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 skills/ggombee/code-forge/e2enpx skills add ggombee/code-forge --skill e2egit clone --depth 1 https://github.com/ggombee/code-forgeWhat 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 | $0.00072 | $0.03613 |
| Opus 5 | $0.00036 | $0.01806 |
| Sonnet 5 | $0.00014 | $0.00723 |
| Haiku 4.5 | $0.00007 | $0.00361 |
Grade A, and why
e2e 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 yesterday.
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 — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/e2e — E2E Forge Loop
화면 단위 E2E 테스트를 자동으로 도출, 생성, 실행합니다. Forge Loop로 모든 테스트가 통과할 때까지 자율 반복하며, 단계별 에스컬레이션으로 다양한 전략을 시도합니다.
설계 문서: @../../docs/e2e-forge-loop-design.md
[즉시 실행] 아래 워크플로우를 바로 시작하세요.
사용법
/e2e src/pages/order/ # 페이지 경로 기반
/e2e --figma https://... # Figma 디자인 기반
/e2e --all # 전체 라우트 스캔
/e2e e2e/order-flow.spec.ts # 기존 spec 재실행 (Forge Loop)
| 옵션 | 설명 |
|---|---|
--figma [URL] |
Figma 화면에서 사용자 흐름 추출 |
--all |
전체 라우트 스캔 → 화면별 spec 생성 |
--skip-gen |
코드 생성 스킵, 기존 spec만 Forge Loop 실행 |
--max-retry N |
Stage별 최대 재시도 횟수 (기본 3) |
전제 조건
- Playwright 설치 필수. 미설치 시 → "
/setup-e2e를 먼저 실행하세요" 안내 - 개발 서버 실행 중 (또는
playwright.config.ts에webServer설정)
# 전제 조건 체크
ls node_modules/@playwright/test 2>/dev/null || echo "NO_PLAYWRIGHT"
ls playwright.config.* 2>/dev/null || echo "NO_CONFIG"
Phase 1: 테스트 케이스 도출
Arguments: $ARGUMENTS
입력 분기:
| 입력 | 동작 |
|---|---|
페이지 경로 (src/pages/...) |
해당 페이지 컴포넌트 + 라우트 분석 |
Figma URL (--figma) |
Figma MCP로 화면 분석 → 사용자 흐름 추출 |
--all |
전체 라우트 파일 스캔 → 화면 목록 도출 |
기존 spec 파일 (e2e/*.spec.ts) |
Phase 1~2 스킵 → Phase 3 직행 |
1-1. 기존 E2E 케이스 확인
ls e2e/*.spec.ts 2>/dev/null | wc -l
- 있으면 → "기존 {N}개 spec이 있습니다. 기존 케이스로 실행할까요, 새로 도출할까요?"
- 없으면 → 도출 진행
1-2. Figma 기반 도출 (--figma 있을 때)
mcp__figma__get_metadata({ fileKey, nodeId })
mcp__figma__get_screenshot({ fileKey, nodeId })
스크린샷에서 추출:
- 화면 상태 (초기/로딩/에러/빈 상태/데이터 있음)
- 사용자 인터랙션 (버튼, 폼 입력, 네비게이션)
- 화면 간 전이 흐름
1-3. 코드 기반 도출 (경로만 있을 때)
# 라우트 구조 분석
grep -r "path:" src/routes/ 2>/dev/null || grep -r "getServerSideProps\|getStaticProps" src/pages/
# 페이지 컴포넌트 분석
# - 폼 필드, 버튼, 조건부 렌더링, API 호출 추출
1-4. BDD 시나리오 출력 (사용자 확인)
## E2E 테스트 시나리오
### 페이지: 주문 목록 (/orders)
| # | 시나리오 | 사전 조건 | 기대 결과 |
|---|---------|----------|----------|
| 1 | 주문 목록이 정상 로드된다 | 로그인 상태 | 테이블에 주문 N건 표시 |
| 2 | 검색 필터로 주문을 찾는다 | 주문 데이터 존재 | 필터링된 결과 표시 |
| 3 | 주문 상세로 이동한다 | 주문 1건 이상 | 상세 페이지 렌더링 |
| 4 | 빈 상태가 올바르게 표시된다 | 주문 0건 | 빈 상태 메시지 표시 |
이 시나리오로 진행할까요? [Y/N/수정]
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.
- yesterday First seen · 426 lines · 72 tokens per session scan A 4034beaf2705
e2e is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 3,613 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mintlify-preview
Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".