What is video-analysis?

A skill for analyzing authorized local videos, direct video URLs, or selected public videos from platforms such as YouTube and Bilibili. It extracts video frames and speech transcription for interpretation.

Summarizing video events, reading visible content, and analyzing speech and frames from permitted videos.

It turns moving video and spoken content into timestamped information that a text-based agent can examine.

video-analysis — Skill for Claude Code and Codex by qingyu321

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/qingyu321/Little-Claude

agentmods

npx agentmods add skills/qingyu321/little-claude/video-analysis

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/qingyu321/little-claude/video-analysis/github.svg)](https://agentmods.dev/skills/qingyu321/little-claude/video-analysis)

Your own site

<a href="https://agentmods.dev/skills/qingyu321/little-claude/video-analysis"><img src="https://agentmods.dev/badge/skills/qingyu321/little-claude/video-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qingyu321/little-claude/video-analysis"><img src="https://agentmods.dev/badge/skills/qingyu321/little-claude/video-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 214 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,562 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 warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Data Exfiltration · line 137
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Data Exfiltration · line 160
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.

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	$0.00214	$0.05562
Opus 5	$0.00107	$0.02781
Sonnet 5	$0.00043	$0.01112
Haiku 4.5	$0.00021	$0.00556

Measured 10d ago against content hash e327faca2b0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-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 10d ago.

The scan reads SKILL.md. This mod also ships 18 executable files (scripts/acceleration.py, scripts/analyze_video.py, scripts/asr_worker.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src-tauri/resources/bundled-skills/video-analysis/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Analysis

Use this skill to turn an authorized video file or direct video URL into a timestamped, auditable report. Remote models do not receive the raw MP4/WebM stream. This workflow decodes the video locally, extracts timestamped JPEG frames and speech transcription, and—only after the user answers the mandatory pre-run interview—interprets frames through the route the user chose.

Authorized inputs only

Accept any of:

A local video file that the user is authorized to analyze.
A public, direct http:// or https:// media URL, such as a public .mp4 or .webm resource.
With --allow-platform, a public video-platform page (for example a Bilibili or YouTube watch link). The skill fetches the single public video with yt-dlp and then processes it locally.

Platform-page fetching is deliberately narrow and these limits are not to be weakened:

Public, anonymously accessible videos only. Never send cookies, passwords, or authenticated headers; never log in; never access member-only, private, friend-only, or age-gated content.
No DRM circumvention. DRM-protected streams are refused with an honest error, not decrypted.
Single video per run (--no-playlist); no batch scraping, playlists, or channels.
The user remains responsible for the platform's terms of service and for being authorized to analyze the content.

If a platform video requires login or membership, do not work around it: ask the user for an authorized original file, a direct public export, or the platform's official API/export route. The same applies when a platform fetch fails on stream merging/postprocessing: the authorized fallback is a local file the user downloaded themselves, re-run with --input — never a credential, format, or access-control workaround.

The URL fetcher blocks local, private, link-local, reserved, and metadata-service addresses. Do not weaken these checks.

Workflow

Step 0 — Pre-run route selection (TOKENICODE defaults first)

Before executing ANY analysis, decide the vision route. Never pick a random vendor just because an unrelated key is in the environment (e.g. DEEPSEEK_API_KEY present ≠ permission to use DeepSeek for vision — DeepSeek is text-only). Prefer the TOKENICODE app defaults when they are complete.

Read the full file on GitHub · 259 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 259 lines · 214 tokens per session scan A e327faca2b0c

Subscribe to this mod's changes

video-analysis is a skill published in the GitHub repository qingyu321/Little-Claude (21 stars, last pushed 16d ago), licensed Apache-2.0. It adds 214 tokens to every session and 5,562 once invoked, about $0.0011 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.

Claude Code Creative and media LLM Research ai-agent harness mcp

bento-slides

Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.

Prism-Shadow/penguin-harness · 0 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.

nexus-research-lab/nexus · 65 tokens

video-analysis