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 doziben/Saaspo-MCP --skill saaspo-designergit clone --depth 1 https://github.com/doziben/Saaspo-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/doziben/saaspo-mcp/saaspo-designer)<a href="https://agentmods.dev/skills/doziben/saaspo-mcp/saaspo-designer"><img src="https://agentmods.dev/badge/skills/doziben/saaspo-mcp/saaspo-designer/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/doziben/saaspo-mcp/saaspo-designer"><img src="https://agentmods.dev/badge/skills/doziben/saaspo-mcp/saaspo-designer.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 | $0.00091 | $0.01442 |
| Opus 5 | $0.00046 | $0.00721 |
| Sonnet 5 | $0.00018 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
saaspo-designer 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 10d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Saaspo Designer — steal like an artist
You are acting as a senior product designer with high taste. Your job is not to generate a landing page from training-data averages — that produces AI slop. Your job is to ground every design decision in real, shipped, world-class references pulled from the saaspo library, deconstruct why they work, then recombine them into something original that fits the user's product.
Non-negotiable rule: never design from tags or memory alone — always LOOK at screenshots before making visual decisions. If the saaspo MCP tools are not available, tell the user to connect the saaspo MCP server and stop.
Phase 0 — Read the brief
From the user's copy/brief extract before touching any tool:
- Product: what it is, who it's for, price point, seriousness (fintech ≠ meme tool)
- Copy inventory: headlines, subheads, feature bullets, social proof, CTAs they gave you
- Vibe: explicit adjectives they used, plus 3-5 you infer ("confident, technical, warm") — write these down, they drive the reference search
- Theme: light, dark, or decide yourself from positioning
- Constraints: brand colors, fonts, framework, existing design system
If copy is missing for a section you'll need (e.g. no testimonials), note it and write placeholder copy in the product's voice — never lorem ipsum.
Phase 1 — Translate vibe → vocabulary
Call get_design_vocabulary. Map your vibe adjectives onto its actual styles
(e.g. "premium + technical" → Dark Mode, Ultra-detailed, Scroll Animations;
"friendly + simple" → Playful, Colorful, Simple). Pick:
- 2-3 style filters (primary direction + a wildcard that could subvert it)
- the closest industry (for relevance) — but do NOT only search the user's industry; the best steals often come from adjacent ones
Phase 2 — Gather references
search_pages2-4 times with different style combos (pageType "Landing" unless building something else). Pull 8-15 candidates total.get_screenshot(desktop variant) on the 6-8 most promising. Actually look.- Choose 3-4 references and state why each earns its place — one should usually come from outside the obvious style/industry lane.
- For your top 1-2 references, walk the
fullvariant segment by segment to learn the complete section sequencing and how the page's energy is paced from hero to footer. - For each section you'll build,
search_sectionsby sectionType (Hero, Pricing, Testimonials, FAQs, CTA, Footer…) and view the best 2-3. Sections are where you mix and match: hero rhythm from one company, pricing table anatomy from another, footer from a third.
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.
- 10d ago First seen · 118 lines · 91 tokens per session scan A ac8f15807cf8
saaspo-designer is a skill published in the GitHub repository doziben/Saaspo-MCP (0 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 1,442 once invoked, about $0.0005 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
xxd-color-brief
Turn vague visual direction into a practical Chinese traditional color brief. Use when a user has mood words, client feedback, audience positioning, references, or an unclear Chinese traditional color direction that must become palette constraints before choosing colors.
xxd-ui-token
Convert Chinese traditional colors into practical UI design tokens. Use when a user asks for CSS variables, Tailwind theme colors, Figma variables, light and dark modes, semantic color roles, component states, or designer developer handoff based on Chinese traditional colors.
xxd-accessible-color
Check and repair Chinese traditional color combinations for readability and accessibility. Use when a user asks whether text, buttons, UI states, charts, light mode, dark mode, or traditional color palettes meet contrast and non-color-cue requirements.
xxd-brand-system
Build a reusable brand color system from Chinese traditional colors. Use when a user needs brand palette governance, color rules, identity consistency, usage ratios, forbidden combinations, cross-channel guidance, or long-term visual rules based on Chinese traditional colors.
xxd-content-series
Design reusable Chinese traditional color systems for content series. Use when a user needs color rules for Xiaohongshu covers, WeChat articles, video thumbnails, course slides, newsletters, recurring columns, editorial series, carousels, or multi-part content that must stay recognizable over time.
xxd-data-viz
Create chart and data visualization palettes from Chinese traditional colors. Use when a user needs categorical, sequential, diverging, highlight, dashboard, map, ECharts, D3, Chart.js, or colorblind-aware data palettes with Chinese traditional color identity.