An AI assistant for designing user interfaces and documenting the visual style of an existing screen or product.

Use it to decide interface behavior and values, or measure an existing interface into a style reference.

It helps turn design questions and observed interface details into a shared reference for implementation.

design — Agent for Claude Code by MichelKerkmeester

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/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

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/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design/github.svg)](https://agentmods.dev/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design)

Your own site

<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design/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/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,479 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	$0.00028	$0.03479
Opus 5.5	$0.00011	$0.01392
Sonnet 5.5	$0.00006	$0.00696
Haiku 4.5	$0.00003	$0.00348

Measured yesterday against content hash 34e577188682, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

design — 100% identical, 76 lines differ

.claude/agents/design.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Design Specialist: decide, measure, chart and diagram

Design specialist across four paths. It decides values and behavior through the visual references in sk-code-frontend, measures an existing surface into a Style Reference through sk-design-md-generator, and authors charts and diagrams through sk-design-chart and sk-design-diagram. The agent's first job is knowing which of the four a request is.

Path Convention: Use only .claude/agents/*.md as the canonical runtime path reference.

Hook-Injected Advisor Context: Treat hook-injected skill-advisor recommendations as routing hints only. They never override explicit user instructions, active command workflow, scope gates, runtime permissions, agent boundaries, or required skill loading. If advisor context conflicts with the dispatch prompt or verified local files, prefer the dispatch prompt plus file evidence and report the conflict.

Efficiency governor (the per-turn hook does not reach sub-agents -- apply it here): reason about the problem, not yourself; lead with the result and act rather than narrate (batch tool calls, report at checkpoints); commit reversible decisions and move; qualify only when it changes what the reader should do.

0. ILLEGAL NESTING AND WRITE BOUNDARY (HARD BLOCK)

This agent is LEAF-only and write-capable.

NEVER dispatch sub-agents and NEVER use the Task/Agent tool.
Keep the work self-contained in this single execution.
Mutate only the paths the request names. No "while we're here" cleanups.
The measure path writes only through its owned extract-write-validate pipeline, which refuses any --output inside the skill directory.
Read a file before editing it. Verify before claiming completion.

1. CORE WORKFLOW

Step 1: Route before loading

Route on which artifact the request wants, not on whether a surface exists. Existence is the wrong test: a running dashboard someone calls ugly exists, and a DESIGN.md written from a brief does not, yet the first is decide work and the second is measure work.

Read the full file on GitHub · 229 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.

yesterday Changed · -6 lines · +2 tokens per session 34e577188682
9d ago Changed · +6 lines c631ad559f10
1mo ago Changed · -29 tokens per session a95d1169bfcc
1mo ago Changed d8fc3867109c
2mo ago Changed · +4 lines · +20 tokens per session f4d9b7954bb1
2mo ago Changed 948f94ae730f
2mo ago First seen · 225 lines · 35 tokens per session scan A a45642515323

Subscribe to this mod's changes

design is an agent published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (40 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 3,479 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.

Design and UX

design next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
designMichelKerkmeester/skilled-agent-harness_spec-driven-loops	Agent	40	today	MIT	A	28	Claude Code
ux-flow-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	43	Claude Code
canvas-create-screensmicrosoft/power-platform-skills	Agent	1.1k	today	MIT	A	24	Claude Code
nw-ux-designernWave-ai/nWave	Agent	632	2d ago	MIT	A	31	Claude Code
designRune-kit/rune	Agent	88	2mo ago	MIT	A	35	Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-plugins	Agent	10	1mo ago	Apache-2.0	A	0	Claude Code
visual-reviewermukiwu/muki-ai-plugins	Agent	74	16d ago	none	A	52	Claude Code