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.
npx agentmods add skills/zulut30/wordpress-skills/wordpress-plugin-devnpx skills add Zulut30/Wordpress-skills --skill wordpress-plugin-devgit clone --depth 1 https://github.com/Zulut30/Wordpress-skillsWhat 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.
| Model | Per session | Once 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 |
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.
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 pluginfeature implementationcode reviewsecurity auditGutenberg/block workREST/admin/settings workperformance optimizationperformance auditfrontend asset optimizationdatabase/query optimizationblock render optimizationREST/admin performance reviewadmin UI designsettings page UXplugin dashboard designfrontend output designGutenberg block UI designonboarding/setup wizardUX/accessibility reviewvisual polishdesign system alignmentClassic Editor compatibilitySEO plugin integrationcache plugin compatibilityperformance plugin compatibilitytheme compatibilitypage builder compatibilitytop-100 plugin compatibilitytop-100 theme compatibilitycompatibility auditintegration adapter implementationcompatibility matrix creationtesting/CIrelease 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.jsonand server-side block registration for blocks. - Prefer
@wordpress/scriptsfor 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_rowswhen totals are not needed, andfields => '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.jsonand 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.
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.
- assets/examples/admin-settings-before-after.md 1.5 KB
- assets/examples/admin-settings-page.md 404 B
- assets/examples/cache-invalidation-patterns.md 902 B
- assets/examples/cache-plugin-compatibility.md 867 B
- assets/examples/classic-editor-fallback.md 996 B
- assets/examples/compatibility-audit-report.md 2.1 KB
- assets/examples/compatibility-matrix-example.md 1.7 KB
- assets/examples/design-audit-report.md 1.6 KB
- assets/examples/dynamic-block.md 3.7 KB
- assets/examples/empty-loading-error-states.md 894 B
- assets/examples/frontend-output-design.md 941 B
- assets/examples/gutenberg-block-ui-before-after.md 1.4 KB
- assets/examples/modern-plugin-tree.md 497 B
- assets/examples/onboarding-flow.md 951 B
- assets/examples/optimized-dynamic-block.md 920 B
- assets/examples/optimized-rest-endpoint.md 1.4 KB
- assets/examples/page-builder-compatibility.md 782 B
- assets/examples/performance-audit-report.md 1.8 KB
- assets/examples/plugin-dashboard-layout.md 1.1 KB
- assets/examples/scoped-asset-loading.md 748 B
- assets/examples/secure-rest-route.md 611 B
- assets/examples/seo-plugin-compatibility.md 991 B
- assets/examples/theme-compatibility-before-after.md 756 B
- assets/templates/accessible-form-field.stub 1.3 KB
- assets/templates/admin-card-grid.stub 1.2 KB
- assets/templates/admin-notice.stub 764 B
- assets/templates/admin-page-layout.stub 1.4 KB
- assets/templates/aioseo-integration.stub 801 B
- assets/templates/astra-compatibility.stub 442 B
- assets/templates/autoptimize-compatibility.stub 646 B
- assets/templates/block-editor-classic-fallback.stub 1.1 KB
- assets/templates/block-inspector-controls.stub 1.3 KB
- assets/templates/block-json.stub 589 B
- assets/templates/block-placeholder.stub 1.1 KB
- assets/templates/cache-integration-interface.stub 371 B
- assets/templates/classic-editor-metabox-fallback.stub 1.6 KB
- assets/templates/compatibility-matrix.stub 911 B
- assets/templates/composer-json.stub 1.2 KB
- assets/templates/cron-batch-job.stub 1.2 KB
- assets/templates/css-scoped-admin-ui.stub 726 B
- assets/templates/divi-adapter.stub 473 B
- assets/templates/dynamic-block-fragment-cache.stub 783 B
- assets/templates/elementor-adapter.stub 602 B
- assets/templates/empty-state.stub 916 B
- assets/templates/frontend-card-output.stub 821 B
- assets/templates/frontend-scoped-css.stub 636 B
- assets/templates/generatepress-compatibility.stub 462 B
- assets/templates/generic-cache-compatibility.stub 593 B
- assets/templates/github-actions-ci.yml.stub 3.7 KB
- assets/templates/integration-interface.stub 500 B
- assets/templates/integration-registry.stub 921 B
- assets/templates/kadence-compatibility.stub 456 B
- assets/templates/litespeed-cache-adapter.stub 940 B
- assets/templates/object-cache-helper.stub 1.1 KB
- assets/templates/onboarding-step.stub 1.6 KB
- assets/templates/optimized-query.stub 748 B
- assets/templates/package-json.stub 923 B
- assets/templates/performant-rest-controller.stub 2.0 KB
- assets/templates/plugin-php-main.stub 2.1 KB
- assets/templates/rankmath-integration.stub 837 B
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.
- 2d ago First seen · 296 lines · 105 tokens per session scan A 5c2caa30b4fc
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.
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.
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.
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.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
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).
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.