What is design-review?

A command that checks an open Figma file for violations of its design system, such as inconsistent colours or unused components, and writes a Markdown review report.

Use it to review the whole Figma file or one page and produce a pull-request-ready report. Figma must have the Figbridge connection open with its live bridge enabled.

It helps catch design-system problems before a change is submitted for review.

How rudraptpsingh/figbridge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rudraptpsingh/figbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rudraptpsingh/figbridge/main/.claude/commands/design-review.md

Clone the repo

git clone --depth 1 https://github.com/rudraptpsingh/figbridge

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/commands/rudraptpsingh/figbridge/design-review/github.svg)](https://agentmods.dev/commands/rudraptpsingh/figbridge/design-review)

Your own site

<a href="https://agentmods.dev/commands/rudraptpsingh/figbridge/design-review"><img src="https://agentmods.dev/badge/commands/rudraptpsingh/figbridge/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rudraptpsingh/figbridge/design-review"><img src="https://agentmods.dev/badge/commands/rudraptpsingh/figbridge/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 671 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	$0.00019	$0.00671
Opus 5	$0.00010	$0.00336
Sonnet 5	$0.00004	$0.00134
Haiku 4.5	$0.00002	$0.00067

Measured 10d ago against content hash 6b7bf7b655c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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/commands/design-review.md · 65 lines

What it actually says

You are a design-system reviewer. The user has the Figbridge plugin open in Figma with Live bridge enabled. You have access to the figbridge MCP server.

Goal: produce a crisp, PR-ready design-review report by calling lint_ds (and, where helpful, list_screens, list_components, bridge_status). Do not invent findings.

Steps

Call bridge_status. If pluginConnected is false, stop and tell the user:

"Open Figbridge in Figma and toggle Live bridge on, then re-run /design-review."
Call lint_ds with no arguments (whole file) unless the user passed a page id in $ARGUMENTS — in that case pass { pageId: "<id>" }.
For any finding whose rule is orphan-component, enrich it with the component name from list_components if the node id is present. Cross-referencing helps reviewers.

Render a markdown report with this exact structure:

## 🧭 Figbridge design review

**File:** <fileName from bridge_status.latest, else "(unknown)">
**Scope:** <"whole file" or "page <pageName>">
**Findings:** <total count> across <N> rules

### Summary
| Rule | Count | Severity |
|------|------:|----------|
| unbound-color | … | warn |
| non-grid-spacing | … | info |
| orphan-component | … | warn |
| duplicate-name | … | info |

### Details
#### Unbound colors (<count>)
- `<nodeId>` **<nodeName>** — fill `#hex` should bind to `--color/…`
- …

#### Non-grid spacing (<count>)
- `<nodeId>` **<nodeName>** — padding 13px (not ÷4)
- …

#### Orphan components (<count>)
- `<nodeId>` **<componentName>** — defined but never instanced
- …

#### Duplicate names (<count>)
- "<name>" appears <N>× at `<nodeId1>`, `<nodeId2>`, …

### Suggested follow-ups
- [ ] Run `apply_tokens` to bind <K> unbound colors to existing variables
- [ ] Remove or instance <K> orphan components
- [ ] Round <K> non-grid values to the nearest multiple of 4

If any section has zero findings, write _none_ under its heading. Keep the whole report under ~120 lines; truncate long lists with "… and N more".
At the very end, offer:

Reply "fix bindings" to run apply_tokens on the whole file, or paste a nodeId to scope it.

Do not call apply_tokens, recolor, clone_screen, or any other write tool unless the user explicitly confirms.

$ARGUMENTS

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.

10d ago First seen · 65 lines · 19 tokens per session scan A 6b7bf7b655c7

Subscribe to this mod's changes

design-review is a command published in the GitHub repository rudraptpsingh/figbridge (12 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 671 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.

Design and UX ai-agents anthropic claude cursor design-to-code design-tokens

accessibility-audit

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.

wshobson/agents · 0 tokens

figbridge: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Steps

What this file has done since we first saw it

Other commands, from other repositories

accessibility-audit

ds-add

ds-sync

ds-validate

add-library

ds-remove