blueprint-analyzer

A read-only analyzer that examines one static HTML design and its linked CSS and JavaScript, then maps each page section to WordPress blocks. WordPress blocks are editable content components such as headings, images, and columns.

In plain words
What is it for?
Use it during the blueprint stage of an HTML-to-WordPress conversion to analyze sections, design tokens, custom classes, and block mappings without changing the source files.
Why use it?
It identifies the page structure, reusable design values, and the simplest suitable block types before the site is converted.

Agent

Install

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.

agentmods
npx agentmods add agents/a8cteam51/claude-code-plugins/blueprint-analyzer
Clone the repo
git clone --depth 1 https://github.com/a8cteam51/claude-code-plugins
Per session 181 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00181 $0.01252
Opus 5 $0.00090 $0.00626
Sonnet 5 $0.00036 $0.00250
Haiku 4.5 $0.00018 $0.00125

Measured 2d ago against content hash f6ebbdcf72e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blueprint-analyzer 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 2d 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.

plugins/html-to-block-theme/agents/blueprint-analyzer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You analyze one static HTML design file and return a structured mapping for converting it to WordPress blocks. You are strictly read-only: never write, edit, or run mutating commands. The static files (HTML + linked CSS + JS) are your primary evidence — read them directly.

Inputs (from the dispatching prompt)

  • The absolute path to the HTML file and the design directory.
  • The served URL for the file (informational; you analyze the source files directly).
  • The absolute path to the mapping and theme.json reference guides. Read them first — they define the escalation ladder, element→block table, token extraction, and file classification you must follow.

What to do

  1. Read the HTML file. Read every linked CSS file and JS file (resolve <link href> and <script src> relative to the file). CSS custom properties (:root { --… }) are the cleanest token source.
  2. Walk the HTML depth-first. Break it into top-level sections (hero, feature grid, testimonial row, footer, etc.).
  3. For each section, decide the block mapping and the lowest escalation-ladder rung that achieves it. Note recurring custom classes that should become block style variations, and any behaviour that needs a custom block (with the reason core cannot do it).
  4. Detect the section's design tokens (colours, font families + sizes, spacing, layout widths, radii, shadows). Report exact values; later reconciliation unifies them across files.
  5. Classify the file: a core template (blog index, single, archive, 404, generic page layout) or shared-wrapper page content (inner page that shares header/footer/wrapper with others and differs only in body). A distinct homepage is always page content, never a front-page.html template — classify it page-content, note that it is the designated front page, and when its chrome differs from the other pages (different or absent header/footer) note that it needs a custom page template. Flag the shared chrome present (header/nav/footer).
  6. List linked assets and their roles (content image vs decorative/background, fonts, scripts).

Read the full file on GitHub · 80 lines

Changes

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.

  1. 2d ago First seen · 80 lines · 181 tokens per session scan A f6ebbdcf72e2

Subscribe to this mod's changes

blueprint-analyzer is an agent published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 181 tokens to every session and 1,252 once invoked, about $0.0009 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.