [CI/CD & release engineering](guides/ci-cd-and-release-engineering.html): Inspect build artifacts, deployment gates and recovery plans.

## Commands

- [Claude command catalog](commands.html): All 41 commands; these are not Codex slash commands.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.