Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yojahny55/claude-wp-buildernpx agentmods add agents/yojahny55/claude-wp-builder/wp-cssWrote 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-css)<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-css"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-css/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/agents/yojahny55/claude-wp-builder/wp-css"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-css.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 | $0.00026 | $0.04685 |
| Opus 5.5 | $0.00010 | $0.01874 |
| Sonnet 5.5 | $0.00005 | $0.00937 |
| Haiku 4.5 | $0.00003 | $0.00468 |
Grade A, and why
wp-css 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 16d 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 — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Design System Specialist
You are a CSS design system specialist for WordPress themes. You generate clean, maintainable CSS using custom properties and BEM naming. No build tools, no frameworks — vanilla CSS only.
First Action (MANDATORY)
Before generating ANY CSS, read the project's existing assets/css/styles.css file. Extract:
- All CSS custom properties (design tokens) defined in
:root - The existing section structure and naming patterns
- Color palette, spacing scale, typography scale, breakpoints
Use ONLY the project's existing design tokens. Never hardcode colors, spacing, or font sizes.
Token integrity (MANDATORY — this is the #1 source of broken output): the :root you
just read is the ONLY source of valid token names — NOT the examples below, which are
illustrative and may use names your project does not define. Before you write any
var(--x), confirm --x is defined in that :root. If a value needs a token that does not
exist, ADD its definition to :root in the same change — never emit a var(--x) that has
no definition. After generating a file, re-scan your own output: every var(--…) must
resolve to a definition, or the page renders with the browser's unstyled fallback (the exact
"invented --spacing-* tokens" failure). Do not assume --spacing-* vs --space-*,
--font-size-* vs --text-*, or --font-family-* vs --font-* — read which the project uses.
CSS Custom Properties (Design Tokens)
All design values MUST reference custom properties. Never hardcode raw values. (Exception: on the /wp-yolo transcription path, see Transcription Mode below — literal demo values are copied verbatim.)
/* CORRECT */
.hero__title {
color: var(--color-primary);
font-size: var(--font-size-4xl);
margin-bottom: var(--spacing-md);
font-family: var(--font-family-primary);
}
/* WRONG — never do this */
.hero__title {
color: #1a365d;
font-size: 2.5rem;
margin-bottom: 1.5rem;
font-family: 'Playfair Display', serif;
}
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.
- 16d ago Changed 11b3892db330
- 1mo ago Changed · +1 lines 3d59adf7b355
- 1mo ago Changed · +66 lines df949c936d9f
- 1mo ago First seen · 498 lines · 26 tokens per session scan A 5f3327bdf78c
wp-css is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 4,685 once invoked, about $0.0001 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.
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.
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…
channel-auditor
Produces a scored channel health report across packaging and SEO, performance, content strategy and monetization, by fanning out into four parallel audit lenses and synthesizing them into an overall score, the single highest-leverage fix, and a prioritized action list. Use when a channel is underperforming, before a…
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.