Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sodam-ai/SoDam-Design-Kit/plugin install sodam-design-kitWrote 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/commands/sodam-ai/sodam-design-kit/open)<a href="https://agentmods.dev/commands/sodam-ai/sodam-design-kit/open"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-design-kit/open/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/commands/sodam-ai/sodam-design-kit/open"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-design-kit/open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.00660 |
| Opus 5 | $0.00018 | $0.00330 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
open scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/sodam-design-kit:open
목적
지금까지의 검증 이력(PASS/FAIL·스크린샷·판정 사유)을 브라우저에서 열람하고, 필요하면 재검증을 트리거합니다. .design-kit/에 아무것도 새로 쓰지 않습니다(열람 전용 + 재검증 트리거).
실행
node "${CLAUDE_PLUGIN_ROOT}/scripts/dashboard-server.mjs" --project <현재 프로젝트 경로>
- 이미 대시보드가 떠 있으면(같은 프로젝트) 새로 띄우지 않고 그 주소를 그대로 재사용합니다.
- 처음이면 127.0.0.1의 빈 포트(4570~4590 대역)에 서버를 백그라운드로 띄우고, 브라우저를 자동으로 엽니다.
- 콘솔에 출력된 주소(
http://127.0.0.1:포트)를 사용자에게 그대로 안내하세요 — 브라우저가 자동으로 안 열렸을 때 직접 열 수 있도록. - 명령이 즉시 반환됩니다(서버가 계속 떠 있어도 이 명령 실행 자체는 바로 끝남 — 터미널이 멈추지 않습니다).
종료
node "${CLAUDE_PLUGIN_ROOT}/scripts/dashboard-server.mjs" --stop --project <현재 프로젝트 경로>
- 사용자가 "대시보드 꺼줘" 등으로 요청하면 이 명령을 실행하세요. 서버가 없으면 조용히 "실행 중인 대시보드가 없습니다"라고만 안내합니다.
- 껐다가 다시
/sodam-design-kit:open을 실행하면 새 프로세스로 다시 뜹니다.
보안 (자동으로 지켜짐 — 별도 조치 불필요)
- 127.0.0.1 전용 바인딩(외부 네트워크에서 접근 불가)
- 실행마다 새 토큰 발급(
.design-kit/.api-token, gitignore 대상) - 판정서·콘솔 에러 등 표시 데이터는 전부 이스케이프(저장형 XSS 방어)
- 대시보드는 검증 상태를 직접 조작하지 않음 — "재검증" 버튼은 파이프라인과 동일한 코어 엔진을 호출할 뿐, 판정은 항상 실제 재검증 결과를 따름
실측 함정
.design-kit/.dashboard.json에 실행 중인 서버의 pid·port·url이 기록됩니다(토큰은 안 들어있음 —.api-token에만 존재). 지우지 마세요 —--stop이 이 파일로 서버를 찾습니다.- 브라우저 자동 실행이 실패해도(방화벽 등) 명령 자체는 실패하지 않습니다 — 콘솔에 출력된 주소를 수동으로 열면 됩니다.
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.
- 9d ago First seen · 35 lines · 36 tokens per session scan A 3675e32ed3e7
open is a command published in the GitHub repository sodam-ai/SoDam-Design-Kit (9 stars, last pushed 5d ago), licensed Apache-2.0. It adds 36 tokens to every session and 660 once invoked, about $0.0002 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.
Other commands, from other repositories
wp-responsive-check
Responsive validation — screenshots at 5 viewports, checks for layout issues.
ios-test
Bu komut iOS/SwiftUI uygulamasini derleyip simulator'da acarak computer use ile gorsel test yapar.
test
Verification suite that checks all integrations, skills, and commands are working correctly. Organized by pillars.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.