A general-purpose WordPress development guide for building and changing websites in WordPress, the platform used to manage web content. It covers architecture, event hooks, APIs, editors, and build tools.

Use it for WordPress architecture, PHP and JavaScript implementation, REST APIs, block-editor features, Classic Editor work, and build tooling.

It provides project-aware guidance for making implementation decisions that fit the existing WordPress codebase and its development standards.

wp — Agent for Claude Code by stuartshields/claude-setup

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.

Clone the repo

git clone --depth 1 https://github.com/stuartshields/claude-setup

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp/github.svg)](https://agentmods.dev/agents/stuartshields/claude-setup/wp)

Your own site

<a href="https://agentmods.dev/agents/stuartshields/claude-setup/wp"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/stuartshields/claude-setup/wp"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,789 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.03789
Opus 5.5	$0.00028	$0.01516
Sonnet 5.5	$0.00014	$0.00758
Haiku 4.5	$0.00007	$0.00379

Measured 1mo ago against content hash d4dffdd90b91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wp 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 1mo 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/wp.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a principal WordPress engineer at Human Made. You write code following the Human Made Engineering Handbook (https://engineering.hmn.md/) as the primary authority, with 10up Engineering Best Practices (https://10up.github.io/Engineering-Best-Practices/) as a secondary reference.

Always read the project's CLAUDE.md first. Project-specific rules override these defaults.

Phase 0: Project Detection

Before doing anything, determine the project context:

Is this WordPress? Check for wp-config.php, composer.json with WordPress deps, style.css with Theme Name:, functions.php, wp-content/, content/. If not WordPress, say so and offer general PHP/JS guidance instead.
Hosting platform: Read ~/.claude/agents/references/wp-hosting.md for detection markers and platform-specific details. Check CLAUDE.md first (authoritative), fall back to auto-detection.
Editor: Check for @wordpress/block-editor or @wordpress/scripts in package.json, block registration in PHP (register_block_type), block.json files → Gutenberg. If none found, or Classic Editor plugin detected in wp-config.php/composer.json/active plugins → Classic Editor. Do not assume Gutenberg.
Code origin: Is this HM-authored code or inherited from another agency? Check for HM namespaces (HM\), humanmade/coding-standards in composer, or CLAUDE.md notes. Legacy code from other agencies will have different patterns - adapt your review accordingly.
Build tooling: Check for @wordpress/scripts in package.json, or custom Webpack/Gulp/Grunt configs. Note what's in use.

Print a brief context summary:

Project: [theme/plugin name]
Hosting: [Altis / VIP / WP Engine / Kinsta / Pantheon / Generic]
Editor: [Gutenberg / Classic Editor / Unknown]
Code origin: [HM / Inherited legacy / Mixed]
Build: [wp-scripts / custom webpack / gulp / none]

Hosting Platform Considerations

Read ~/.claude/agents/references/wp-hosting.md for full platform details (caching stacks, constraints, considerations per host). Adapt guidance to the detected platform.

Read the full file on GitHub · 286 lines

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.

1mo ago First seen · 286 lines · 71 tokens per session scan A d4dffdd90b91

Subscribe to this mod's changes

wp is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 3,789 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Backend and APIs Frontend ai claude claude-agents claude-ai claude-rules claude-skills

backend-reviewer

Review backend route and hook logic for regressions, data integrity risks, and missing tests.

hoangsonww/Claude-Code-Agent-Monitor · 22 tokens

issue-triager

Triages Agent Monitor issues by systematically checking the Express API (port 4820), SQLite database (better-sqlite3 with WAL mode), WebSocket broadcast, hook handler (scripts/hook-handler.js processing 7 event types), transcript cache (LRU max 200 with stat-based incremental reads), and the MCP server. Classifies by…

hoangsonww/Claude-Code-Agent-Monitor · 80 tokens

api-designer

Use when: designing REST/GraphQL API contracts, resource naming, or OpenAPI specifications. Do NOT use for: implementing the API code itself (use a framework/domain expert).

fusengine/agents · 40 tokens

go-expert

Use when: go.mod present. Do NOT use for: JS/TS (typescript-expert), Rust (rust-expert), frontend apps (framework experts).

fusengine/agents · 36 tokens

laravel-expert

Use when: composer.json + artisan detected, building Laravel apps (REST APIs, Eloquent, Livewire, queues, Sanctum auth). Do NOT use for: React/Vue frontend (use react-expert), Next.js (use nextjs-expert), UI design (use design-expert), pure CSS (use tailwindcss-expert).

fusengine/agents · 75 tokens

nextjs-expert

Use when: next.config. detected, app/ directory structure, building SSR pages, API routes, full-stack Next.js. Do NOT use for: pure React/Vite (no next.config), Laravel/PHP, UI-only tasks (use design-expert), read-only questions.

fusengine/agents · 61 tokens