Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install design-packWrote 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/atretyak1985/swarmery/design-implement)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/design-implement"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/design-implement.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 5.1 | $0.00163 | $0.03664 |
| Opus 5 | $0.00081 | $0.01832 |
| Sonnet 5 | $0.00033 | $0.00733 |
| Haiku 4.5 | $0.00016 | $0.00366 |
Grade A, and why
design-implement 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Six phases that carry a screen from "here is a design" to "here is a measured diff". Each phase has exactly one output, and the next phase does not start until that output exists.
Two rules hold the whole workflow up: the token inventory comes from a real headless render, never from reading the design's CSS by eye; and completion is a number plus an image, never an impression.
This document is the procedure only. Input shapes and what each one can promise live in
design-acquire; the measurement procedure lives in design-verify; the precision rules
live in references/fidelity-checklist.md and the named failure modes in
references/anti-patterns.md. Nothing here repeats them.
Step 0 — Prerequisites
0.1 — Read ${CLAUDE_PROJECT_DIR}/.claude/project.json, the design block.
Required: design.tokensFile, design.componentsRoot, design.routesRoot, design.devUrl,
design.verify (both verify.lint and verify.typecheck).
If the block is missing, or any required field is empty, stop loudly. Name the specific fields that are not filled in — not "the config is incomplete", but the list of them — and say where the form is: the project dashboard → plugins → design-pack. Do not guess a path, do not infer a components root from a directory listing, do not run on a partial block.
Optional fields and their defaults:
| Field | Default | Read by |
|---|---|---|
design.fontLoader |
— | Phase 3 font check (next-font | link-tag | self-hosted | none) |
design.devCommand |
— | Phase 6, when design.devUrl does not answer |
design.diff.threshold |
0.5 |
Phase 6 verdict |
design.diff.pixelTolerance |
0.1 |
Phase 6 per-pixel comparison |
design.budget.maxIterations |
4 |
Phase 5 correction loop cap |
design.budget.maxFiles |
12 |
Phase 4 sanity cap on the approved file list |
0.2 — Read the project's CLAUDE.md in full, before any edit. In a large repository that
file carries the decision history that changes how a screen is built — which layer owns
styling, which component library is already committed to, what is deliberately not abstracted.
Skipping it produces work that is locally correct and architecturally wrong.
What ships with it
2 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.
- 5d ago First seen · 282 lines · 163 tokens per session scan A 1edef2c86aff
design-implement is a skill published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 3,664 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
brand-landingpage
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…
smui
Local copy of the smui ("spacemolt") design system ( ), adapted for the CAD Viewer. smui is a Nord-inspired terminal aesthetic for shadcn/ui with light and dark modes: sharp edges, monospace everything. Read this whole document before restyling viewer UI.
web-animation-design
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use…
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.