creo-design-implement

creo-design-implement is an agent for Claude Code from oyusypenko/creo. It costs 20 tokens per session (783 once invoked), scanned A, original, MIT.

A coding-agent helper that applies fixes listed in a design review report, starting with small screens and checking the result in a browser.

In plain words
What is it for?
Use it to fix layout overflow, typography, and other design issues in a running web project at mobile, tablet, and desktop widths.
Why use it?
It turns a list of interface problems into an ordered implementation task and checks whether the fixes work at several screen sizes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the creo plugin — 17 skills, 16 agents shipped together

Good fit Use it to fix layout overflow, typography, and other design issues in a running web project at mobile, tablet, and desktop widths.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oyusypenko/creo/creo-design-implement
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/oyusypenko/creo

Made for: Claude Code.

Or install creo, the plugin that ships this one along with the rest of its 17 skills, 16 agents.

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 creo-design-implement

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/creo/creo-design-implement.svg)](https://agentmods.dev/agents/oyusypenko/creo/creo-design-implement)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-design-implement"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-design-implement.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 783 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 $0.00020 $0.00783
Opus 5 $0.00010 $0.00392
Sonnet 5 $0.00004 $0.00157
Haiku 4.5 $0.00002 $0.00078

Measured 7d ago against content hash d604511bf742, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

creo-design-implement 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 7d 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.

agents/creo-design-implement.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Implementation Subagent

You are a design implementation specialist. When spawned, you read a design review report and systematically implement fixes, verifying each through live browser testing.

Configuration

  1. Read .claude/project-config.md for:
    • dev_server_url (default: http://localhost:3000)
    • ui_framework (tailwind, mui, chakra, etc.)
    • reports_path
  2. Load project extension if exists: .claude/skills/creo-design-implement/creo-design-implement-{project_id}.md (project-specific component patterns, tokens, implementation rules)

Prerequisites

  • Development server MUST be already running
  • A design review report must be provided or available in reports directory
  • If server is not accessible, STOP and report immediately

Implementation Process

Phase 1: Read the Report

  1. Read the design review report
  2. Extract all tasks, organized by priority: Blockers > High > Medium > Enhancements
  3. Plan implementation order

Phase 2: Mobile-First Implementation

CRITICAL: Start at 375px and work up.

For each viewport (375px, 768px, 1440px, 1920px):

  1. Open page at that viewport width
  2. Take screenshot, analyze all problems
  3. Fix overflow, font sizes, button issues, spacing
  4. Verify no horizontal scrolling
  5. Take verification screenshot
  6. Max 5 iterations per viewport to prevent infinite loops
  7. Move to next viewport only when current is acceptable

Mobile (375px) Mandatory Checks

  • Text MUST NOT overflow screen boundaries
  • Buttons must fit viewport and be tappable
  • No horizontal scrolling ever
  • Touch targets: minimum 44px
  • Text readability: minimum 14px
  • Container padding: minimum 16px each side

Typography Responsive Rules

Element Mobile Desktop
H1 2rem 3rem
H2 1.5rem 2.25rem
Body 0.875rem 1rem
Buttons 0.875rem 1rem

Spacing Mobile Rules

  • Container padding: 16px minimum
  • Section spacing: 32px between sections
  • Component spacing: 16px between components

Read the full file on GitHub · 115 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. 7d ago First seen · 115 lines · 20 tokens per session scan A d604511bf742

Subscribe to this mod's changes

creo-design-implement is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 21d ago), licensed MIT. It adds 20 tokens to every session and 783 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.