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 skills add dr-robert-li/cowork-wordpress-expert --skill build-visualgit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote 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/skills/dr-robert-li/cowork-wordpress-expert/build-visual)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-visual"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-visual/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/skills/dr-robert-li/cowork-wordpress-expert/build-visual"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-visual.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 | $0.00048 | $0.13337 |
| Opus 5 | $0.00024 | $0.06668 |
| Sonnet 5 | $0.00010 | $0.02667 |
| Haiku 4.5 | $0.00005 | $0.01334 |
Grade A, and why
build-visual scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 1,261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Visual Skill
Translates a visual design input (HTML/CSS export directory or screenshot image) into a complete, installable WordPress FSE block theme with a custom-{slug} naming prefix. This skill is the core engine for Phase 14's visual input mode — it reads a design, extracts tokens, scaffolds the FSE theme directory, downloads and bundles Google Fonts, activates the theme via WP-CLI, and generates a visual-specific SETUP.md.
Critical sequencing: This skill runs AFTER build-mcp Section 2 (MCP adapter activated, database re-exported) and BEFORE build-git Section 3 (dynamic .gitignore update adds custom-{slug} to tracked paths).
This skill expects the following variables to already be set by the calling command:
BUILD_DIR— absolute path to the build directory (set by build-scaffold Section 2)WP— the WP-CLI command prefix (e.g.,wp --path=$BUILD_DIRor the Docker equivalent, set by build-scaffold Section 4)VISUAL_PATH— path to the design input (directory or image file, set by COMMAND.md Section 1)SLUG— build slug (set by COMMAND.md Section 1)SITE_TITLE— site title (set by COMMAND.md Section 1)PLUGIN_DIR— absolute path to the CoWork plugin directory
Section 1: Input Detection and Design Parsing
Detect whether VISUAL_PATH is a directory (HTML/CSS export) or an image file (screenshot), then parse the design to prepare for token extraction.
1a: Input Type Detection
# VISUAL_PATH set by COMMAND.md Section 1 argument parsing
THEME_SLUG="custom-${SLUG}"
THEME_DIR="$BUILD_DIR/wp-content/themes/${THEME_SLUG}"
if [ -d "$VISUAL_PATH" ]; then
# Check if directory actually contains HTML/CSS files
HTML_COUNT=$(find "$VISUAL_PATH" -maxdepth 3 -name "*.html" -o -name "*.css" 2>/dev/null | wc -l | tr -d ' ')
if [ "$HTML_COUNT" -gt 0 ]; then
VISUAL_MODE="html-css"
echo "[Build] Visual input: HTML/CSS export directory ($VISUAL_PATH) — $HTML_COUNT files found"
else
# Directory contains no HTML/CSS — check for images (Canva/Miro image-only exports)
IMG_FILE=$(find "$VISUAL_PATH" -maxdepth 3 \( -name "*.png" -o -name "*.jpg" -o -name "*.jpeg" -o -name "*.webp" \) 2>/dev/null | sort -k5 -rn 2>/dev/null | head -1)
if [ -n "$IMG_FILE" ]; then
VISUAL_MODE="screenshot"
VISUAL_PATH="$IMG_FILE"
echo "[Build] Visual input: directory contained only images — switching to screenshot mode ($VISUAL_PATH)"
else
echo ""
echo "ERROR: --visual directory contains no HTML, CSS, or image files: $VISUAL_PATH"
echo ""
exit 1
fi
fi
elif [ -f "$VISUAL_PATH" ]; then
# Check file extension for supported image formats
EXT=$(echo "${VISUAL_PATH##*.}" | tr '[:upper:]' '[:lower:]')
case "$EXT" in
png|jpg|jpeg|gif|webp|bmp|tiff)
VISUAL_MODE="screenshot"
echo "[Build] Visual input: Screenshot image ($VISUAL_PATH)"
;;
*)
echo ""
echo "ERROR: --visual path must be a directory (HTML/CSS export) or an image file (png, jpg, jpeg, gif, webp, bmp, tiff)"
echo ""
exit 1
;;
esac
else
echo ""
echo "ERROR: --visual path does not exist: $VISUAL_PATH"
echo ""
exit 1
fi
echo "[Build] VISUAL_MODE=$VISUAL_MODE, THEME_SLUG=$THEME_SLUG"
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.
- 9d ago First seen · 1,261 lines · 48 tokens per session scan E bc3b594abc59
build-visual is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (28 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 13,337 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.