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 skills add a8cteam51/claude-code-plugins --skill create-designgit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/create-design)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/create-design"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/create-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/create-design"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/create-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00154 | $0.04956 |
| Opus 5.5 | $0.00062 | $0.01982 |
| Sonnet 5.5 | $0.00031 | $0.00991 |
| Haiku 4.5 | $0.00015 | $0.00496 |
Grade A, and why
create-design 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 7d 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Design
Phase 2 of the sp-site-design-harness pipeline (Research → Design → Dev
Handoff). This skill is consistent-high-quality-design, kept close to
as-is and renamed for this plugin — its DISCOVER→DEFINE→DELIVER engine,
seed/risk-ladder variety mechanism, critique pass, and anti-slop audit are
the actual "quality" differentiator in this system and nothing else
reproduces them. See ../../references/instruction-priority.md for the
harness-wide priority order this skill reconciles brief constraints against
its own creative judgment with — brief constraints beat an unstated
stylistic default, explicit brand rules beat the brief's own goals, and
nothing beats accessibility.
Core rule
Do not design by predicting the safest conventional interface. Explore, select, deepen, critique, reduce, and refine until the result has a coherent identity and a convincing level of polish.
Your failure mode is making individually reasonable decisions that are collectively predictable. Check for it at every phase.
Workflow
DISCOVER (expand) → intake, seed, explore in prose, select N (default 3)
DEFINE (commit) → visual thesis + design language, then build composition
DELIVER (reduce) → critique, delete, polish, validate in a browser
DISCOVER runs once; DEFINE and DELIVER run once per selected direction.
Never jump from requirements to implementation. A supplied brand, palette, typeface or reference is a constraint to explore within, never a reason to stop exploring: it fixes the visual identity and says nothing about composition, structure or density — which is where the design actually gets decided.
Skip to DEFINE only when the composition itself is locked — settled page templates, or "match this existing page." Having brand guidelines is not that.
Pass each gate before advancing — see references/gates.md.
Load references on demand:
| File | Read before |
|---|---|
references/intake.md |
Starting any design work (DISCOVER 1) |
references/gates.md |
Advancing phases; declaring the work done |
references/critique.md |
Running the independent design critic (DELIVER 2) |
references/craft-corrections.md |
Running the critic (DELIVER 2) and the craft pass (DELIVER 6) — accumulated craft judgment |
references/typography.md |
Choosing and embedding a typeface (DEFINE 2) |
references/polish.md |
The craft, responsive, and accessibility passes (DELIVER 6-8) |
references/generated-media.md |
Generating any image or video asset (OPTIONAL techniques) |
What ships with it
7 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.
- 7d ago Changed · +6 lines · +27 tokens per session 78cfeb67e3db
- 17d ago First seen · 467 lines · 127 tokens per session scan A cb1fcdb40f04
create-design is a skill published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 154 tokens to every session and 4,956 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.