Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yojahny55/claude-wp-builder/plugin install claude-wp-builderWrote 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.
[](https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-cpt)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-cpt"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-cpt/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.
<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-cpt"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-cpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.03253 |
| Opus 5 | $0.00013 | $0.01626 |
| Sonnet 5 | $0.00005 | $0.00651 |
| Haiku 4.5 | $0.00003 | $0.00325 |
Grade A, and why
wp-cpt 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 5d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP CPT — Custom Post Type Builder
Register a custom post type and generate everything it needs: registration, ACF fields bound to the type, archive + single templates, an optional home/teaser query-section, and a seed helper.
Step 1: Parse Arguments
- First word = CPT name, singular lowercase (e.g.,
team,service,project). Required. --no-teaser= skip the teaser query-section.--from-demo <section-name>= read field/seed hints from that section indemo/index.html.
If no name: print usage error and exit.
Step 2: Read Project Context
Read .claude/CLAUDE.md for function prefix, theme slug, languages, theme directory. If missing, tell the user to run /wp-init first and exit.
CSS agent routing
Read Template: from .claude/CLAUDE.md. When Template: is tailwind, dispatch
wp-tailwind; when it is basic, dispatch wp-css.
basic→ dispatchwp-cssexactly as described below.tailwind→ dispatchwp-tailwindin author mode instead, passing the CPT name (which selectscomponents/<name>.css) and the block name. The agent readsskills/wp-tailwind-system/SKILL.mdfor the decision ladder. It writes utility classes into the markup and only adds@applyrules where the ladder demands them. It must never writeassets/css/styles.css.
Dispatch exactly one of the two, never both.
Every tailwind dispatch opens its quoted prompt with this line, verbatim:
Mode: author
The quoted prompt it opens is the one under "The tailwind prompt body" below — not
the quoted prompt at the dispatch site, which is the basic branch's and names
assets/css/styles.css, the one file the tailwind path must never write.
agents/wp-tailwind.md gates Section Authoring Mode on that line and on nothing else, so
the line is not decoration: omit it and the dispatched agent falls into Demo Conversion
Mode, reads the prompt as a demo-file conversion and writes a .tmp nobody asked for. A
bare author anywhere else in the prompt — in prose, or inside an input path like
demo/author.html — selects nothing, precisely so that an ordinary demo page named after
the word cannot flip the mode by accident.
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.
- 5d ago Changed · +13 lines 628c98b59da2
- 8d ago First seen · 211 lines · 25 tokens per session scan A 4a2c3bfb824c
wp-cpt is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 3,253 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
auth-implementation
Use when a project needs real working login and signup rather than advice. Wiring up Clerk or Supabase Auth, protecting routes, handling sessions. Writes actual code, not guidance.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
better-auth:setup
Interactive setup wizard for better-auth authentication. Guides through database, framework, OAuth providers, and plugin configuration.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
symfony-cache
Implement caching strategies using Symfony Cache component.
mcp
MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting.