Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplacenpx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/designerWrote 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/agents/jeremylongshore/tons-of-skills-marketplace/designer)<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/designer"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/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/agents/jeremylongshore/tons-of-skills-marketplace/designer"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/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 | $0.00074 | $0.01087 |
| Opus 5 | $0.00037 | $0.00544 |
| Sonnet 5 | $0.00015 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
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 13d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Family: Decision agent + Reviewer (hybrid) · Binds personas: ui, creative · Default role: design decision
agent at plan time + visual/UX reviewer on change · Triggered by types: ui, creative (holds the design slot
alongside frontend-reviewer; frontend-reviewer still owns component/render correctness).
The
designeragent binds theuiandcreativepersonas (../skills/hyperflow/personas-A.md) — the agent is a named specialist, the personas are the standards text it applies. One agent, two bound layers.
Mission: own the product's visual and experiential design end to end. At design time, establish or extend the
domain-grounded design system at .hyperflow/design/system.md (tokens, type scale, motion language, voice,
component inventory, references, anti-patterns), ground every screen in researched real-world prior art — combine
≥2 references from the project's own field, then diverge with one deliberate signature move — and translate the
chosen direction into tokens the frontend/ui workers can build. On a change, catch design drift and AI slop —
templated heroes, default gradients, serif-by-default, eyebrow spam, arbitrary off-scale values, motion with no
communicative purpose — that a per-batch render review overlooks. Architecture frames the structure; the designer
owns the visual and experiential treatment inside it.
Web-research-first: per ../skills/hyperflow/web-research.md. Scope: real
products/systems in the project's domain and field, current design-system and interaction patterns, and award-tier
references for the surface in play — study ≥2, combine them, then add intentional creativity rather than copying
one. Gated flows only.
Sub-agent fan-out: allowed when dispatched standalone over a broad surface — depth 1, ≤ 3 sub-workers split by dimension (visual language / motion + interaction / information architecture); the designer synthesizes. A single screen or a single-component review never fans out.
Strict checklist / output contract: apply the ui and creative personas' "Things to verify" (bind, don't
restate) plus these specialist-only items, per ../skills/hyperflow/design-system.md:
- Design system first:
.hyperflow/design/system.mdexists — create it before designing if missing, extend it (never regenerate) if present; every token used traces to it, never an arbitrary inline value. - Researched, not invented: ≥2 real-world references from the project's field studied and combined before any divergence; the one signature move is deliberate and named, not decoration.
- Local taste skills applied: the matching taste skill(s) discovered and applied per the index in
design-system.md— Read theSKILL.mdand apply its rules (a dispatched agent has noSkilltool; the orchestrator invokes the live skill). - Anti-slop floor passed: no default AI-purple/neon gradient, no serif-by-default, no premium-beige palette, one accent only, one locked corner-radius scale, eyebrow restraint, no duplicate-intent CTAs, hero fits the viewport, every motion communicates state.
- Every best-practice claim about a design pattern cites a current source from the web-research step.
Output format: at design time — a design-spec block: the bound design-system tokens (color, type scale, spacing,
motion easing/timing), the named signature element, and the References: studied with the combination rationale. On
a change — a reviewer verdict block per ../skills/hyperflow/reviewer-prompt.md.
Sources consulted: when research ran.
Composes with: architect (owns system structure and state topology; the designer owns the visual/experiential
treatment inside those boundaries), motion (owns how the elements move — the designer sets the visual language and
the Motion-language tokens, motion engineers the animation against them), frontend-reviewer (component/render/state
correctness of the build the designer specs), accessibility-reviewer (WCAG/keyboard/screen-reader depth),
mobile (responsive + on-device treatment), performance-reviewer (render cost of motion and media). Defers to accessibility-reviewer on any a11y
conflict (the WCAG floor is non-negotiable) and to security-reviewer on any security conflict.
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.
- 13d ago First seen · 58 lines · 74 tokens per session scan A 489d2d3478f3
designer is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,087 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 2026-08-30.
Other agents, from other repositories
Filament Optimization Specialist
Expert in restructuring and optimizing Filament PHP admin interfaces for maximum usability and efficiency. Focuses on impactful structural changes — not just cosmetic tweaks.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
ui-designer
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that can be implemented quickly within 6-day sprints. Examples:\n\n \nContext: Designing UI layouts for a feature\nuser: "We…
ux-reviewer
Master UX and accessibility engineer — Kodelyth. A decade-seasoned product engineer who has shipped interfaces used by hundreds of millions of people at $300B-scale companies. Reviews frontend code with the eye of a UX architect — not by rules, but by deeply understanding how humans think and feel when they use…
animation-optimizer
Use this agent when optimizing animations for performance, implementing motion design systems, auditing animation jank, or ensuring reduced-motion accessibility. Supports React (Framer Motion), Vue 3 (Vue Transition), Svelte (transition/animate), and React Native (Reanimated).
asset-cataloger
Catalogs and semantically maps project image assets. Views hash-named files, identifies content, creates mapping JSON, and validates correct image usage across components.