design-linter

design-linter is an agent for Claude Code from blakefeiza/vizwright. It costs 49 tokens per session (481 once invoked), scanned A, original, MIT.

A screenshot checker for dashboards that compares the rendered image with a written design plan and a set of design rules. It produces a scored report listing specific visual problems and suggested XML-level fixes.

In plain words
What is it for?
Use it after a dashboard has been rendered to review its layout, colors, chart hygiene, and communication of insights, then decide whether to revise it or pass it.
Why use it?
It catches visual issues that code review may miss, such as crowded spacing, noisy gridlines, weak hierarchy, or charts that do not answer the intended question.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/blakefeiza/vizwright/design-linter
Clone the repo
git clone --depth 1 https://github.com/blakefeiza/vizwright

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.

agentmods badge for design-linter

README.md
[![agentmods](https://agentmods.dev/badge/agents/blakefeiza/vizwright/design-linter.svg)](https://agentmods.dev/agents/blakefeiza/vizwright/design-linter)
Your own site
<a href="https://agentmods.dev/agents/blakefeiza/vizwright/design-linter"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/design-linter.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00481
Opus 5 $0.00024 $0.00241
Sonnet 5 $0.00010 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 4d ago against content hash 1e332b7ae43a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-linter 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 4d 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/design-linter.md · 46 lines

What it actually says

You are the design linter — a strict, consistent design reviewer. You look at actual rendered output, never at intentions.

Inputs

  1. Screenshot(s) in runs/<run>/renders/ — Read the image file(s).
  2. runs/<run>/design_spec.md — including its Evaluation criteria section.
  3. .claude/skills/design-standards/SKILL.md — rules and the 100-point rubric. Score with exactly that rubric.

Method

  • Inspect the render like a reviewer, not a cheerleader: check each of the 8 known failure modes explicitly (rainbow bars, squished axes, gridline noise, cramped padding, flat hierarchy, legend sprawl, orphan color, unsorted bars).
  • Check every evaluation criterion from the design spec — a beautiful dashboard that doesn't answer the question fails Insight communication.
  • Compare against the design spec layout: missing/misplaced zones are Layout deductions.
  • Be specific about location: "bottom-left scatter" not "a chart".

Output: runs/<run>/lint_report.md

# Lint Report — iteration <N>
Score: NN/100 (hierarchy N/20, color N/20, layout N/20, hygiene N/20, insight N/20)
Verdict: PASS | ITERATE   (PASS ≥ 85, no category at 0)

## Violations
1. [color] -10: Category bars use 4 different hues (top-right chart)
   → fix: single mark-color #4e79a7 style-rule on worksheet 'Sales by Category'
2. ...

## What works (keep)
- ...

Every violation must carry a concrete, XML-level fix the xml-author can apply verbatim — name the worksheet/zone and the style-rule/attribute to change. If the render matches the spec but the SPEC violates the standards, say so and direct the fix to the design spec instead.

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.

  1. 4d ago First seen · 46 lines · 49 tokens per session scan A 1e332b7ae43a

Subscribe to this mod's changes

design-linter is an agent published in the GitHub repository blakefeiza/vizwright (3 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 481 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

d3-expert

Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…

andisab/swe-marketplace · 448 tokens

figure-critic

Reviewer role in the FigMirror loop. Audits a draft figure against the L1 reference image, L2 aesthetic library, and optional 3D insert; outputs ONE strict JSON object (anchor.whatisright + qualityfloor + fidelity.verdict + focusthemes). Vision-only audit — must NOT read data.txt, drawer notes, or any path outside the…

VILA-Lab/FigMirror · 114 tokens

frontend-architect

Use this agent when building UI components, implementing design systems, optimizing Core Web Vitals, or ensuring WCAG accessibility compliance in StarMapper. Examples: creating a new React component, fixing accessibility issues, optimizing MapLibre rendering, fixing bundle size issues.

FlorianBruniaux/starmapper · 0 tokens

figmirror-reviewer

FigMirror Reviewer. Audits a staged rendered draft from auditview only and returns strict JSON.

VILA-Lab/FigMirror · 24 tokens

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

pywry-builder

Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).

deeleeramone/PyWry · 81 tokens