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 agents/a8cteam51/claude-code-plugins/blueprint-analyzergit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWhat 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 | $0.00181 | $0.01252 |
| Opus 5 | $0.00090 | $0.00626 |
| Sonnet 5 | $0.00036 | $0.00250 |
| Haiku 4.5 | $0.00018 | $0.00125 |
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.
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
- 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. - Walk the HTML depth-first. Break it into top-level sections (hero, feature grid, testimonial row, footer, etc.).
- 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).
- Detect the section's design tokens (colours, font families + sizes, spacing, layout widths, radii, shadows). Report exact values; later reconciliation unifies them across files.
- 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.htmltemplate — classify itpage-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). - List linked assets and their roles (content image vs decorative/background, fonts, scripts).
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.
- 2d ago First seen · 80 lines · 181 tokens per session scan A f6ebbdcf72e2
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.