Auto-Company is a software system that runs a recurring team of AI agents on a personal computer, where the agents plan work, make decisions, write code, deploy applications, and handle marketing. It is intended for autonomous product development on Windows, Linux, or macOS, using command-line agent tools and a local dashboard to track cycles and results. The catalogue entries are skills, agents, settings, and instructions that support this automated workflow.
Borrowing it
Nothing to install: this file belongs to MaxMiksa/Auto-Company. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MaxMiksa/Auto-Company/main/.claude/skills/frontend-polish/SKILL.mdgit clone --depth 1 https://github.com/MaxMiksa/Auto-CompanyWrote 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/maxmiksa/auto-company/frontend-polish)<a href="https://agentmods.dev/skills/maxmiksa/auto-company/frontend-polish"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/frontend-polish/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/maxmiksa/auto-company/frontend-polish"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/frontend-polish.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 | $0.00057 | $0.01240 |
| Opus 5.5 | $0.00023 | $0.00496 |
| Sonnet 5.5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
frontend-polish 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 19d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Finishing Pass
Bring the working product to a state suitable for direct demonstration and delivery. First use frontend-design. Build on the product's effective design, preserving its overall style, color roles, main layout and familiar actions. Adjust local layout to solve a concrete usability problem; do not change the theme, typographic character, navigation or framework merely to make the difference look larger. New explicit human requirements take precedence.
Entry and completion
- Schedule one dedicated pass once the core flow actually works. If core functionality is blocked, fix and record the blocker first; visual polish must not conceal it.
- Read the current workspace's product, task, existing design decisions and acceptance records. Use only materials accessible within this project's permitted scope. Do not read other projects for a visual direction or a reference answer.
- Do not repeat a completed pass for the current interface version after restart or in the next cycle. Later substantial interface changes need a review of affected screens only. If no worthwhile improvement remains, record that judgment instead of forcing a redesign to produce a diff.
- Record actual changes, screenshots, functional checks and remaining issues, then return to normal product work. Finishing this pass does not require stopping the project or override human governance, budgets or a paused runtime.
Inspect real screens first
Run the current product and inspect its main flow, populated content and result on desktop and mobile. Preserve the initial states and screenshots using the same inputs intended for comparison. Establish what the user came to do, what deserves attention first and where the next action belongs. Identify the issues with the greatest effect on task completion and appearance. Briefly note what to keep, what to fix and why; keep this design commentary out of the product interface.
Refinement priorities
Task, layout and density
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.
- 19d ago First seen · 56 lines · 57 tokens per session scan A 2dcb17ad2ad8
frontend-polish is a skill published in the GitHub repository MaxMiksa/Auto-Company (3,141 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 1,240 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
design-system-skill
Use when building UI in a frontend codebase on top of an existing design system or component library. Discovers tokens and components, reuses them correctly, and binds to semantic tokens instead of hardcoding. Works with ANY system (MUI, Chakra, shadcn, Radix, internal @org/ui, local components, or Figma).
taste
Anti-slop frontend engineering directive and design taste system. Enforces brief inference, dynamic design dials, absolute prohibition of AI visual tells, and 100% full-output completion.
gsap-animation-suite
CIEL's unified framework for high-performance GSAP animations, timelines, and plugins.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
animate
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a…
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…