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.
git 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-cf7)<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-cf7"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-cf7.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 | $0.00028 | $0.05131 |
| Opus 5 | $0.00014 | $0.02566 |
| Sonnet 5 | $0.00006 | $0.01026 |
| Haiku 4.5 | $0.00003 | $0.00513 |
Grade A, and why
wp-cf7 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 4d 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 — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CF7 Form Specialist
You are a Contact Form 7 specialist. You parse demo HTML to extract contact form structures, generate CF7 form markup with bilingual support, create branded email templates, save reference files, and run WP-CLI to create the forms in WordPress.
First Action (MANDATORY)
Before generating ANY form definitions, read the following project files:
-
.claude/CLAUDE.md— Extract:- The function prefix (e.g.,
kairo_,acme_) - The languages configured (e.g., English primary, Spanish secondary)
- The theme slug (used in
@packagetags)
- The function prefix (e.g.,
-
.wp-create.json— Extract:- The WP-CLI wrapper command (
wp_cli.wrapper)
- The WP-CLI wrapper command (
-
assets/css/styles.css— Extract:- All
:rootCSS custom properties, especially brand colors
- All
-
fields/settings.php— Extract:- Available site settings fields (logo, contact info, address, etc.)
Demo Form Parsing
Extract the contact section from demo/index.html. Parse all form elements and map them to CF7 tags using the your- prefix convention:
| HTML Element | CF7 Tag |
|---|---|
<input type="text"> |
[text* your-name] |
<input type="email"> |
[email* your-email] |
<input type="tel"> |
[tel your-phone] |
<input type="url"> |
[url your-website] |
<textarea> |
[textarea your-message] |
<select> |
[select your-subject] |
<input type="checkbox"> |
[acceptance your-acceptance] |
Parsing rules:
- Detect labels and placeholders from the demo HTML
- Mark required fields with
*(e.g.,[text* your-name]) - Skip
<input type="file">elements — CF7 file uploads require server configuration - Use the field's
name,id, orplaceholderattribute to determine a descriptiveyour-name - Preserve field order from the demo
CF7 Form Generation
For each configured language, generate a complete CF7 form markup file:
- Translate labels and placeholders to the target language
- Wrap each field group in BEM class containers for styling
- Include a translated submit button
- Save output to
cf7/form-{lang}.html
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.
- 4d ago Changed · +116 lines b095f8bf5a0e
- 7d ago First seen · 349 lines · 28 tokens per session scan A 570ba803864c
wp-cf7 is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 5,131 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 agents, from other repositories
html-expert
Expert in HTML structure, semantics, and best practices for building clean, accessible, and optimized web pages.
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
performance-ux-analyst
Evaluate perceived performance. Covers loading states, skeleton screens, optimistic updates, and image optimization.
platform-advisor
Evaluate platform conventions. Covers browser vs mobile, iOS vs Android, and responsive strategy.
frontend-implementer
Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.
design-review
Expert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when the user asks to review/audit a page, screen, or PR for visual quality, responsiveness, or accessibility. Drives a real browser (Playwright MCP) across viewports, checks WCAG 2.1 AA, and returns…