agentmods.dev

analyze-social

analyze-social is a skill for Claude Code from Shivang0/social-vision. It costs 106 tokens per session (1,108 once invoked), scanned A, original, MIT.

A tool for understanding videos and posts from Instagram, TikTok, YouTube, YouTube Shorts, or X, as well as local video files. It produces readable material such as sampled images, captions, and a transcript.

In plain words
What is it for?
Use it to inspect the visuals, caption, and spoken content of a social post or local MP4 or MOV file.
Why use it?
It saves you from watching and manually transcribing a video before you can analyze what it contains.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the social-vision plugin — 1 skill, 1 command shipped together

not rated 1repo 2mo ago A scan 106 tokens original MIT

Good fit Use it to inspect the visuals, caption, and spoken content of a social post or local MP4 or MOV file.

Compare 6 skills from other repositories ↓
View source ↗ Shivang0/social-vision
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Shivang0/social-vision
Claude Code
/plugin install social-vision

Made for: Claude Code.

Or install social-vision, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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.

agentmods badge for analyze-social

README.md
[![agentmods](https://agentmods.dev/badge/skills/shivang0/social-vision/analyze-social/github.svg)](https://agentmods.dev/skills/shivang0/social-vision/analyze-social)
Your own site
<a href="https://agentmods.dev/skills/shivang0/social-vision/analyze-social"><img src="https://agentmods.dev/badge/skills/shivang0/social-vision/analyze-social/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.

agentmods 80×15 button for analyze-social

Your own site · 80×15
<a href="https://agentmods.dev/skills/shivang0/social-vision/analyze-social"><img src="https://agentmods.dev/badge/skills/shivang0/social-vision/analyze-social.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.01108
Opus 5 $0.00053 $0.00554
Sonnet 5 $0.00021 $0.00222
Haiku 4.5 $0.00011 $0.00111

Measured 10d ago against content hash 7865b3a67efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

analyze-social 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.

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.

skills/analyze-social/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Social (watch a video/post for the user)

Overview

Turns a social link (or local video) into material you can actually read: sampled frames you view with native vision, a full transcript, and the post's caption. Then you write a thorough breakdown. A bundled cross-platform Python pipeline does the fetching/transcribing; you do the understanding.

When to use

  • The user pastes an Instagram / TikTok / YouTube / YouTube Shorts / X (Twitter) URL.
  • The user gives a local video file path.
  • The user asks to watch / analyze / transcribe / summarize a video, reel, short, or post.

Workflow

  1. Run the pipeline (use the Bash tool):

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/analyze.py" "<URL or local file path>"
    • The first run auto-installs its tools (yt-dlp, gallery-dl, a Whisper engine, and ffmpeg). Tell the user this one-time setup can take a few minutes and may ask them to approve installs. Subsequent runs are fast.
    • Useful flags: --no-transcribe (frames + caption only, faster), --target-frames N, --lang <code>.

  2. Read the printed result block. It ends with ERROR_CODE, BUNDLE, TYPE, FRAMES, TRANSCRIPT. Handle the error code:

    • NEEDS_LOGIN → the content is private/login-walled. Ask the user: "Which browser are you logged into that platform on? (chrome / firefox / safari / edge / brave)" then re-run with --cookies-from-browser <browser>. Only do this when the user has opted in — reading browser cookies is sensitive and may trigger a keychain prompt.
    • RATE_LIMITED → tell them to wait a few minutes, or retry with --cookies-from-browser to use their logged-in session.
    • SETUP_FAILED → show the MESSAGE (usually a one-line command to install ffmpeg) and offer to run it.
    • none → success, continue.

  3. Load the bundle. Read manifest.json (the contract) from the BUNDLE path, then:

    • Read meta.txt (caption + metadata) and, if present, transcript.txt.
    • View the frames with the Read tool — a spread across the timeline (first, several middle, last) for video; all slides in order for an image carousel. You read on-screen text/captions directly from the frames; no separate OCR.

Read the full file on GitHub · 61 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.

  1. 10d ago First seen · 61 lines · 106 tokens per session scan A 7865b3a67efe

Subscribe to this mod's changes

analyze-social is a skill published in the GitHub repository Shivang0/social-vision (1 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 1,108 once invoked, about $0.0005 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 2026-08-31.

Claude CodeCreative and mediaclaudeclaude-code-pluginclaude-plugininstagramtiktok
Related

Other skills, from other repositories

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens

video-content

Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…

cbrock84/headcount · 89 tokens

visual-content

Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…

cbrock84/headcount · 72 tokens

demo-shorts

Cut a vertical 9:16 Short (YouTube Shorts, Instagram Reels, TikTok) from a demo video project in one of four named styles — listicle (rapid numbered beats), cohost (split screen with presenter), flashcard (typographic interstitials), or glide (immersive pan). Use when the user asks for a "short", "shorts", "vertical…

mrieck/demoday-claude-plugin · 106 tokens

demo-script

Writing the script and shot list for a demo video, and the demo.json manifest schema. Use when planning what a product video should say and show, writing voiceover narration, structuring scenes, or editing demo.json.

mrieck/demoday-claude-plugin · 47 tokens

demo-assembly

Assembling and rendering a demo video with Remotion and ffmpeg — the timeline, transitions, captions, zoom-to-click, audio ducking, and diagnosing a render that comes out wrong. Use when rendering the final video, customising its look, or fixing timing, black frames or missing audio.

mrieck/demoday-claude-plugin · 64 tokens