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.
/plugin marketplace add fledgeling-co/fledgeling-pluginsnpx agentmods add plugins/fledgeling-co/fledgeling-plugins/design-craftgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsGrade A, and why
design-craft 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 — 10 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "design-craft",
"version": "1.4.0",
"description": "Design or review a user-facing visual artifact \u2014 a landing page, app screen, dashboard, clickable prototype, native mobile mockup, wireframe, variation set, tweakable panel, motion piece, 3D hero, print document, generated imagery or design system \u2014 as an opinionated designer rather than a code generator. Roots every hi-fi build in existing context by default and lifts a matched system's resolved values exactly, never rounding them to a 4/8px grid and reporting the rounding as a fix. Names the category's rut and its predictable opposite before generating, derives seven candidates across at least three material families as a probability distribution rather than a best answer, and writes the chosen direction into the artifact as a five-block contract the critique gate then audits promise by promise \u2014 because more than a quarter of a generative UI tool's stated design rationales are measured not to appear in what it built. Ships a deterministic gate that computes WCAG contrast from source across hex, rgba, hsl and oklch, follows tokens to their :root definitions, composites opacity, and treats contrast as tri-state: a gradient, image or undeclared ground is reported UNMEASURABLE rather than skipped, since an unmeasured pair and a passing pair otherwise serialise identically. The gate names the silent downstream consequence of every finding, gates on mechanism and warns on fashion, runs markup checks through a real HTML parser, refuses to lint its own documentation, requires a reason on every suppression, proves each of its forty rules can still fire, and prints what it did not check so a clean run cannot be read as verified. Carries a Known limits section measured against the one sanctioned browser, so motion, print, reduced-motion and type fidelity are declared unchecked rather than reported clean \u2014 and names the delivery surface's own refusals, because a CDN script inside a publisWhat it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 361 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 10 lines scan A 6d368d6a4864
design-craft is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. 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.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.
ui-ux-pro-max
UI/UX design intelligence. Searchable local database with 84 styles, 192 palettes, 74 font pairings, 25 charts, and 22 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP…