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/cleanupnpx skills add ggombee/code-forge --skill cleanupgit 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 | $0.00021 | $0.00664 |
| Opus 5 | $0.00010 | $0.00332 |
| Sonnet 5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade C, and why
cleanup scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf **/test-results/ 2>/dev/null What it actually says
/cleanup
작업 중 생성된 산출물을 정리합니다.
[즉시 실행] 아래 워크플로우를 바로 실행하세요.
사용법
/cleanup → 기본 정리 (design-refs + test-results)
/cleanup --all → 전체 정리 (temp 파일 포함)
/cleanup --dry-run → 삭제 없이 목록만 출력
Step 1: 정리 대상 스캔
Arguments: $ARGUMENTS
--dry-run → 목록만 출력, 삭제 안 함
--all → 전체 대상
없음 → 기본 대상
기본 정리 대상
| 대상 | 패턴 | 생성 시점 |
|---|---|---|
| Figma 스크린샷 | **/.design-refs/*.{png,jpg} |
/start Figma 분석 시 |
| Playwright 결과 | **/test-results/ |
E2E 실행 시 |
| Playwright 리포트 | **/playwright-report/ |
E2E 실행 시 |
--all 추가 대상
| 대상 | 경로 | 생성 시점 |
|---|---|---|
| 계획 파일 | .claude/temp/plan.md |
/start 계획 출력 시 |
| 분석 파일 | .claude/temp/analysis.md |
/start 분석 시 |
| REFLECT flag | .claude/state/reflect.flag |
quality-gate 실패 시 |
| Quality 로그 | .claude/state/quality.jsonl |
quality-gate 실행 시 (보통 GC에 맡김) |
Step 2: 실행
# 기본 정리
find . -path "*/.design-refs/*.png" -delete 2>/dev/null
find . -path "*/.design-refs/*.jpg" -delete 2>/dev/null
rm -rf **/test-results/ 2>/dev/null
rm -rf **/playwright-report/ 2>/dev/null
# --all 추가
rm -f .claude/temp/plan.md 2>/dev/null
rm -f .claude/temp/analysis.md 2>/dev/null
rm -f .claude/state/reflect.flag 2>/dev/null
Step 3: 결과 출력
## /cleanup 결과
| 대상 | 삭제 수 |
|------|---------|
| design-refs | N개 |
| test-results | 삭제됨 |
| playwright-report | 삭제됨 |
| .claude/temp | (--all 시) 삭제됨 |
금지 사항
e2e/.auth/*.json삭제 금지 — 로그인 세션, 수동 삭제만node_modules/.cache건드리지 않음 — 빌드 캐시.policy/건드리지 않음 — 정책 데이터.claude/docs/건드리지 않음 — 정책 문서src/,packages/건드리지 않음 — 소스 코드
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 · 91 lines · 21 tokens per session scan C 5fa644c778ff
cleanup is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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".