Borrowing it
Nothing to install: this file belongs to subicura/purplemux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/subicura/purplemux/main/.claude/skills/2-draft/SKILL.mdgit clone --depth 1 https://github.com/subicura/purplemuxWrote 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/subicura/purplemux/2-draft)<a href="https://agentmods.dev/skills/subicura/purplemux/2-draft"><img src="https://agentmods.dev/badge/skills/subicura/purplemux/2-draft/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/subicura/purplemux/2-draft"><img src="https://agentmods.dev/badge/skills/subicura/purplemux/2-draft.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 | $0.00000 | $0.00746 |
| Opus 5.5 | $0.00000 | $0.00298 |
| Sonnet 5.5 | $0.00000 | $0.00149 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
2-draft 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
spec-draft — 스펙 초안 작성
기능 스펙 초안(spec.md)을 작성합니다. 페이지명 지정 시 해당 페이지만, 미지정 시 전체 일괄 생성합니다. "v1 스펙 초안", "v1 전체 스펙 초안" 요청 시 사용합니다.
Instructions
다음 단계를 순서대로 수행하세요.
1. 버전 확인
- 사용자가 버전을 지정한 경우 해당 버전 사용 (예: v1, v2)
- 미지정 시 현재 진행 중인 버전 사용
2. 요구사항 파악
.specs/v{N}/PRD.md를 읽어 요구사항 파악
3. 프로젝트 가이드 파악
CLAUDE.md의 "참고 문서" 섹션에서docs/가이드 목록 파악
4. 대상 결정
- 페이지명 지정 → 해당 페이지만 생성
- 미지정 →
PRD.md의 페이지 목록 기반으로 전체 일괄 생성
5. spec.md 생성
.specs/v{N}/features/{feature-name}/spec.md를 다음 구조로 생성합니다:
---
page: { page-name }
title: { 페이지 제목 }
route: { 라우트 경로 }
status: DRAFT
complexity: Low | Medium | High
depends_on:
- docs/{관련 가이드}.md
created: { 날짜 }
updated: { 날짜 }
assignee: ''
---
# {페이지 제목}
## 개요
(페이지 목적과 범위)
## 주요 기능
- 기능 항목들
## 하위 문서
- [화면 구성](./detail/ui.md)
- [사용자 흐름](./detail/flow.md)
- [API 연동](./detail/api.md)
## 변경 이력
| 날짜 | 변경 내용 | 상태 |
| ------ | --------- | ----- |
| {날짜} | 초안 작성 | DRAFT |
6. depends_on 연결
- 페이지와 관련된 프로젝트 가이드(
docs/)를depends_on에 연결
7. 일관성 유지
- 기존에 작성된 페이지 스펙이 있으면 스타일을 참고하여 일관성 유지
8. 품질 기준 적용
각 페이지의 주요 기능을 아래 세 축으로 검증하고, 부족한 부분을 spec.md에 반영합니다:
- 빠르다 — 주요 기능 중 성능 전략이 필요한 항목을 식별하고 기능 목록에 포함 (prefetch, 캐싱, 지연 로딩 등)
- 토스급 완성도 — 로딩·빈·에러 상태 처리, 인터랙션 피드백, 전환 애니메이션 등 UX 완성도 항목을 기능에 포함. "동작만 하는" 수준의 기능 정의는 허용하지 않음
- 포브스 TOP 10 기업 수준 — 기능 하나하나가 실무에서 바로 쓸 수 있는 깊이인지 검증. "되긴 되는" 수준이 아닌 "이 정도면 감탄한다" 수준을 목표로 기능 정의
9. 다음 단계 안내
작성 완료 후 다음 안내 메시지를 반드시 출력:
각 feature의 spec.md를 검토한 뒤, frontmatter의 status를 CONFIRMED로 변경하세요.
CONFIRMED된 feature만 `/3-detail`과 `/4-build`에서 처리됩니다.
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 · 94 lines · 0 tokens per session scan A 756d624d2b24
2-draft is a skill published in the GitHub repository subicura/purplemux (61 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 746 tokens. 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
goal-orchestrator
Run a long-lived, headless per-project GOAL orchestrator on hyperpanes — hold a project's goal list, spawn a fable/opus spec agent per goal, have it fan work out to sonnet impl agents via the durable work queue, watchdog wedged agents, rotate across Claude accounts on limits, and loop 24/7. Use when the user wants a…
searchrag-skill
A skill that sends a search query to a script and receives text from a retrieval-augmented generation system, which finds relevant source material before producing an answer.
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.