design-review

design-review is a command for Claude Code from mohitagw15856/pm-claude-skills. It costs 24 tokens per session (652 once invoked), scanned A, original, MIT.

A four-step design review workflow that checks a design and ends with measured results. It can inspect colours, text sizing, rounded corners, contrast, and colour-vision concerns when given a URL or colour values.

In plain words
What is it for?
Use it to review a website or interface for colour contrast, accessibility against a chosen WCAG level, colour-vision issues, and other visual design details.
Why use it?
It replaces visual guesswork with numbers and clearly states when a screenshot is not enough for a reliable finding. It also carries each review stage's results into the next one.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to review a website or interface for colour contrast, accessibility against a chosen WCAG level, colour-vision issues, and other visual design details.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mohitagw15856/pm-claude-skills/design-review
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,357 stars · on GitHub · mohitagw15856.github.io

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/mohitagw15856/pm-claude-skills

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mohitagw15856/pm-claude-skills/design-review/github.svg)](https://agentmods.dev/commands/mohitagw15856/pm-claude-skills/design-review)
Your own site
<a href="https://agentmods.dev/commands/mohitagw15856/pm-claude-skills/design-review"><img src="https://agentmods.dev/badge/commands/mohitagw15856/pm-claude-skills/design-review/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.

agentmods 80×15 button for design-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/mohitagw15856/pm-claude-skills/design-review"><img src="https://agentmods.dev/badge/commands/mohitagw15856/pm-claude-skills/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00652
Opus 5 $0.00012 $0.00326
Sonnet 5 $0.00005 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 12d ago against content hash 39d618e4cd1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-review 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 12d 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.

commands/design-review.md · 28 lines

What it actually says

Run the Design Review workflow recipe for: $ARGUMENTS

This is a chain of skills. Run each stage in order and carry every stage's output forward as context for the next. Open with a one-line plan of the 4 stages, then ask once for essential missing inputs (the actual hex values or a URL, the target WCAG level, whether it will ever be printed, who signs off). Don't re-ask between stages.

Before stage 2, measure. A design review that assesses contrast by eye is an opinion with a standards reference attached. If you have a URL or hex values, run these first and carry the numbers through every stage:

npx --yes notugly spec <url>                        # palette, type scale, radii — what it is made of
npx --yes notugly onepager <url> --out review.html  # every pairing, with the nearest passing colour
npx --yes notugly vision <url>                      # colours that merge for colour-blind viewers

Deterministic, zero dependencies, no model call. If you only have a screenshot, say so explicitly in the output — an inferred ratio is not a finding.

Run each stage under a clear ## Stage N — <name> heading:

  1. React honestly — apply the design-critique skill: what the design is trying to do, where it succeeds, and where intent and execution diverge. Do this before the measurements so the critique is about the design rather than about its contrast ratios.
  2. Measure what can be measured — apply the accessibility-audit skill, filling every contrast row from the notugly output above rather than assessing it. Flag explicitly which findings are computed and which are judgement.
  3. Check the system behind it — apply the design-system-audit skill: is this a one-off, or does it reveal a token problem? Run npx notugly tokens <file> if a token file exists; it names failing pairs semantically (color.text.danger on surface.default is 2.99:1), which turns a vague note into a bug with an owner.
  4. Hand it over — apply the design-handoff-brief skill: the decisions, the measured values, and the open questions, in the form an engineer can build from.

Close with a one-page verdict: the three things to fix before ship, the measured evidence for each, and the split between find-and-replace fixes and fixes that need a design decision. That split is the whole reason this recipe exists — "twelve accessibility issues" gets deferred; "nine are a find-and-replace and three need Priya to pick a colour" gets scheduled.

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. 12d ago First seen · 28 lines · 24 tokens per session scan A 39d618e4cd1e

Subscribe to this mod's changes

design-review is a command published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 652 once invoked, about $0.0001 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 2026-08-30.