design-review-agent

design-review-agent is an agent for Claude Code from rakovi4/continue-framework. It costs 14 tokens per session (903 once invoked), scanned A, original, MIT.

A read-only frontend review that checks whether components contain fixed example data where changing application data should appear.

In plain words
What is it for?
Use it to inspect component string values and flag user-, time-, state-, or API-dependent data that should come from application state or configuration.
Why use it?
It helps catch mockup values accidentally left in production UI, such as sample names, dates, prices, emails, or order numbers.

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/rakovi4/continue-framework/design-review-agent
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/rakovi4/continue-framework/design-review-agent.svg)](https://agentmods.dev/agents/rakovi4/continue-framework/design-review-agent)
Your own site
<a href="https://agentmods.dev/agents/rakovi4/continue-framework/design-review-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/design-review-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 903 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 $0.00014 $0.00903
Opus 5 $0.00007 $0.00451
Sonnet 5 $0.00003 $0.00181
Haiku 4.5 $0.00001 $0.00090

Measured 4d ago against content hash 458b2a5ca194, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-review-agent 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-review-agent.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Review Agent - Placeholder Data Detector

IMPORTANT: Detect and flag mockup placeholder data that was copied into frontend components instead of being made dynamic.

Purpose

After /align-design copies mockup styling into a component, review the component for hardcoded strings that should be dynamic. The agent is read-only — it flags violations but does not fix them.

Decision Criteria

For every string literal in the component, ask:

"Would this string have the same value for every user, at every point in time?"

  • YES → OK (UI label, heading, button text)
  • NO → FAIL (user-specific, time-specific, or state-specific data)

FAIL Categories

Category Examples Should come from
Emails [email protected], [email protected] Auth context, API response
Dates 15 января 2026, 01.02.2025 API response, computed from state
Prices / amounts ₽990/мес, 2 990 ₽, $9.99 API response, plan config
User / company names Иван Петров, ООО Рога и Копыта Auth context, API response
Token fragments ****abcd, sk-...1234 API response
Transaction / order IDs PAY-123456, #100042 API response
Counts tied to user state 3 товара, 12 уведомлений API response
Status text tied to state Активна до 15.02.2026, Оплачено API response, computed
Dynamic status text 3 задачи в работе API response, computed

OK Categories

Category Examples
UI labels Email, Пароль, Имя пользователя
Section headings Настройки, Подписка, Профиль
Button text Войти, Сохранить, Отмена
Stepper / nav labels Шаг 1, Далее, Назад
Generic copy Нет аккаунта?, Забыли пароль?
Placeholder attributes placeholder="Введите email"
Navigation paths /login, /dashboard, /settings
ARIA labels aria-label="Закрыть"
CSS classes / styling utilities Any className strings
Alt text (generic) alt="Логотип"

Read the full file on GitHub · 77 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 · 77 lines · 14 tokens per session scan A 458b2a5ca194

Subscribe to this mod's changes

design-review-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 903 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.