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 agentmods add skills/bryntay/a1-mcp/design-referencenpx skills add bryntay/a1-mcp --skill design-referencegit clone --depth 1 https://github.com/bryntay/a1-mcpWrote 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/bryntay/a1-mcp/design-reference)<a href="https://agentmods.dev/skills/bryntay/a1-mcp/design-reference"><img src="https://agentmods.dev/badge/skills/bryntay/a1-mcp/design-reference.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 | $0.00072 | $0.00692 |
| Opus 5 | $0.00036 | $0.00346 |
| Sonnet 5 | $0.00014 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
design-reference 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground the decision in real sites
A1 holds 1,165 live websites, 3,209 captured sections across 826 of them, and 2,860 full-page captures. Sections carry values measured off the live page — type sizes, spacing, container width, radius, palette hex — so a design question can be answered with numbers rather than an opinion.
Pick the tool by the shape of the question.
| Question | Tool |
|---|---|
| "What type scale do agency heroes use?" | analyze_design_tokens |
| "What do portfolio FAQs ask about?" | analyze_section_content |
| "Show me dark fintech heroes" | search_sections |
| "Find minimal law-firm sites" | search_websites |
| "How does Stripe design its pricing page?" | get_website_pages |
| "Compare pricing pages across sites" | search_pages |
Aggregates before examples
For anything phrased as a norm — how big, how much, what's typical — start with
analyze_design_tokens or analyze_section_content. They read every site captured. A
handful of screenshots is not evidence of a norm, and picking three examples yourself
invents one.
Then pull two or three examples with search_sections so the user can see the numbers in
context.
Read the quartiles as quartiles
analyze_design_tokens returns p25 / median / p75, not an average, because these values
are long-tailed. Report the range. "Agency heroes run 48–72px, median 60" is the useful
answer; "the average is 58.4px" is not.
Respect lowSample
Both aggregate tools set lowSample: true when the slice is thin, and narrow slices go
thin fast — a sectionType and a websiteType together often land on five sections.
When you see it, say so and widen the filter. Do not report a percentage off five
sections, and do not present them as what such sites typically do. The tool tells you
which way to widen; drop websiteType first.
Search in the gallery's own vocabulary
search_websites matches taxonomy tags, so a vague visual brief lands better rephrased in
the gallery's terms: big-type, minimal, editorial, brutalist, monochrome,
blurred-gradients, scroll-animation, bento. get_design_filters returns the full
list with counts.
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 · 63 lines · 72 tokens per session scan A 4427d3f0b4fa
design-reference is a skill published in the GitHub repository bryntay/a1-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 692 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
使用 OpenQuantum 的 QMClaw Local Tool 对超导量子比特 S21、能谱、Rabi、Ramsey、T1、SingleShot、DRAG、π 脉冲、功率偏移、Delta 和 RB 等 13 类测控实验做有界、确定性的本地模拟，并组织单比特调校工作流。用于实验规划、接口联调、教学和无硬件预检；不连接 LabRAD/lqms、真实仪器或量子云，不修改校准参数，也不替代 Scientific Validator。.
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
xmemo-vscode
Use XMemo from VS Code (and forks like Cursor/Windsurf) to recall project context, capture engineering decisions, preserve handoff state, and connect to the hosted XMemo MCP endpoint safely.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.