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-themegit 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-theme)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-theme"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-theme/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-theme"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-theme.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 | $0.00047 | $0.03313 |
| Opus 5 | $0.00023 | $0.01656 |
| Sonnet 5 | $0.00009 | $0.00663 |
| Haiku 4.5 | $0.00005 | $0.00331 |
Grade A, and why
build-theme scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 10 \ How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Theme Skill
Selects, installs, and activates a Full Site Editing (FSE) block theme from WP.org based on the user's natural language site description. This skill queries the WP.org Themes API v1.2 for FSE themes, evaluates results against the NL prompt using Claude's in-context judgment, and installs the best match. A curated fallback list provides guaranteed theme selection when the API returns poor results or is unavailable.
Critical sequencing: This skill runs AFTER build-mcp Section 2 (MCP adapter activated, DB re-exported) and BEFORE build-content (content seeding requires the theme to be active for menu location discovery).
This skill expects the following variables to already be set by the calling command:
BUILD_DIR— absolute path to the build directory (set by build-scaffold Section 2)WP— the WP-CLI command prefix (e.g.,wp --path=$BUILD_DIRor the Docker equivalent, set by build-scaffold Section 4)NL_PROMPT— the user's natural language site description stringSITE_TITLE— site title derived from the NL prompt (set by the calling command before this skill)
Section 1: WP.org Themes API Query
Query the WP.org Themes API v1.2 for the FSE block theme pool. Use the full-site-editing tag to filter — this is the canonical public signal for FSE/block themes. Do NOT combine search and tag parameters: the API ignores tags when search is present. Claude evaluates theme relevance in-context after fetching the pool.
echo "[Build] Querying WP.org Themes API for FSE theme pool..."
# CRITICAL anti-pattern: Do NOT use ?action=query_themes&request[search]=...&request[tag][]=full-site-editing
# The API ignores tag[] when search is present. Use tag-only query; Claude evaluates relevance in-context.
FSE_THEMES_FILE="/tmp/fse_themes_$$.json"
curl -s --max-time 10 \
"https://api.wordpress.org/themes/info/1.2/?action=query_themes&request[tag][]=full-site-editing&request[browse]=popular&request[per_page]=50&request[fields][active_installs]=true&request[fields][rating]=true&request[fields][description]=true&request[fields][tags]=true" \
-o "$FSE_THEMES_FILE"
CURL_EXIT=$?
# Validate response — check exit code, non-empty file, and JSON structure
API_AVAILABLE=false
if [ $CURL_EXIT -eq 0 ] && [ -s "$FSE_THEMES_FILE" ]; then
# Count themes in response — need at least 3 for Claude to evaluate properly
THEME_COUNT=$(python3 -c "import json,sys; d=json.load(open(sys.argv[1])); print(len(d.get('themes', [])))" "$FSE_THEMES_FILE" 2>/dev/null || echo "0")
if [ "$THEME_COUNT" -ge 3 ]; then
API_AVAILABLE=true
echo "[Build] WP.org API returned $THEME_COUNT FSE themes for evaluation."
else
echo "[Build] WP.org API returned fewer than 3 themes ($THEME_COUNT). Falling back to curated list."
fi
else
echo "[Build] WP.org API unavailable — using curated theme list"
fi
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 · 259 lines · 47 tokens per session scan A e711620d724a
build-theme is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (28 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 3,313 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-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.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…