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 dandacompany/bluekiwi --skill bk-designgit clone --depth 1 https://github.com/dandacompany/bluekiwiWrote 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/dandacompany/bluekiwi/bk-design)<a href="https://agentmods.dev/skills/dandacompany/bluekiwi/bk-design"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-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/dandacompany/bluekiwi/bk-design"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-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 | $0.00061 | $0.06848 |
| Opus 5 | $0.00030 | $0.03424 |
| Sonnet 5 | $0.00012 | $0.01370 |
| Haiku 4.5 | $0.00006 | $0.00685 |
Grade A, and why
bk-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 9d 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 — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asking questions across runtimes: wherever this skill says
AskUserQuestion, use your host runtime's native structured-question tool:AskUserQuestion(Claude Code),clarify(Hermes Agent),requestUserInput(Codex CLI),question(opencode). Always present the choices through that tool rather than plain prose. If the runtime has no such tool, list the options as numbered text and wait for the user's reply before proceeding.
BlueKiwi Design System
Use BlueKiwi's design-system registry through MCP tools. Do not write directly to the database or call raw HTTP APIs when MCP tools are available.
Core Concepts
A BlueKiwi design system is a versioned registry resource containing:
- metadata: title, slug, description, status
- taxonomy metadata: category and surface (
web,slides,docs,image,video, oraudio) - schema and split token JSON (
color_tokens,typography_tokens,component_tokens) - guidelines markdown
- SKILL.md-compatible markdown
- component documents for React, pure HTML/CSS, Tailwind CSS, and shadcn/ui components
- assets such as CSS, templates, references, logos, or images
Required Interaction Gate
If the user invokes bk-design without explicitly saying what operation they
want, ask an AskUserQuestion before using mutation tools. The first question
must classify the intent:
- create a design system
- update a design system
- delete a design system
- load or export a design system
Use AskUserQuestion for selection and confirmation steps whenever the next
action would create, update, or delete registry data. Do not infer destructive
intent from vague wording.
Non-Negotiable Operation Protocol
Follow this order for every bk-design invocation:
- Determine intent: create, update, delete, load, export, seed, or apply.
- If intent is missing or ambiguous, ask
AskUserQuestionand stop until the user answers. - For create/update/delete, call
list_design_systemsbefore choosing a target or deciding whether the registry is empty. - For create, compare the request with existing title, slug, category, surface, description, and version family. If any system is plausibly related, ask whether to create a new system or create a new version.
- For update/delete, ask the user to choose the target system from the loaded list before any mutation.
- Ask whether the operation applies to the whole system or a category/entry.
- Show the selected target and intended tool call in plain language, then ask for confirmation before destructive or broad replacement operations.
- Run
lint_design_systemafter substantial create/update work. Resolve errors before saying the system is ready.
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.
- 9d ago First seen · 664 lines · 61 tokens per session scan A 58f79609a325
bk-design is a skill published in the GitHub repository dandacompany/bluekiwi (23 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 6,848 once invoked, about $0.0003 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 2026-08-30.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.