social-capture

social-capture is a skill for Claude Code from kellykampen/agent-skills. It costs 39 tokens per session (4,355 once invoked), scanned A, original, MIT.

A workflow that captures YouTube transcripts and X/Twitter threads from URLs posted in a specific Telegram topic and saves the resulting content to an Obsidian note vault.

In plain words
What is it for?
Use it to extract YouTube transcripts, optionally download videos and frames, capture X posts or threads, and organize them in Obsidian.
Why use it?
It preserves useful social-media content in a searchable personal knowledge base instead of leaving it scattered across platforms.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/greg/Library/Mobile.

Part of the agent-skills plugin — 25 skills, 7 commands shipped together

Good fit Use it to extract YouTube transcripts, optionally download videos and frames, capture X posts or threads, and organize them in Obsidian.

Compare 6 skills from other repositories ↓
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 kellykampen/agent-skills
Claude Code
/plugin install agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 25 skills, 7 commands.

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 social-capture

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kellykampen/agent-skills/social-capture"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/social-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00039 $0.04355
Opus 5 $0.00019 $0.02178
Sonnet 5 $0.00008 $0.00871
Haiku 4.5 $0.00004 $0.00436

Measured 11d ago against content hash e59a8053424b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

social-capture scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/extract_frames.sh, scripts/extract-youtube.py, scripts/save-x-post.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `github.com` | GitHub API via curl | No browser needed, see GitHub section below |
skills/personal/social-capture/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Content Capture

CRITICAL: Obsidian Path

ALWAYS use the iCloud Obsidian vault path:

/Users/greg/Library/Mobile Documents/iCloud~md~obsidian/Documents/Ideaverse/Social/

DO NOT use /Users/greg/Ideaverse/ - that's a stale local copy.

Overview

Automatically captures content from social platforms and saves organized transcripts/content to Obsidian.

Purpose: Extract and archive social media content for later reference.

When to Use

  • YouTube URL posted in Social topic (530)
  • X/Twitter post URL posted in Social topic
  • Any social platform URL in Social topic

Available Scripts

Located in scripts/:

Script Purpose Usage
extract-youtube.py Extract YouTube transcript only python scripts/extract-youtube.py <url>
watch_youtube.py Download video + extract frames + transcript python scripts/watch_youtube.py <url>
extract_frames.sh Extract JPG frames from a video file ./scripts/extract_frames.sh <video_path> --max-frames 30
save-x-post.py Save X/Twitter post to Obsidian python scripts/save-x-post.py <username> <title> (pipe content)

CRITICAL: Acknowledge Immediately — Before Any Processing

The FIRST thing you do when any URL arrives is send an instant acknowledgment to Telegram. Do this before opening any browser, running any script, or doing anything else.

import sys
sys.path.insert(0, '/Users/greg/codebase/telegram-claude')
from telegram_sender import send_to_telegram
send_to_telegram(topic_id=530, text="Got it, processing...")

This fires in under 1 second. Greg should never be left wondering if his message was received.

Workflow

YouTube URL Detection

When a message in Social topic contains a YouTube URL:

  1. Send immediate acknowledgment (see above)
  2. Detect YouTube URL pattern (youtube.com/watch or youtu.be/)
  3. Check for --watch flag (see Watch Mode below)
  4. Run the appropriate script
  5. Read the saved transcript file
  6. Write a proper summary to the channel folder (not transcripts/) — with real content from the transcript, using the frontmatter template below
  7. Reply to Telegram with result — only AFTER both transcript AND summary are saved

Read the full file on GitHub · 478 lines

Files

What ships with it

5 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.

  1. 11d ago First seen · 478 lines · 39 tokens per session scan A e59a8053424b

Subscribe to this mod's changes

social-capture is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 4,355 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens