check-design

check-design is a command for Claude Code from alifanov/darkflow. It costs 20 tokens per session (1,084 once invoked), scanned A, original, MIT.

A proposal-only review of an interface’s visual quality, speed, and readiness for real users and content.

In plain words
What is it for?
Use it to review pages listed in a site map or inspect repository components, then create one task for each distinct visual issue.
Why use it?
It finds visual problems such as overflow on small screens, poor contrast, untranslated text, and truncation before they reach production. It records findings as tasks without changing the project.

Command 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 commands/alifanov/darkflow/check-design
Clone the repo
git clone --depth 1 https://github.com/alifanov/darkflow

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 check-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/alifanov/darkflow/check-design.svg)](https://agentmods.dev/commands/alifanov/darkflow/check-design)
Your own site
<a href="https://agentmods.dev/commands/alifanov/darkflow/check-design"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/check-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,084 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 $0.00020 $0.01084
Opus 5 $0.00010 $0.00542
Sonnet 5 $0.00004 $0.00217
Haiku 4.5 $0.00002 $0.00108

Measured 4d ago against content hash 0de8102e0903, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-design 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.

templates/.claude/commands/darkflow/check-design.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The visual half of design review: what the interface looks like, how fast it paints, and whether it survives contact with real content. Its counterpart is check-ux, which walks the flows instead of looking at the surfaces.

Proposal-only. Findings become tasks; nothing is changed here.

Step 1 — Read project config

Load the project config (contract in .darkflow.d/claude.mdProject config). Uses: language, stagingUrl, domain.

Check against stagingUrl when it is set, otherwise domain. There is no list of key pages to maintain: read sitemap.xml and pick the pages from it. If neither URL is set and there is no sitemap, audit the components in the repo and say so in one line.

Step 2 — Quality

/impeccable:audit

Step 3 — UI performance

/impeccable:optimize

Step 4 — Production readiness

/impeccable:harden

Cover the visual failure modes only — text overflow at 320px, contrast, untranslated strings, truncation with long real-world content. The behavioural ones (a flow that dead-ends on an error, a missing empty state you can only reach by using the app) belong to check-ux.

Step 5 — Deduplicate, then file

Read every task in the project, not just this routine's own:

~/.darkflow/df task list --state all --format compact

Design, UX, performance and build audits all reach the same slow page from different angles; filtering by --source would file it two or three times. Skip anything already tracked or already dismissed (closed without a merged fix — rejected). Re-file only when a previously-fixed problem has demonstrably regressed. A performance finding already covered by build-optimization is theirs, not yours.

  • --source design, --status proposed
  • Priority:
    • high — broken layout, inaccessible element, missing state on a critical screen, LCP > 2.5s, CLS > 0.1
    • medium — visual inconsistency, unclear hierarchy, spacing, measurable slowdown, large unoptimized asset
    • polish and nice-to-have → no task. It goes in the snapshot's Recommendations, nowhere else.

Read the full file on GitHub · 128 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.

  1. 4d ago First seen · 128 lines · 20 tokens per session scan A 0de8102e0903

Subscribe to this mod's changes

check-design is a command published in the GitHub repository alifanov/darkflow (2 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 1,084 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 2026-08-31.