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 LucasSantana-Dev/sharekit --skill frontend-reference-huntgit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/frontend-reference-hunt)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/frontend-reference-hunt"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/frontend-reference-hunt/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/lucassantana-dev/sharekit/frontend-reference-hunt"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/frontend-reference-hunt.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 | $0.00158 | $0.01306 |
| Opus 5 | $0.00079 | $0.00653 |
| Sonnet 5 | $0.00032 | $0.00261 |
| Haiku 4.5 | $0.00016 | $0.00131 |
Grade A, and why
frontend-reference-hunt 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Reference Hunt
Turns "I want it to look premium, not AI-made" into a concrete, current reference board sourced from real platforms, so build skills anchor on shipped work instead of training-data averages (the root cause of slop convergence).
Use When
- A frontend task needs visual direction and no reference board exists yet.
- A build skill (repaint, frontend-craft) is about to run its reference-anchor phase and would otherwise anchor from memory.
- User asks for UI/UX/motion references, a moodboard, or "what does good look like" for a surface.
Do Not Use When
- References already curated this session (reuse the existing board).
- The task is building or restyling UI itself — hand the board to
repaint/frontend-craft. - Pure motion implementation questions —
repaint's motion archetypes may suffice without a hunt.
Inputs / Prereqs
- Brief: surface type (landing / dashboard / app / component), register (production-credible vs art-directed), brand constraints (existing tokens? audience?), motion ambition (none / subtle / immersive).
- Browser:
claude-in-chromeMCP against the user's Chrome (Mobbin and Pinterest gate most content behind the user's logged-in session). Fallback for public pages: WebSearch + WebFetch.
Workflow
- Lock the brief (4 axes above). If a build skill dispatched this hunt, inherit its register lock verbatim; never re-decide register here.
- Route platforms by goal — full URL patterns, query recipes, and per-platform quality
heuristics in references/platform-playbook.md:
- Real shipped product UI / UX flows → Mobbin (strongest anti-slop signal).
- Visual direction, type, art-direction polish → Dribbble (concept work; steal visuals, distrust feasibility).
- Broad moodboard, typography, palettes → Pinterest.
- Immersive motion / award-grade → Awwwards, Godly. Landing pages → Land-book, SaaS Landing Page. Editorial → siteinspire. Minimum 2 platforms per hunt; one platform = one aesthetic monoculture.
- Search with the playbook's query recipes. Screenshot every candidate
(claude-in-chrome) into the project's
.claude/design/refs/(create if missing). - Curate 5–9 references through the quality gates:
- Shipped beats concept; recent (≤2y) beats classic unless deliberately retro.
- Reject anything matching the slop cluster: default purple-gradient-on-dark, glassmorphism cards, hero + 3 feature cards, Inter-everywhere, emoji icons.
- Board must disagree with itself somewhere (two candidate directions), or it is a monoculture.
- Extract per reference into the board (template: references/reference-board-template.md): URL + screenshot path, register, typography pairing, palette (sample real values from the screenshot), spacing/layout rhythm, motion archetypes by name, steal list, avoid list.
- Emit + hand off: write
<project>/.claude/design/reference-board-<slug>.md, then state the 2 candidate directions and which one you recommend for the brief. If a build skill is waiting, pass the board path as its reference anchor.
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.
- 8d ago First seen · 99 lines · 158 tokens per session scan A 0726b772a88b
frontend-reference-hunt is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 1,306 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
accessibility
This skill should be used when the user asks to "add accessibility", "check ARIA", "handle keyboard navigation", "add focus management", or creates UI components, forms, or interactive elements. Provides WCAG 2.2 AA patterns for keyboard navigation, ARIA roles and states, focus management, color contrast, and screen…
ui-design
This skill should be used when the user asks to "design a component", "pick colors", "improve typography", "fix spacing", "choose a layout", or discusses visual design, CSS, styling decisions, or responsive interfaces. Provides patterns for typography scales, color systems, spacing, and production-grade UI design.
frontend-taste
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…
designer-skill
Prescriptive frontend design guidance via the designer-skill MCP server. Use when the user asks to use designer-skill, improve UI/UX, run the anti-slop ship gate, apply a design system, or enhance pages/components with MCP-backed design references — especially for Pythinker docs and marketing surfaces with…
design-tokens
Project-level DESIGN.md tokens reference. When the project has a DESIGN.md file, agents producing UI / components / visuals must consult this skill to use canonical color/typography/spacing tokens rather than inventing new ones. Triggers on: UI generation, component creation, design brief, visual asset, tailwind…
ui-audit
Audit UI for design token compliance and component adoption. Static grep-based analysis against the sitemap's page and component files. Requires a design system with semantic tokens.