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 skills add daeryundf2-prog/LAZYANTIGRAVITY --skill media-analysisgit clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITYWrote 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/daeryundf2-prog/lazyantigravity/media-analysis)<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/media-analysis"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/media-analysis/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/daeryundf2-prog/lazyantigravity/media-analysis"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/media-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.00736 |
| Opus 5.5 | $0.00033 | $0.00294 |
| Sonnet 5.5 | $0.00016 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
media-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 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
media-analysis
음성·이미지·영상 파일을 분석할 때 이 스킬을 사용한다. 모든 도구는 media MCP 서버의
로컬 바이너리(ffmpeg/ffprobe/tesseract/whisper.cpp/yt-dlp)로 동작하며, 결과물은
.lazyantigravity/media/ 아래에 저장된다.
Pipeline (이 순서를 지켜라)
- Probe 먼저:
media_probe로 길이·스트림·코덱을 확인한다. 분석 전략이 여기서 결정된다. - YouTube라면 자막 우선:
media_youtube(subaction: "subtitles")— 자동 자막이 있으면 전사(whisper)보다 빠르고 정확하다. 자막이 없으면subaction: "audio"→media_transcribe. - 영상 내용 분석:
media_frames로 프레임을 추출한 뒤, 반환된 이미지 경로를 호스트 네이티브 비전으로 직접 읽는다 (프레임 수는 maxFrames로 제한, 기본 10). - OCR: 이미지 속 텍스트는
media_ocr(기본 lang: kor+eng). - 전사:
media_transcribe— whisper.cpp ggml 모델 경로가 필요하다 (model 파라미터 또는 LAZYANTIGRAVITY_WHISPER_MODEL).
도구별 전제 조건
| 도구 | 바이너리 | 미설치 시 |
|---|---|---|
| media_probe / media_frames | ffmpeg, ffprobe | "NOT INSTALLED" + 설치 안내 반환 |
| media_ocr | tesseract (kor+eng traineddata) | 동일 |
| media_transcribe | whisper.cpp + ggml 모델 파일 | 동일 |
| media_youtube | yt-dlp + LAZYANTIGRAVITY_MEDIA_NETWORK=1 | 게이트 에러 (네트워크 옵트인) |
설치 (macOS): brew install ffmpeg tesseract tesseract-lang yt-dlp,
whisper.cpp는 github.com/ggml-org/whisper.cpp 빌드 또는 brew install whisper-cpp.
바이너리 경로가 특수하면 LAZYANTIGRAVITY_<도구>_BIN 환경변수로 지정한다.
규칙
- 입력 경로는 반드시 워크스페이스 상대경로 (절대경로·
~거부). - 대용량 영상은
media_frames의 maxFrames를 먼저 낮춰 시도하고, 필요한 구간만 intervalSec을 조정해서 정밀 추출한다. - 전사·OCR 결과 파일(
.txt)은 증거로 체크포인트에 첨부할 수 있다. - 유튜브 다운로드는 저작권과 서비스 약관 범위 내에서만 사용한다.
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 · 45 lines · 82 tokens per session scan A 4e010047e37a
media-analysis is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 7d ago), licensed MIT. It adds 82 tokens to every session and 736 once invoked, about $0.0003 per session on Opus 5.5. 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
top-down-typescript
TypeScript and JavaScript coding style conventions, centered on top-down narrative ordering (caller first, helpers below) and functions over classes. Read before writing or reviewing TypeScript/JavaScript code, including code inside a spec or a plan.
loom-typescript
TypeScript language expertise for type-safe, production-quality code.
ai-provider-anthropic-sdk
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.