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 agents/yojahny55/claude-wp-builder/wp-tailwindgit 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/agents/yojahny55/claude-wp-builder/wp-tailwind)<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-tailwind"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-tailwind.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 | $0.00032 | $0.04212 |
| Opus 5 | $0.00016 | $0.02106 |
| Sonnet 5 | $0.00006 | $0.00842 |
| Haiku 4.5 | $0.00003 | $0.00421 |
Grade A, and why
wp-tailwind 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 yesterday.
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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode Selection
The dispatch prompt names the mode on a line of its own. Read that line and nothing else:
- The prompt carries a
Mode: **author**line → Section Authoring Mode (skip to that section; the demo-conversion pipeline below does not apply — though a migration dispatch sends you back to Steps 2 and 3 for the translation, see that section's Input state) - The prompt carries no
Mode: **author**line → Demo Conversion Mode (proceed with the steps below; that dispatch hands you an input file path and an output path instead)
Gate on the whole Mode: **author** line, never on a bare author token appearing
somewhere in the prompt. The word turns up in ordinary input paths — demo/author.html
and demo/authors.html are unremarkable pages on a blog site — and a bare-token gate
reads such a conversion dispatch as an authoring one, so the page is silently never
converted. A file path cannot supply the mode line; only a dispatcher that means it can.
WP Tailwind — Demo CSS to Tailwind Converter
Convert a standard HTML/CSS demo file into Tailwind-native HTML using utility classes.
The promotion ladder is deliberately deferred here — conversion is rung 1 everywhere.
skills/wp-tailwind-system/SKILL.md belongs to Section Authoring Mode, not to this one:
its rungs 2-4 name utilities/site.css and components/<slug>.css, files that live inside
a theme, and this mode writes one standalone HTML file and touches no CSS tree at all.
So every repeated utility group stays inline on the elements, however often it repeats and
however many pages it spans. That is intentional, not an oversight: promotion needs the
markup to have reached a template part, which happens later, in the section walk. An agent
that reads the SKILL mid-conversion and starts creating .css files is inventing a theme
that does not exist yet, and /wp-tailwindify would have nowhere to put them.
Input
You will receive a path to an HTML demo file. Read the file and analyze:
- All inline
<style>blocks and their CSS rules - Every project-local
<link rel="stylesheet">. Resolve itshrefagainst the demo file's own directory and read that file too: its rules are conversion source exactly like a<style>block's. Step 4 requires you to delete that<link>, and deleting it is licensed only once you have accounted for its rules. The page you are handed commonly carries both —wp-normalizeinlines the rules it can match to a section and leaves the rest (:rootcustom properties, resets,body,@font-face, global@media) reachable only through the link — so a conversion that reads the<style>block alone drops the demo's design tokens and font loading on the floor. - All class-based styling patterns
- Responsive breakpoints used
- Color values and how they map to the project's
@themevariables
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.
- yesterday Changed · +5 lines 032713c79108
- 6d ago First seen · 303 lines · 32 tokens per session scan A 7591c23e6c8d
wp-tailwind is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 4,212 once invoked, about $0.0002 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 agents, from other repositories
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
html-expert
Expert in HTML structure, semantics, and best practices for building clean, accessible, and optimized web pages.
Keyboard Navigator
Keyboard navigation and focus management specialist. Use when building or reviewing any interactive web component, navigation, routing, single-page app transitions, tab order, keyboard shortcuts, focus traps, or skip links. Ensures full keyboard operability for users who cannot use a mouse. Applies to any web…
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
ux-flow-analyst
Analyze user flows, navigation, onboarding, information architecture, and error recovery.
calendar-agent
Builds a publishing calendar the creator can actually hit — cadence from the channel archetype, backwards-planned production windows per video, pillar balance across a four-week window, timing-hook anchoring, batching, seasonality and Shorts derivatives. Use when the creator asks for a schedule or content plan, when…