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 commands/yojahny55/claude-wp-builder/wp-sectiongit clone --depth 1 https://github.com/yojahny55/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-section)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-section"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-section.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.06754 |
| Opus 5 | $0.00010 | $0.03377 |
| Sonnet 5 | $0.00004 | $0.01351 |
| Haiku 4.5 | $0.00002 | $0.00675 |
Grade A, and why
wp-section 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 today.
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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Section — One-Shot Section Builder
Generate ACF field definitions, a template part, and CSS for a single section — all in one command. On basic it dispatches three agents in parallel; on tailwind, wp-tailwind runs after wp-template returns (see File ownership below).
Step 1: Parse Arguments
Parse $ARGUMENTS:
- First word = section name (required, e.g.,
hero,services,about,contact) - Remaining non-flag word = screenshot path (optional; a flag token or its value is never treated as the screenshot path)
--cf7flag = force CF7 contact form integration (optional)--hybridflag = cinematic projects only (Template: cinematic): build the section as a trailing flex layout appended to thetrailing_sectionsflexible-content field infields/trailing-sections.php, not as a standalone field group, and skip the page-template injection —front-page.php's trailing loop already renders every layout (see the Hybrid overlay below). Error and exit if the project is not cinematic.--page <slug>= read the section fromdemo/<slug>.htmlinstead ofdemo/index.html(optional, defaultindex— existing behavior unchanged when omitted)--target <template>= inject theget_template_partcall into<template>(e.g.page-about.php) instead offront-page.php(optional, defaultfront-page.php— existing behavior unchanged when omitted)--transcribeflag = activate faithful Transcription Mode (optional). When set, the dispatched agents reproduce the demo's exact declared CSS/geometry instead of re-authoring fresh design-system styles. When omitted, behavior is unchanged (the current re-authoring / design-system path).--block <name>= the unique BEM block name to scope every generated selector under (optional; used with--transcribeso parallel section builds can never collide on a selector).--css <source>= the demo source the section is transcribed from (optional; required with--transcribe). What it means depends on the project'sTemplate:, per the transcription overlay below:basic→ the section's verbatim demo CSS, and the SOURCE OF TRUTH for the transcription: an inline CSS blob or a path to a CSS file, whose declared values are copied exactly.tailwind→ the converted demo page itself (HTML, converted in place by/wp-yoloStep 2.6). Here it is a geometry reference, not a source of verbatim declarations — the overlay's instruction is "reproduce this geometry using Tailwind utilities", never "copy the declared values verbatim".
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.
- today Changed · +8 lines 8885f5d0732f
- 2d ago Changed · +50 lines 84739ffa2e04
- 5d ago First seen · 473 lines · 20 tokens per session scan A fbe7f1452757
wp-section is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 6,754 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
setup
SoDam-Design-Kit 설정 마법사 — config.json 생성 + shadcn 컴포넌트 스캔으로 component-map 초기 시드.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.