wordpress-plugin-dev

A set of working rules for developing WordPress plugins, including admin pages, APIs, editor blocks, tests, security, and performance. WordPress plugins are add-ons that extend a WordPress site.

In plain words
What is it for?
Use it to build or review plugins, create Gutenberg blocks, add settings or REST endpoints, audit security and performance, and check compatibility with themes and other plugins.
Why use it?
It helps keep plugin changes compatible with WordPress, secure, maintainable, accessible, and ready to release.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/zulut30/wordpress-skills/wordpress-plugin-dev
Any agent
npx skills add Zulut30/Wordpress-skills --skill wordpress-plugin-dev
Clone the repo
git clone --depth 1 https://github.com/Zulut30/Wordpress-skills

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.03782
Opus 5 $0.00053 $0.01891
Sonnet 5 $0.00021 $0.00756
Haiku 4.5 $0.00011 $0.00378

Measured 2d ago against content hash 5c2caa30b4fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wordpress-plugin-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/wordpress-plugin-dev/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WordPress Plugin Dev

Act as a senior WordPress plugin engineer. Build in the style of the target codebase, prefer official WordPress APIs, keep changes scoped, and make security, maintainability, accessibility, and release readiness part of the default workflow.

Start By Classifying The Task

Before planning or editing, identify the primary task type:

  • new plugin
  • feature implementation
  • code review
  • security audit
  • Gutenberg/block work
  • REST/admin/settings work
  • performance optimization
  • performance audit
  • frontend asset optimization
  • database/query optimization
  • block render optimization
  • REST/admin performance review
  • admin UI design
  • settings page UX
  • plugin dashboard design
  • frontend output design
  • Gutenberg block UI design
  • onboarding/setup wizard
  • UX/accessibility review
  • visual polish
  • design system alignment
  • Classic Editor compatibility
  • SEO plugin integration
  • cache plugin compatibility
  • performance plugin compatibility
  • theme compatibility
  • page builder compatibility
  • top-100 plugin compatibility
  • top-100 theme compatibility
  • compatibility audit
  • integration adapter implementation
  • compatibility matrix creation
  • testing/CI
  • release to WordPress.org

Then inspect the plugin structure and load only the references needed for that task. For review tasks, use the advanced workflow in references/review-checklists.md that matches the requested review type before writing findings.

Mandatory Rules

  • Do not write unsafe PHP. Treat request data, options, meta, block attributes, REST payloads, shortcode attributes, and external responses as untrusted.
  • Check both capability and nonce for browser/admin actions that change data. Use capabilities for authorization and nonces for intent.
  • Sanitize on input, validate before use, and escape on output for the exact context.
  • Give every REST route a real permission_callback; use explicit public access only when the route truly exposes public data.
  • Prefer block.json and server-side block registration for blocks.
  • Prefer @wordpress/scripts for JavaScript builds unless the existing project has a clear reason to use custom webpack, Vite, or another pipeline.
  • Use WordPress i18n functions for new public strings in PHP and JavaScript.
  • For public release, check readme.txt, plugin headers, licenses, assets, build artifacts, and Plugin Check output.
  • Do not optimize by removing security checks, validation, escaping, capability gates, or nonces.
  • Measure or identify hot paths before optimizing; avoid expensive work on every request.
  • Scope assets, hooks, queries, REST responses, admin screens, and block rendering.
  • Prefer bounded queries, pagination, no_found_rows when totals are not needed, and fields => 'ids' when only IDs are required.
  • Cache expensive safe operations with explicit TTL and invalidation. Do not cache private/user-specific data globally.
  • Do not store large rarely used data in autoloaded options.
  • Do not make remote HTTP calls during frontend render without caching, timeout, and fallback.
  • Do not call flush_rewrite_rules() on normal requests.
  • Use block.json and conditional block assets for Gutenberg where suitable.
  • Design must fit WordPress unless a custom branded experience is explicitly justified.
  • Prefer WordPress-native UI patterns and components for admin/editor UI.
  • Never improve visuals by reducing accessibility, security, performance, or i18n quality.
  • Every generated UI should consider empty, loading, success, error, and edge states.
  • Frontend output should inherit theme styles where possible and scope plugin CSS.
  • Do not use placeholders as labels, do not rely on color alone, and give destructive actions clear labels plus confirmation.
  • Admin assets must be scoped to relevant screens, and generated UI text must be translation-ready.
  • If using experimental WordPress UI packages, verify current docs first.
  • Prefer WordPress core APIs before third-party plugin/theme-specific APIs.
  • Use feature detection before integration code; never fatal when an optional plugin, theme, or builder is missing.
  • Do not output duplicate SEO meta, schema, canonical, robots, Open Graph, or Twitter tags.
  • Do not cache user-specific/private data in public page cache, and do not purge all cache on every request.
  • Do not disable cache, SEO, or minification plugins as the first solution.
  • Do not load Elementor, Divi, or theme-specific adapters unless the dependency is detected.
  • Do not globally override theme CSS.
  • Classic Editor and Block Editor compatibility must use separate scoped assets/flows where needed.
  • Verify current third-party docs before release-sensitive integration work.

Read the full file on GitHub · 296 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 296 lines · 105 tokens per session scan A 5c2caa30b4fc

Subscribe to this mod's changes

wordpress-plugin-dev is a skill published in the GitHub repository Zulut30/Wordpress-skills (33 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 3,782 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

auth-web-cloudbase

CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

TencentCloudBase/CloudBase-AI-Toolkit · 38 tokens

fix-codesign-error

Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.

robinebers/openusage · 42 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

loop-engineering

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

huytieu/COG-second-brain · 63 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens