seed-changeset

seed-changeset is a skill for Claude Code, Codex from daangn/seed-design. It costs 64 tokens per session (1,100 once invoked), scanned A, original, Apache-2.0.

A tool for finding public packages affected by current Git changes and preparing a changeset, which is a file that records package release information.

In plain words
What is it for?
It is for reviewing release candidates, choosing package version bumps, and writing approved Korean changeset messages.
Why use it?
It helps identify which packages need a version update while avoiding duplicate release notes and accidental dependency changes.

Skill for Claude CodeCodex

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 · 1,084 stars · on GitHub

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.

agentmods
npx agentmods add skills/daangn/seed-design/seed-changeset
Any agent
npx skills add daangn/seed-design --skill seed-changeset
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-changeset

README.md
[![agentmods](https://agentmods.dev/badge/skills/daangn/seed-design/seed-changeset.svg)](https://agentmods.dev/skills/daangn/seed-design/seed-changeset)
Your own site
<a href="https://agentmods.dev/skills/daangn/seed-design/seed-changeset"><img src="https://agentmods.dev/badge/skills/daangn/seed-design/seed-changeset.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,100 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00064 $0.01100
Opus 5 $0.00032 $0.00550
Sonnet 5 $0.00013 $0.00220
Haiku 4.5 $0.00006 $0.00110

Measured today against content hash 1f7b092faf1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seed-changeset 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/changeset-plan.test.ts, scripts/changeset-plan.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-changeset/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEED Changeset

현재 diff에서 릴리스 후보를 찾고, 공개 출력에 미치는 영향으로 bump를 정한다. 변경 의미와 bump는 자동으로 추측하지 않는다. 사용자가 패키지별 bump와 메시지를 승인한 뒤에만 .changeset/*.md를 작성한다.

이 스킬은 package.json의 dependency 또는 peer dependency 범위를 수정하지 않는다. 새 기능 때문에 필요한 peer dependency 하한 조정은 Version Changes PR에서 수동으로 처리한다.

후보 계획

저장소 루트에서 읽기 전용 계획 스크립트를 실행한다.

bun skills/seed-changeset/scripts/changeset-plan.ts --base-ref origin/dev

--base-ref에는 seed-change-plan이 선택한 실제 기준 브랜치를 지정한다. 리베이스 전에는 feature 브랜치의 기존 기준을 사용한다. 리베이스 뒤 최종 확인에서는 확정된 targetRef를 사용한다.

결과에서 다음 항목을 확인한다.

  • candidates: 기준 브랜치 이후 변경된 공개 workspace 패키지다. rename은 이전·새 경로를 모두 포함한다. 삭제된 패키지는 기준 브랜치의 package.json으로 복원한다.
  • excluded: private 또는 packages/archive/*라서 changeset 후보에서 제외된 패키지다.
  • coveredBy: 기존 .changeset/*.md가 후보를 이미 다루는지 보여준다. 충분한 파일이 있으면 중복 changeset을 만들지 않는다.
  • reverseDependencies: 변경 후보를 의존하는 공개 workspace 패키지다. 실제 공개 영향이 전파되는지 판단할 때 사용한다.
  • versionChangesReviewCandidates: Version Changes PR에서 peer dependency 하한을 검토할 후보 목록이다. 현재 작업에서는 이 목록의 package.json을 수정하지 않는다.

스크립트는 기준 브랜치 이후 커밋, index, worktree, untracked 파일을 합쳐 보여준다. stacked 변경이 섞였다면 후보의 diff와 커밋 로그를 직접 읽고 이번 작업에 속한 패키지만 남긴다.

bump 확정

version-matrix.md를 읽는다. 후보별 공개 export, 타입, prop, Recipe, 토큰, 렌더 결과, 접근성 동작을 직접 확인하고 major, minor, patch, 안함(제외) 중 하나를 추천한다.

표준 SemVer를 모든 패키지에 동일하게 적용한다. Lynx 패키지도 breaking은 major, 하위 호환 기능 추가는 minor, 버그 수정은 patch다.

역의존 패키지는 실제로 새 기능을 소비하거나 변경을 공개 표면에 노출할 때만 동반 bump 후보가 된다. 의존 관계가 있다는 사실만으로 동반 bump를 만들지 않는다. 이 판단은 changeset 범위를 정하기 위한 것이며 dependency range 편집을 허용하지 않는다.

패키지마다 추천 bump와 근거를 사용자에게 보여주고 확정받는다. 스크립트는 변경 의미, bump, 배포 브랜치를 결정하지 않는다.

메시지 작성과 승인

patterns.md를 읽고 디자인 시스템 소비자 관점의 한국어 메시지를 작성한다. 하나의 사용자 변화가 여러 패키지에 전파되면 한 파일에 묶는다. 서로 독립적인 변화는 파일을 나눈다.

다음 형식으로 초안을 보여준다.

## Changeset 초안

| 패키지 | bump |
| --- | --- |
| @seed-design/react | patch |

```changeset
---
"@seed-design/react": patch
---

사용자에게 보이는 변경을 설명합니다.
```

Read the full file on GitHub · 73 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. today First seen · 73 lines · 64 tokens per session scan A 1f7b092faf1e

Subscribe to this mod's changes

seed-changeset is a skill published in the GitHub repository daangn/seed-design (1,084 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,100 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.

Related

Other skills, from other repositories

omd:release-hygiene

오픈소스 릴리스 위생 루틴. 새 기능/스킬/에이전트를 추가했을 때 (1) 부산물(v1/v2 .bak, source, 로그, scratch dir)이 changeset에 없는지, (2) 문서(README/docs/home)가 동기화됐는지, (3) npm 배포 대상인지(skills/ + files vs .claude local-preview) 판단했는지 체크리스트로 강제. '릴리스 준비', '커밋 전 점검', 'push 전에 정리', '배포 위생', 'release hygiene' 류 트리거. husky pre-commit이 부산물 게이트를 자동 실행.

kwakseongjae/oh-my-design · 157 tokens

release-retrospective

Produce a structured look-back after a major release or deprecation — capturing what the plan got right, what it missed, and what to do differently. Trigger when someone says: release retrospective, post-release review, what went wrong with the release, how did the deprecation go, release post-mortem, retro on the…

murphytrueman/design-system-ops · 89 tokens

version-bump-advisor

Recommend the correct semver bump with reasoning and a generated changelog entry. Trigger when someone says: what version bump, is this a breaking change, semver recommendation, should this be major or minor, version this release, changelog entry, what kind of release is this, or anything about versioning a design…

murphytrueman/design-system-ops · 72 tokens

release

Release designer-skill-mcp to npm with a git tag and GitHub release. Use when the user asks to ship, publish, cut a release, bump version, push tags, or run npm publish for designer-skill-mcp.

PyModel/designer-skill · 50 tokens

changelog-writer

Write external-facing changelog and release note entries in a pithy, tastefully sassy, occasionally clever voice that makes software updates fun to read without burying what actually shipped. Use this skill whenever someone asks to write, draft, or review a changelog entry, release notes, "what's new" post, or product…

ommakes/Skills · 123 tokens

shipping-and-archiving

Use when the user says "done", "ship it", "finish", "complete", "archive", or otherwise indicates the current design is ready to be shipped. Runs final verification (Gate B), archives the CSpec, updates history, extracts a recipe when eligible, and cleans up temp files.

noemuch/bridge · 66 tokens