A video research skill for finding, importing, downloading, indexing, and visually searching online videos and local video files. It works with YouTube, X/Twitter, Instagram, TikTok, generic URLs, and local assets.

Use it to discover videos, inspect sources, save media, create searchable visual indexes, and answer questions about what appears in video footage.

It removes the need to manually search through videos or rely only on spoken transcripts when looking for visual details. It helps an agent locate trends, scenes, slides, charts, whiteboards, and screen content.

vidlens — Skill for Claude Code and Codex by thatsrajan

Install

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.

Any agent

npx skills add thatsrajan/vidlens-mcp --skill vidlens

Clone the repo

git clone --depth 1 https://github.com/thatsrajan/vidlens-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thatsrajan/vidlens-mcp/vidlens/github.svg)](https://agentmods.dev/skills/thatsrajan/vidlens-mcp/vidlens)

Your own site

<a href="https://agentmods.dev/skills/thatsrajan/vidlens-mcp/vidlens"><img src="https://agentmods.dev/badge/skills/thatsrajan/vidlens-mcp/vidlens/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thatsrajan/vidlens-mcp/vidlens"><img src="https://agentmods.dev/badge/skills/thatsrajan/vidlens-mcp/vidlens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 928 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00928
Opus 5	$0.00023	$0.00464
Sonnet 5	$0.00009	$0.00186
Haiku 4.5	$0.00005	$0.00093

Measured 11d ago against content hash fe9d4cdfd1ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vidlens 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 11d 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.

plugins/vidlens/skills/vidlens/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VidLens

Use the VidLens MCP tools for video intelligence work:

Use inspectVideoSource first when the input could be a YouTube ID, social video URL, generic URL, or local video file.
Use searchSocialTrends when the user wants to search social platforms for trends, posts, reels, or cross-platform signal around a topic.
Use searchVideoSources for discovery. It searches YouTube natively, local assets locally, and explains fallback paths for social/web platforms.
Use importVideoSources to store one or more URLs or local files as local VidLens assets.
Use downloadAsset for explicit storage of a video/audio/thumbnail asset without visual indexing.
Use indexVisualContent after import/download to build Apple Vision OCR/similarity and optional Gemini visual embeddings.
Use searchVisualContent when the user asks what was shown in a video, slide, chart, whiteboard, screen recording, or local clip.

Use the cheapest available path automatically. An API key is an uplift, not a prerequisite.

Call recallWorkspace and reuse an existing transcript or media asset.
For an exact public X status, Instagram reel/post, or TikTok video URL, call inspectVideoSource, then transcribeVideoSource or importVideoSources. VidLens tries yt-dlp anonymously first, then configured cookies and local/selected STT.
If the user supplied a creator/topic instead of a URL, call searchVideoSources. Accept only concrete post/video URLs; never pass a profile, explore, hashtag, or popular page to import.
If discovery is incomplete or the platform page blocks anonymous inspection, use an available Browser/Chrome tool to open the public page or signed-in session and collect the canonical post URL plus visible author, caption, date, duration, and engagement. Prefer Browser/Chrome to Computer Use because it exposes page structure; use Computer Use only when no browser tool is available.
Pass the canonical URL back to VidLens. If the browser can legitimately save/download the video, import that local file. Do not claim that browser visibility guarantees media export, and do not treat a CDN/blob URL as durable provenance.
When SCRAPECREATORS_API_KEY, Brave, or SerpAPI is configured, use it automatically for scale, repeatability, or unattended discovery. Keep the no-key route available for individual videos.

Read the full file on GitHub · 58 lines

Changes

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.

11d ago First seen · 58 lines · 46 tokens per session scan A fe9d4cdfd1ce

Subscribe to this mod's changes

vidlens is a skill published in the GitHub repository thatsrajan/vidlens-mcp (36 stars, last pushed 20d ago), licensed MIT. It adds 46 tokens to every session and 928 once invoked, about $0.0002 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.

Creative and media Research

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

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…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens