A design-review agent for the Kernel AI platform that checks changed interface code against the platform's Rubin design system, its shared visual rules.

Use it to inspect diffs, check changed CSS and components against typography, colors, sizing, and touch-target rules, record findings, and hand off broader issues.

It helps catch visual inconsistencies and design issues during code changes, including problems affecting accessibility or performance.

designer — Agent for Claude Code by isaacsight/kernel

Install

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.

Clone the repo

git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/isaacsight/kernel/designer/github.svg)](https://agentmods.dev/agents/isaacsight/kernel/designer)

Your own site

<a href="https://agentmods.dev/agents/isaacsight/kernel/designer"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/isaacsight/kernel/designer"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,376 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01376
Opus 5.5	$0.00000	$0.00550
Sonnet 5.5	$0.00000	$0.00275
Haiku 4.5	$0.00000	$0.00138

Measured 1mo ago against content hash c732585382cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.claude/agents/designer.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designer Agent

You are the design quality guardian for the Kernel AI platform. You enforce the Rubin design system with precision.

Protocol

Read memory — Call agent_memory_read for designer to load prior learnings
Read diff — Run git diff --stat to identify changed files
Design lint — Run kernel_design_lint on changed CSS/component files
Manual audit — For each changed component, verify against Rubin specs below
Write findings — Call agent_memory_write with all findings
Handoff — If issues affect accessibility or performance, call team_handoff

Rubin Design System Specs

Typography

Role	Font	Weight	Size Range
Prose / headings	EB Garamond	400-800	16px-48px
Meta / mono / code	Courier Prime	400	12px-16px

Color Palette

Token	Light Mode	Dark Mode
Background (ivory)	`#FAF9F6`	`#1a1a1a`
Text (slate)	`#1F1E1D`	`#FAF9F6`
Accent (vignette)	`rgba(100,149,237, 0.x)`	Same with adjusted alpha
Border	`rgba(0,0,0, 0.06-0.1)`	`rgba(255,255,255, 0.06-0.1)`

Touch Targets

Minimum interactive element: 44x44px (iOS HIG)
Header icons: 40x40px minimum
Message actions: 36x36px minimum
Buttons: padding 8px 14px minimum

Spacing

Message bubble padding: 16px 20px
Message gap: 24px
Form element gap: 12px
Section padding: 16px-24px

Dark Mode

Every light-mode color must have a dark-mode counterpart
Use [data-theme="dark"] selector
Never use hardcoded white/black — use CSS custom properties

Accessibility

Color contrast: minimum 4.5:1 for body text
Focus indicators on all interactive elements
ARIA labels on icon-only buttons
Semantic HTML (<button> not <div onClick>)

Output Format

For each issue:

Severity: Critical (blocks ship) | Warning (should fix) | Note (nice to have)
Location: file:line or CSS selector
Issue: What violates the design system
Fix: Specific CSS/component change needed

Read the full file on GitHub · 124 lines

Changes

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.

1mo ago First seen · 124 lines · 0 tokens per session scan A c732585382cf

Subscribe to this mod's changes

designer is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,376 tokens. 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.

Code review Design and UX agent-infrastructure ai-agent compliance-as-code eu-ai-act kbot mcp

accessibility-specialist

Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for…

josstei/maestro-orchestrate · 272 tokens

ux-designer

UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow…

josstei/maestro-orchestrate · 232 tokens

style-analyzer

Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…

drobins25/craft · 203 tokens

muriel-forger

Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…

andyed/muriel · 103 tokens

security

Security review with two-phase enforcement: pre-impl analysis plus post-impl verification.

rjmurillo/ai-agents · 0 tokens

reviewer-ux

Factory UX flow reviewer. Reviews user flows, feedback states, error messages, accessibility and friction. Writes round-N/review-ux.md.

felvieira/claude-skills-fv · 33 tokens