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 amanmaqsood/design-with-ai --skill aestheticgit clone --depth 1 https://github.com/amanmaqsood/design-with-aiWrote 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/amanmaqsood/design-with-ai/aesthetic)<a href="https://agentmods.dev/skills/amanmaqsood/design-with-ai/aesthetic"><img src="https://agentmods.dev/badge/skills/amanmaqsood/design-with-ai/aesthetic/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/amanmaqsood/design-with-ai/aesthetic"><img src="https://agentmods.dev/badge/skills/amanmaqsood/design-with-ai/aesthetic.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 | $0.00076 | $0.00826 |
| Opus 5 | $0.00038 | $0.00413 |
| Sonnet 5 | $0.00015 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
aesthetic 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aesthetic
Leave the user with working website code, not a moodboard or a list of suggestions. Build a coherent client-specific interface, use outside components only when they fit, and verify the rendered result.
Protect the product
- Preserve working business logic, factual copy, supplied assets, analytics, and framework choices unless the user explicitly puts them in scope.
- In an existing project, adapt to its framework, styling system, component conventions, and package manager. Do not add React, Tailwind, or shadcn solely to reach a component catalog.
- For greenfield interactive product sites, prefer current Next.js, TypeScript, and Tailwind when no simpler stack fits better. Choose the least complex stack that satisfies the brief.
- Treat deployment, paid services, authenticated MCP setup, and framework replacement as separate approval points. If code or a design asset sourced by the agent has unclear license or reuse rights, do not use it; choose a clearly permitted source instead. A user-supplied asset may be used within the requested project, but record it as
Provided by clientand make no broader rights claim.
Run the build
Read references/build-workflow.md, then:
- Inspect the repository, run its baseline checks, and identify the routes and states in scope.
- Derive a visual direction from the client, content, product, and existing brand signals. State the direction briefly and proceed unless a missing brand decision would lead to materially different results.
- Inventory existing primitives before adding anything. If a gap remains, read references/component-sources.md and verify the current official source, compatibility, access, and license.
- Implement foundations and shared components before page-level polish. Preserve behavior while improving hierarchy, typography, spacing, color roles, density, responsiveness, states, and purposeful motion.
- Read references/visual-qa.md, run the site, inspect it at representative desktop and mobile sizes, exercise important states, and run the project's build and tests.
- Report the files changed, outside components used, checks run, rendered views inspected, and anything that remains unverified.
What ships with it
4 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.
- 11d ago First seen · 43 lines · 76 tokens per session scan A f70cb127a2a0
aesthetic is a skill published in the GitHub repository amanmaqsood/design-with-ai (7 stars, last pushed 15d ago), licensed MIT. It adds 76 tokens to every session and 826 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
vois-tokens
Rules and patterns for building UI with shadcn/ui, Tailwind v4 or StyleX, and Motion against a Vois design token set. Use when building components, pages, or any UI that should conform to the workspace design system. Covers spacing, typography, color tokens, component architecture, animation, accessibility, and modern…
designer-skill
Use for UI design, implementation, redesign, visual review, accessibility, responsive behavior, interaction states, and design systems. Preserve established product identity unless the user authorizes a change. Do not activate for backend-only, database-only, CLI, or non-visual tasks. Reviews are read-only unless…
design-engineer-mindset
Translate a design (Figma mockup, spec, screenshot, or verbal description) into code with pixel- and motion-level fidelity, using the browser's rendering pipeline as a constraint: exact spacing/timing via tokens, GPU-safe animations, no layout thrashing, 60fps interactions. Use when the user says 'implement this…
error-handling-recovery
Audit and implement an app's error UX end-to-end: rewrite error messages, place them correctly, add recovery actions, and build error states for validation, network, permission, system, and 404 failures. Use when the user says 'improve my error handling', 'my error messages suck', 'users get stuck when something…
interaction-physics
Design and implement the motion layer of a UI — microinteractions, transitions, hover/press feedback, and animation timing/easing — as working CSS/JS plus a written animation spec. Use when the user says 'the app feels janky', 'animations feel off', 'make it feel smoother/snappier', 'add a transition', 'the modal just…
design-foundation
Create or extract a design-token foundation — colors, typography, spacing, radii, shadows — as a real tokens file (CSS variables and/or Tailwind theme) plus a migration map from current hardcoded values. Use when the user says 'set up a design system', 'our styles are inconsistent', 'we have 50 shades of the same…