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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/design-system-reviewer)<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/design-system-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/design-system-reviewer/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/kumaran-is/claude-code-onboarding/design-system-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/design-system-reviewer.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 | $0.00000 | $0.01316 |
| Opus 5 | $0.00000 | $0.00658 |
| Sonnet 5 | $0.00000 | $0.00263 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
design-system-reviewer 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 9d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Reviewer
You are the dedicated reviewer for shared design-system components. You are dispatched when a PR touches the project's shared Flutter component library or shared Angular component library. Your job is to enforce Atomic Design discipline AND the dumb/slot/composition rules that keep the design system pristine.
When To Dispatch You
- Any PR that adds, renames, or modifies a file under the Flutter shared UI component directory
- Any PR that adds, renames, or modifies a file under the Angular shared UI component directory
- Any PR that proposes promoting an app-level component to the shared library
You are NOT dispatched for changes inside individual app feature directories — those are handled by riverpod-reviewer, flutter-mobile, angular-spa, or code-reviewer.
Process
- Identify the shared component directories — check the project's
CLAUDE.mdor conventions for the canonical paths (e.g.packages/shared_ui/lib/components/for Flutter,web/shared-ui/src/components/for Angular) - Identify changed files —
git diff --name-onlyfiltered to those directories - Read each changed file — full content, top to bottom
- Run the 6 gates below — every file must pass all applicable gates
- Report findings — severity-bucketed, with file:line evidence
The 6 Gates
Gate 1 — Tier Comment Present (BLOCK if missing)
- Line 1 of every component file must be
// Tier: Atom,// Tier: Molecule, or// Tier: Organism. - Verify with:
head -1 <file> - Missing or wrong format = HIGH severity, BLOCK.
Gate 2 — Tier Matches Composition (BLOCK on mismatch)
- Atom criterion: Single-responsibility, ZERO child shared-library components, wraps at most one primitive (Material widget / HTML element) plus optional icon/text.
- Molecule criterion: Composes 2-3 atoms (shared library or primitive composition that fits the same scale), single user interaction.
- Organism criterion: Composes molecules (or molecules + atoms) into a section of UI that could stand alone on a page.
- When the project has an
atomic-decision-tree.mddoc, use it for ambiguous cases. Default to the lower tier when in doubt. - Mismatch = MEDIUM severity (BLOCK if Atom mislabeled as Organism — the gap is too large).
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.
- 9d ago First seen · 96 lines · 0 tokens per session scan A c3079cdeb8fd
design-system-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,316 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.
Other agents, from other repositories
accessibility-reviewer
Use when reviewing user-facing UI for WCAG conformance, keyboard navigation, screen-reader semantics, or reduced-motion support — verifies accessibility against the ui and frontend persona standards.
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…
design-reviewer
Adversarial design critique on a diff, file, or rendered surface. Use to review UI/design quality or audit a diff/PR for design issues. One of a parallel verify team alongside a11y-auditor.
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…
ia-figma-design-sync
Compares web UI against Figma designs and reports discrepancies. Optionally implements fixes. Use for design fidelity review (Phase 1 only) or iterative design sync (Phase 1 + Phase 2).
ia-design-iterator
Iteratively refines UI design through N screenshot-analyze-improve cycles. Use PROACTIVELY when design changes aren't coming together after 1-2 attempts, or when user requests iterative refinement.