claude-real-video is a local command-line tool that helps Claude or another language model inspect video by combining selected video frames with a transcript. It is for developers who want an AI agent to answer questions about videos from URLs or local files while reducing redundant visual input. The catalogue add-ons extend agent workflows around the tool.
Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/huangchihhungleo/claude-real-video/personal-skill-backup)<a href="https://agentmods.dev/skills/huangchihhungleo/claude-real-video/personal-skill-backup"><img src="https://agentmods.dev/badge/skills/huangchihhungleo/claude-real-video/personal-skill-backup/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/huangchihhungleo/claude-real-video/personal-skill-backup"><img src="https://agentmods.dev/badge/skills/huangchihhungleo/claude-real-video/personal-skill-backup.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 | $0.00087 | $0.01186 |
| Opus 5 | $0.00044 | $0.00593 |
| Sonnet 5 | $0.00017 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
claude-real-video 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-real-video / crv Pro — 幫 Leo 看影片
Leo 本機裝的是 Pro 版 0.5.0（~/Projects/crv-pro/.venv/bin/crv-pro，PATH 有的環境直接 crv-pro）。
什麼時候用
Leo 給影片（網址或檔案路徑）問內容、要摘要、拆對標 reel、問「他怎麼講/怎麼拍/觀眾為什麼買單」時。
指令怎麼選（0.5.0）
| Leo 的話聽起來像 | 指令 |
|---|---|
| 「這在講什麼」「幫我摘要」「他說的是真的嗎」 | crv-pro "<src>" -o out --mode watch |
| 「怎麼做的」「拆解」「為什麼會紅」「能學嗎」 | crv-pro "<src>" -o out --mode creator |
| 「完整分析」或意圖不明 | crv-pro "<src>" -o out --mode full |
Leo 有具體問題就加 --why "<他的原話>"。
--senses= 五感全開：聲音事件、語氣曲線、情緒、手勢/表情、畫面標籤（首次跑下載模型 ~2.7GB，之後 86 秒影片約 40 秒）- 只要單一感官：
--prosody/--audio-events/--emotion/--gesture/--scene-labels --lens content|creator|both（預設 both）決定 MANIFEST 教讀的 AI 往哪個方向分析- 長影片加
--max-frames 60；無語音影片--no-transcribe - IG/TikTok 這類要登入的平台：先把 cookie JSON 轉 Netscape 格式再走
--cookies（2026-07-05 實測可直接抓 IG reel，這才是正路）：
這條也失敗才退 [[reference_ig_post_full_read]] 的 IG 內部 API 手動下載python3 -c "import json; ck=json.load(open('/Users/leo/Projects/auto-post/browse-cookies/kanisleo328-threads.json')); cs=ck if isinstance(ck,list) else ck['cookies']; print('# Netscape HTTP Cookie File'); [print('\t'.join([c['domain'],'TRUE' if c['domain'].startswith('.') else 'FALSE',c.get('path','/'),'TRUE',str(int(c.get('expirationDate',2e9))),c['name'],c['value']])) for c in cs if 'instagram' in c.get('domain','')]" > /tmp/ig-cookies.txt crv-pro "<reel url>" --cookies /tmp/ig-cookies.txt --mode full
讀輸出的順序
MANIFEST.txt— 開頭有 lens 指令區塊照著做；含幀清單、motion 區塊、perception timeline（聲音/語氣/情緒/手勢/畫面事件，各帶秒數與信心分數）、逐字稿grids/九宮格連續幀；要看細節才開frames/*.jpg（讀前縮 1500px 內）perception.json— 完整感知資料（被門檻藏掉的低信心事件在這）
⚠️ 鐵則（2026-07-05 Leo QA 定的）
-
逐字稿必須從頭讀到尾才准出報告（2026-07-16 Leo 抓到抽樣讀導致講錯出處＋漏掉全片最有哏的三個細節）：transcript.txt 全文讀完再寫內容拆解，抽樣只能用來對秒數，不能替代理解
-
感知標籤是線索不是定論：引用前對照幀和逐字稿交叉驗證（MANIFEST 開頭也這樣教）；情緒模型會把「正常有力的語氣」誤讀成 angry——非中性情緒信心 <0.75 已被藏，露出的也要驗
-
拆對標/做復刻前必看 motion 節奏表（cuts/min、中位鏡頭長、運鏡分佈），別憑感覺（詳 [[reference_reel_clone_pipeline]]）
-
回答引用具體秒數和數據，不籠統
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.
- 13d ago First seen · 53 lines · 87 tokens per session scan A e280b916dfc5
claude-real-video is a skill published in the GitHub repository HUANGCHIHHUNGLeo/claude-real-video (2,132 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,186 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
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.