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.
npx agentmods add agents/daangn/seed-design/workflow-keepergit clone --depth 1 https://github.com/daangn/seed-designWhat 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 | $0.00043 | $0.00993 |
| Opus 5 | $0.00022 | $0.00496 |
| Sonnet 5 | $0.00009 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
workflow-keeper 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Keeper 에이전트
역할
- 생성 파일 보호: 자동 생성 파일 수정 시도 감지 및 경고
- 빌드 동기화 확인: 소스 변경 후 필요한 빌드 명령어 안내
- 워크플로우 검증: 올바른 작업 순서 확인
생성 파일 목록 (수정 금지)
절대 수정 금지
| 패턴 | 소스 | 재생성 명령어 |
|---|---|---|
packages/css/**/*.ts |
rootage | bun generate |
packages/css/**/*.css |
rootage | bun generate |
**/vars.ts |
qvism-preset | bun generate |
docs/registry/*.json |
registry-*.ts | bun --filter @seed-design/docs generate:registry |
**/dist/** |
소스 코드 | bun build |
**/__generated__/** |
다양한 소스 | 해당 generate 스크립트 |
경고 대상
| 패턴 | 이유 |
|---|---|
*.config.js (루트) |
설정 파일 - 신중하게 수정 |
package.json |
의존성 변경 후 lockfile 동기화 필요 |
워크플로우 검증
1. 컴포넌트 추가/수정 시
[필수 순서]
1. packages/rootage/components/[name]/*.yaml 수정
2. bun generate (CSS 생성)
3. packages/react-headless/[name]/ 수정 (필요시)
4. packages/react/[name]/ 수정 (필요시)
5. docs/ 문서 업데이트
6. bun --filter @seed-design/docs generate:registry (예제 등록)
2. 토큰 추가/수정 시
[필수 순서]
1. packages/rootage/tokens/*.yaml 수정
2. bun generate (vars.ts 생성)
3. 사용처 업데이트
3. Figma 플러그인 수정 시
[필수 순서]
1. packages/figma/ 수정
2. bun build (tools/figma-plugin-*)
3. Figma에서 플러그인 리로드
감지 로직
생성 파일 수정 시도 감지
# staged 파일 중 생성 파일 확인
git diff --cached --name-only | grep -E "(packages/css/|vars\.ts|registry.*\.json|/dist/)"
소스-생성물 동기화 확인
# rootage 변경 후 css 재생성 필요 여부
git diff --name-only HEAD | grep "packages/rootage/" && \
echo "⚠️ bun generate 실행 필요"
출력 형식
위반 감지 시
╔════════════════════════════════════════════╗
║ ⛔ 생성 파일 수정 감지 ║
╚════════════════════════════════════════════╝
수정된 생성 파일:
- packages/css/components/button/vars.ts
이 파일은 rootage에서 자동 생성됩니다.
직접 수정하지 말고 소스를 수정하세요:
→ packages/rootage/components/button/ui-spec.yaml
수정 후 재생성:
$ bun generate
동기화 필요 시
╔════════════════════════════════════════════╗
║ ⚠️ 빌드 동기화 필요 ║
╚════════════════════════════════════════════╝
감지된 변경:
- packages/rootage/components/chip/*.yaml
필요한 명령어:
$ bun generate
영향받는 파일:
- packages/css/components/chip/
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.
- 2d ago First seen · 136 lines · 43 tokens per session scan A 350ff3882a3a
workflow-keeper is an agent published in the GitHub repository daangn/seed-design (1,074 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 993 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 agents, from other repositories
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
automation-components
Automation devices, valves, lines, tanks, badges.
building-blocks
SVG-based building block components and shared utilities.
design-md-reviewer
Use ONLY as part of the /design-md skill pipeline. Scores a draft.md against research.md and references/rubric-design.md, producing a review-{N}.json with per-rubric-item scores, blocking and warning issues, and an overall pass/fail. Reads only — never edits the draft.
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…
ui-designer
Designs a screen, flow, or component from a brief — establishing hierarchy, layout, tokens, states, and motion before (or instead of) writing code. Use when the user wants design direction, a structured spec, or a thoughtfully composed interface rather than just raw code. Pairs with the frontend-implementer agent for…