What is yd-doksam-ui?

A coding-agent guide for creating doksam interfaces according to the project's shared design system. It covers both using the existing component catalogue and adding new components to that catalogue.

Use it when an agent must implement a frontend screen, add reusable UI components, update demonstrations and translations, or run the project's standards checks.

It gives an agent a defined workflow instead of leaving UI choices and validation to guesswork. It also makes the agent check its result against the project's standards.

yd-doksam-ui — Agent for Claude Code by LeeYudok/agents-scaffold

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/LeeYudok/agents-scaffold

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/leeyudok/agents-scaffold/yd-doksam-ui/github.svg)](https://agentmods.dev/agents/leeyudok/agents-scaffold/yd-doksam-ui)

Your own site

<a href="https://agentmods.dev/agents/leeyudok/agents-scaffold/yd-doksam-ui"><img src="https://agentmods.dev/badge/agents/leeyudok/agents-scaffold/yd-doksam-ui/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/leeyudok/agents-scaffold/yd-doksam-ui"><img src="https://agentmods.dev/badge/agents/leeyudok/agents-scaffold/yd-doksam-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 321 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	$0.00061	$0.00321
Opus 5.5	$0.00024	$0.00128
Sonnet 5.5	$0.00012	$0.00064
Haiku 4.5	$0.00006	$0.00032

Measured 13d ago against content hash 7f0c2a52dc14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yd-doksam-ui 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 13d 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.

presets/skills/personal/.claude/agents/yd-doksam-ui.md · 22 lines

What it actually says

yd-doksam-ui Skill 을 작업 계약의 단일 원본으로 사용한다.

작업 시작 시 모드를 먼저 판별한다 — 대상 레포에 lib/showcase/registry.ts 가 없으면 모드 A(소비자), 있으면 모드 B(생산자·카탈로그 확장)다.

모드 A: ui.doksam.com 이 SSOT 다. /llms.txt 로 카탈로그를 live 확인하고, 브랜드 프로필 확정 → 레지스트리 설치(재발명 금지) → 규칙 준수 구현 순서를 따른다.
모드 B: 레포의 lib/rules-markdown.ts 가 규칙 원문이다. 레지스트리 등록·데모· i18n 4개 로케일·배포 산출물 재생성까지 한 묶음으로 끝낸다.

규칙 세부는 Skill 에 있는 것을 따르고 이 파일에 복제하지 않는다.

자가 검증(scripts/check_standards.py 또는 레포 테스트)을 통과한 결과와 함께 산출물을 전달한다.

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.

13d ago First seen · 22 lines · 61 tokens per session scan A 7f0c2a52dc14

Subscribe to this mod's changes

yd-doksam-ui is an agent published in the GitHub repository LeeYudok/agents-scaffold (38 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 321 once invoked, about $0.0002 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 2026-10-25.

Building agents CSS and styling Frontend agent-skills ai-agents ai-coding anthropic boilerplate claude

yd-doksam-ui next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
yd-doksam-uiLeeYudok/agents-scaffold	Agent	38	yesterday	MIT	A	61	Claude Code
seo-specialisttravisjneuman/.claude	Agent	107	yesterday	MIT	A	78	Claude Code
motion-designertravisjneuman/.claude	Agent	107	yesterday	MIT	A	18	Claude Code
designerKevinZai/commander	Agent	6	yesterday	MIT	A	33	Claude Code
ui-ux-designeropencue/cuecards	Agent	7	yesterday	MIT	A	427	Claude Code
bug-hunterdachivadachkoria/claude-code-starter-kit	Agent	4	8mo ago	MIT	A	16	Claude Code
code-reviewerdachivadachkoria/claude-code-starter-kit	Agent	4	8mo ago	MIT	A	12	Claude Code