Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TOKTOKHAN-DEV/agent-companynpx agentmods add skills/toktokhan-dev/agent-company/build-screenWrote 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.
[](https://agentmods.dev/skills/toktokhan-dev/agent-company/build-screen)<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/build-screen"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/build-screen/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.
<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/build-screen"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/build-screen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00002 | $0.00698 |
| Opus 5.5 | $0.00001 | $0.00279 |
| Sonnet 5.5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
build-screen 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 1mo 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.
What it actually says
build-screen
1. 명세를 연다
ls specs/
만들 화면이 「화면」 표에 있는지, 「수용 기준」에 관련 항목이 있는지 확인한다.
없으면 만들지 않는다. spec-writer 가 먼저 필요하다고 보고한다.
2. 화면 파일을 만든다
apps/miniapp/src/screens/<Name>Screen.tsx.
import { Button, Text } from '@toss/tds-mobile';
import { navigate } from '../router.tsx';
export function <Name>Screen(): JSX.Element {
return (
<main style={{ padding: '24px 20px', display: 'flex', flexDirection: 'column', gap: 16 }}>
{/* 제목 · 본문 · 액션 */}
</main>
);
}
레이아웃 여백 정도는 인라인 스타일로 두되, 색·타이포·컴포넌트는 TDS 를 쓴다.
Text 의 typography 와 color, Button 의 size 와 style 을 쓰고 직접 색을 넣지 않는다.
3. 세 가지 상태를 만든다
빈 상태 · 로딩 · 실패. 명세에 적힌 문구를 그대로 쓴다.
if (isLoading) return <LoadingView />;
if (error != null) return <ErrorView onRetry={retry} />;
if (items.length === 0) return <EmptyView />;
실패 화면에는 재시도 수단이 있어야 한다. "오류가 발생했습니다" 만 띄우고 끝내지 않는다.
4. 라우트에 등록한다
apps/miniapp/src/App.tsx 의 routes 배열에 추가한다.
const routes: Route[] = [
{ path: '/', element: () => <HomeScreen /> },
{ path: '/<path>', element: () => <<Name>Screen /> },
];
첫 항목이 진입 화면이자 폴백이다. 순서를 바꾸지 않는다.
여러 ui-builder 가 동시에 돌고 있다면 이 파일에서 충돌한다. 라우트 등록만 한 명이 몰아서
하거나 순서를 정한다.
5. 이탈 경로를 확인한다
- 하위 화면이면 → 홈으로 돌아가는 수단
- 첫 화면이면 →
Screen.close()로 미니앱을 닫는 수단
import { closeMiniApp } from '../App.tsx';
완료 확인
pnpm typecheck
pnpm preflight
tds · light-only · no-eval 규칙에 걸리면 고치고 다시 돌린다.
출력
- 만든 화면과 경로
- 충족한 수용 기준 (명세의 체크박스 기준)
- 사람이 눈으로 봐야 하는 것 (2초 반응, 실기기 레이아웃 등)
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.
- 1mo ago First seen · 90 lines · 2 tokens per session scan A 602f1e3b6e54
build-screen is a skill published in the GitHub repository TOKTOKHAN-DEV/agent-company (85 stars, last pushed 2mo ago), licensed MIT. It adds 2 tokens to every session and 698 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
ui-designer
Aura - Senior UI/UX Design Architect with 12+ years creating premium digital experiences. Use when designing landing pages, dashboards, mobile apps, design systems, component libraries, or brand-aligned UI. Specializes in React/Tailwind/Framer Motion prototypes, responsive design, micro-interactions, and…
bf-ui
Use when a rebuild must keep the legacy UI's screens and visual theme.
ux-researcher
UX Researcher (/ux) — the research side of UX: user interviews, surveys, usability testing, personas, journey maps, information architecture, card sorting, jobs-to-be-done, and turning findings into prioritized design requirements. Use when you need to understand users, validate a concept, define IA/navigation, plan…
prototype
Answer one open question from a requirement brief with a throwaway prototype (原型) — logic, UI, or a feature slice — then record the answer, the evidence, and the prototype's commit in the brief and remove the prototype in the next commit. Use when a brief's Open Questions entry is marked needs prototype, or the user…
options
Present multiple design options as a vertical stack of anchored turns.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.