seed-token-analysis

seed-token-analysis is a skill for Claude Code, Codex from daangn/seed-design. It costs 70 tokens per session (1,259 once invoked), scanned A, original, Apache-2.0.

A read-only analyzer for one SEED color token, including its definitions, aliases, dependent tokens, component uses, generated outputs, and color contrast. A design token is a named value such as a color that can be reused across an interface.

In plain words
What is it for?
It maps token relationships, checks light and dark values, finds component usage, compares generated surfaces, and tests WCAG contrast against backgrounds.
Why use it?
It shows where a token comes from, how it resolves in each theme, where it is used, and whether generated platform files are missing or incomplete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It maps token relationships, checks light and dark values, finds component usage…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daangn/seed-design/seed-token-analysis
About the project

SEED is a design system that provides shared visual tokens, styling recipes, and UI components for React, iOS, Android, and Lynx, with Figma integration. It is used to build consistent products across platforms; the catalogue add-ons support agents working with its components, tools, documentation, and development workflows.

daangn/seed-design · 1,094 stars · on GitHub · seed-design.io

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.

Any agent
npx skills add daangn/seed-design --skill seed-token-analysis
Clone the repo
git clone --depth 1 https://github.com/daangn/seed-design

Made for: Claude Code, Codex.

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.

agentmods badge for seed-token-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/daangn/seed-design/seed-token-analysis.svg)](https://agentmods.dev/skills/daangn/seed-design/seed-token-analysis)
Your own site
<a href="https://agentmods.dev/skills/daangn/seed-design/seed-token-analysis"><img src="https://agentmods.dev/badge/skills/daangn/seed-design/seed-token-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,259 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01259
Opus 5 $0.00035 $0.00629
Sonnet 5 $0.00014 $0.00252
Haiku 4.5 $0.00007 $0.00126

Measured 2d ago against content hash 9a9673b31521, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seed-token-analysis 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/token-contrast.test.ts, scripts/token-contrast.ts, scripts/token-map.test.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/seed-token-analysis/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEED 토큰 분석

현재 체크아웃의 packages/rootage/color.yaml을 기준으로 색상 토큰의 정의, 연결 관계, 생성 결과와 대비를 확인한다. 스크립트는 파일과 Git 상태를 바꾸지 않는다.

토큰 지도

색상 토큰 하나를 지정한다.

bun skills/seed-token-analysis/scripts/token-map.ts '$color.fg.neutral'

결과 JSON은 다음 순서로 읽는다.

  1. token에서 입력을 정규화한 canonicalstate를 확인한다. statematched, ambiguous, not-found 중 하나다. ambiguouscandidates의 정확한 토큰으로 다시 실행하고, not-found면 비슷한 이름을 임의로 선택하지 않는다.
  2. definition에서 Rootage 원천 경로, 설명과 mode별 원시 값을 확인한다.
  3. resolvedValues에서 각 mode의 원시 값, alias 연결과 최종 색상 값을 확인한다. 한 mode의 값이 없거나 alias를 끝까지 해석하지 못했다면 다른 mode 값으로 대신하지 않는다.
  4. dependentTokens에서 대상 토큰을 직접 참조하는 토큰을 확인한다. 이 목록은 전이 의존 관계나 여러 변경의 결합 영향을 계산하지 않는다.
  5. componentUsages에서 컴포넌트의 변형, 상태, 슬롯, 속성과 근거 경로가 구조화되어 있는지 확인한다.
  6. generatedSurfaces에서 플랫폼과 패키지별 status, 실제 paths, 예상 expectedPaths를 비교한다. missing은 생성 결과를 찾지 못했다는 뜻이며 Rootage 원천을 직접 수정하라는 뜻이 아니다.
  7. warnings를 확인하고 readOnlytrue인지 확인한다.

token.publicNames가 있으면 CSS 변수와 공개 이름을 확인할 수 있다. 생성 파일은 실제 배포 표면을 확인하는 근거로만 사용하고 직접 수정하지 않는다.

대비 검사

전경 토큰 하나와 하나 이상의 배경 토큰을 지정한다. --background--theme은 반복할 수 있고, 반투명 배경 아래의 실제 색상이 필요하면 --backdrop을 추가한다. --theme을 생략하면 light와 dark를 모두 검사한다. 중복 테마는 제거하고 결과는 light, dark 순서로 반환한다.

bun skills/seed-token-analysis/scripts/token-contrast.ts \
  --foreground '$color.fg.warning-contrast' \
  --background '$color.bg.warning-solid' \
  --background '$color.bg.warning-solid-pressed' \
  --theme light \
  --theme dark
bun skills/seed-token-analysis/scripts/token-contrast.ts \
  --foreground '$color.fg.neutral' \
  --background '$color.bg.overlay' \
  --theme light \
  --backdrop '$color.bg.layer-default'

sourcerequest에서 분석한 Rootage 원천과 입력이 맞는지 먼저 확인한다. 결과의 checks는 배경과 테마 조합별로 다음 상태를 반환한다.

  • resolved: alias와 색상 합성을 마치고 WCAG 2.x 대비율과 기준별 통과 여부를 계산했다.
  • unresolved: 해당 mode 값이나 alias를 해석하지 못했다. 다른 테마의 값을 대신 사용하지 않는다.
  • needs-backdrop: 반투명 배경 아래의 색상을 확정할 수 없다. 실제 불투명 backdrop 토큰을 지정해 다시 검사한다.

Read the full file on GitHub · 68 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 68 lines · 70 tokens per session scan A 9a9673b31521

Subscribe to this mod's changes

seed-token-analysis is a skill published in the GitHub repository daangn/seed-design (1,094 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,259 once invoked, about $0.0003 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 2026-09-04.