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 skills/a8cteam51/claude-code-plugins/html-to-block-themenpx skills add a8cteam51/claude-code-plugins --skill html-to-block-themegit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/html-to-block-theme)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/html-to-block-theme"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/html-to-block-theme.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 | $0.00120 | $0.03459 |
| Opus 5 | $0.00060 | $0.01729 |
| Sonnet 5 | $0.00024 | $0.00692 |
| Haiku 4.5 | $0.00012 | $0.00346 |
Grade A, and why
html-to-block-theme 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a WordPress block theme from a set of static HTML designs
End-to-end conversion of a directory of static Claude Design files (HTML + linked CSS + JS + assets) into a standards-driven WordPress block theme on a local Studio site. The output reproduces the designs as closely as possible using WordPress primitives — theme.json, templates, template parts, block patterns, block styles, and page content — not hand-written CSS.
Work in phases and do not skip the blueprint. Plan the whole mapping first, get it on disk, then build section by section and refine each section against the original in a real browser. The reference guides under ${CLAUDE_PLUGIN_ROOT}/skills/html-to-block-theme/references/ are the source of truth for every mapping, standards, and tooling decision — load the relevant one before acting in each phase.
Inputs
- Design directory (required) — absolute path to a folder of static
.htmlfiles plus their linked.css,.js, image, and font assets. The user provides this. - Studio site (optional but preferred) — path or registered name of the target Studio site. If the user provides a path, use it as-is. If they don't, infer it from
studio site list --format=json(match a sensible name, or ask if ambiguous). The site has a minimal block-theme scaffold the agent fully controls.
Critical environment quirks
These will silently corrupt output if missed (inherited from the Studio environment — same constraints the wpbakery-to-gutenberg skill documents):
- Use
studio wp ... --path=<site>, never barewp. Studio sites use SQLite; the Studio-managedwpwrapper handles that connection. Barewpfrom the host shell connects to nothing useful. - Studio's
wpruns in a sandbox that cannot see the host/tmp/. Any file PHP must read insidestudio wp eval-filemust live inside the site directory. This skill stages such files at<site-path>/.h2bt/and cleans them up. studio wp eval-file -(stdin heredoc) can silently no-op — exit 0, no output, database unchanged. Always pass a real file path and have the PHP echo a sentinel line the caller greps for. Trust nothing without the sentinel.- Build files serially — all of them, not just page-content writes. Concurrent
wp_update_post/wp_insert_postunder SQLite trips Yoast indexable errors and corrupts results, and every builder also mutates shared theme files (functions.php,theme.json, block CSS) and refines against the same live site — a parallel builder would screenshot another's half-applied changes. So template-only files are serial too. Onesection-builderat a time — and "no file writes for a while" is not a completion signal (builders go quiet for long stretches during browser refinement); wait for the agent's completion notification before dispatching the next.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 127 lines · 120 tokens per session scan A ed11976c96ce
html-to-block-theme is a skill published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session and 3,459 once invoked, about $0.0006 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 skills, from other repositories
Shade dropdown surface contract
DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.
Shade ShadCN install
Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.
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…
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
better-colors
Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.
design-frontend-dev
Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, onboarding, empty states…