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 liqiongyu/lenny_skills_plus --skill design-systemsgit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/design-systems)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/design-systems"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/design-systems/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/liqiongyu/lenny_skills_plus/design-systems"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/design-systems.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 | $0.00022 | $0.01997 |
| Opus 5 | $0.00011 | $0.00999 |
| Sonnet 5 | $0.00004 | $0.00399 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
design-systems 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 12d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Systems
Scope
Covers
- Creating or upgrading a design system (tokens + components + guidelines)
- Using blockframes (lo-fi, system-aware wireframes) to lock logic before hi-fi execution
- Designing a future-ready visual foundation (depth/elevation, motion, texture) without breaking consistency
- Making the system easy for non-experts to use (guardrails, examples, starter templates)
- Driving adoption + governance (contribution model, champions, release cadence)
When to use
- “We need a design system / component library and a plan to build it.”
- “Our UI is inconsistent—define tokens + components + documentation to standardize.”
- “We want to refresh our UI style (more depth/texture/motion) without chaos.”
- “We need to scale design across teams or support enterprise customers with customization.”
- “We want faster hi-fi output by locking flows in lo-fi first.”
When NOT to use
- You’re defining a brand identity or logo system (different process).
- You need user research/discovery to decide what to build.
- You only need to ship one isolated UI change (just implement it).
- You’re doing pure front-end architecture unrelated to UI consistency.
- You want to stand up a design engineering function or define the hybrid role (use
design-engineering). - You need to run a one-off design review or critique session (use
running-design-reviews). - You want to improve engineering team culture, rituals, or hiring (use
engineering-culture). - You need a detailed feature spec or UX flow document (use
writing-specs-designs).
Inputs
Minimum required
- Product + surfaces: web/iOS/Android; key flows
- Current state: existing UI kit/design system (if any), design tool (e.g., Figma), code stack (if relevant)
- Goals: speed, consistency, accessibility, scalability, customization, enterprise adoption
- Constraints: timeline, team ownership, level of engineering support, compliance/a11y needs
Missing-info strategy
- Ask up to 5 questions from references/INTAKE.md, then proceed with explicit assumptions.
- If platform/stack is unknown, assume a modern web product with a component library and design tokens.
- Do not request secrets or credentials.
What ships with it
13 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.
- eval/eval_config.json 885 B
- eval/SHOWCASE.md 5.1 KB
- eval/with_skill.md 39 KB
- eval/without_skill.md 23 KB
- README.md 1.8 KB
- references/CHECKLISTS.md 2.0 KB
- references/EXAMPLES.md 1.8 KB
- references/INTAKE.md 1.8 KB
- references/RUBRIC.md 4.5 KB
- references/SOURCE_SUMMARY.md 1.1 KB
- references/TEMPLATES.md 4.6 KB
- references/WORKFLOW.md 4.6 KB
- skillpack.json 354 B
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.
- 12d ago First seen · 129 lines · 22 tokens per session scan A 4616e49d774e
design-systems is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,997 once invoked, about $0.0001 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
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
peer-selection
A guide for thinking about which friends, partners, and social circles to keep close, based on shared values and their influence on your life.