component-consulting-v3

component-consulting-v3 is a plugin for Claude Code from laguna821/Achmage-Skills. Its manifest loads nothing; the 1 skill it bundles cost 246 tokens per session together, scanned A, original, Apache-2.0.

A page-writing and interface-component consultant that studies a loaded HTML page, works out its audience and structure, and fills sections with code from a bundled open-source component collection. It also provides checks for licensing, content density, and implementation completeness.

In plain words
What is it for?
Planning page sections, selecting frontend components, supplying their source code, and preparing results for visual rendering checks.
Why use it?
It reduces the need to choose interface pieces from memory or search for suitable code manually, while checking that the selected material meets defined constraints.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add laguna821/Achmage-Skills
agentmods
npx agentmods add plugins/laguna821/achmage-skills/component-consulting-v3
Clone the repo
git clone --depth 1 https://github.com/laguna821/Achmage-Skills

Made for: Claude Code.

Wrote 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.

agentmods badge for component-consulting-v3

README.md
[![agentmods](https://agentmods.dev/badge/plugins/laguna821/achmage-skills/component-consulting-v3.svg)](https://agentmods.dev/plugins/laguna821/achmage-skills/component-consulting-v3)
Your own site
<a href="https://agentmods.dev/plugins/laguna821/achmage-skills/component-consulting-v3"><img src="https://agentmods.dev/badge/plugins/laguna821/achmage-skills/component-consulting-v3.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 246 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

component-consulting-v3 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 5d 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.

Design-Consulting/component-consulting-v3/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "component-consulting-v3",
  "description": "Page-as-text component consultant with a real vendored corpus. Treats one loaded HTML page as one complete piece of writing: derives WHO reads it, WHAT genre it is, and HOW to compose it (Reader → Genre → Beats), then fills each beat from a 4,200+ open-source component corpus with actual code (uiverse, smoothui, magicui, tailark — MIT, commit-pinned, author-attributed) via deterministic retrieval. No live-scan sourcing, no model-memory stubs: every STUB is copied from a corpus code_path. Ships blocking gates (license, density floor, slop bans, prescription completeness) and emits a Render QA hand-off contract consumed by the render-audit skill. Supersedes component-consulting v1/v2. Design.md posture: consumes.",
  "version": "3.6.0",
  "author": {
    "name": "laguna821"
  },
  "homepage": "https://github.com/laguna821/Achmage-Skills/tree/main/Design-Consulting/component-consulting-v3",
  "license": "MIT",
  "keywords": ["skill", "component-selection", "design-consulting", "frontend", "design-tokens", "design-md", "component-corpus", "page-as-text", "claude-code"]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 246 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 5d ago First seen · 12 lines scan A 8fa7db376746

Subscribe to this mod's changes

component-consulting-v3 is a plugin published in the GitHub repository laguna821/Achmage-Skills (5 stars, last pushed 6d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.