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.
npx skills add felipenalves/InvOS --skill youtube-summarizergit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/youtube-summarizer)<a href="https://agentmods.dev/skills/felipenalves/invos/youtube-summarizer"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/youtube-summarizer/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/felipenalves/invos/youtube-summarizer"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/youtube-summarizer.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 | $0.00072 | $0.01843 |
| Opus 5 | $0.00036 | $0.00922 |
| Sonnet 5 | $0.00014 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
youtube-summarizer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
GROQ_RESPONSE=$(curl -s https://api.groq.com/openai/v1/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
This skill extracts transcripts from YouTube videos and generates comprehensive, verbose summaries using the STAR + R-I-S-E framework. It validates video availability, extracts transcripts using the youtube-transcript-api Python library, and produces detailed documentation capturing all insights, arguments, and key points.
The skill is designed for users who need thorough content analysis and reference documentation from educational videos, lectures, tutorials, or informational content.
When to Use This Skill
This skill should be used when:
- User provides a YouTube video URL and wants a detailed summary
- User needs to document video content for reference without rewatching
- User wants to extract insights, key points, and arguments from educational content
- User needs transcripts from YouTube videos for analysis
- User asks to "summarize", "resume", or "extract content" from YouTube videos
- User wants comprehensive documentation prioritizing completeness over brevity
Step 0: Discovery & Setup
Before processing videos, validate the environment and dependencies:
# Check if youtube-transcript-api is installed
~/.venvs/youtube-summarizer/bin/python3 -c "import youtube_transcript_api" 2>/dev/null
if [ $? -ne 0 ]; then
echo "⚠️ youtube-transcript-api not found"
# Offer to install
fi
# Check Python availability
if ! command -v python3 &>/dev/null; then
echo "❌ Python 3 is required but not installed"
exit 1
fi
# Check Groq key (resumo sem tokens Claude)
if [ -z "$GROQ_API_KEY" ]; then
echo "⚠️ GROQ_API_KEY não definido — resumo usará Claude (gasta tokens)"
fi
# Check faster-whisper (fallback para vídeos sem legenda)
python3 -c "import faster_whisper" 2>/dev/null || echo "⚠️ faster-whisper não instalado (necessário só para vídeos sem legenda)"
Fallback: Vídeo sem legenda → faster-whisper tiny
Se o Step 2 retornar TranscriptsDisabled ou NoTranscriptFound, usar áudio local:
# Baixar áudio do vídeo
python3 -m yt_dlp -x --audio-format mp3 -o /tmp/yt_audio_$VIDEO_ID.mp3 "$URL" 2>/dev/null
# Transcrever localmente com Whisper tiny (~300MB RAM, libera logo)
python3 -c "
from faster_whisper import WhisperModel
model = WhisperModel('tiny', device='cpu', compute_type='int8')
segments, info = model.transcribe('/tmp/yt_audio_$VIDEO_ID.mp3', language='pt')
text = ' '.join(s.text for s in segments)
with open('/tmp/transcript_$VIDEO_ID.txt', 'w') as f:
f.write(text)
print(f'✅ Transcrição local: {len(text)} chars')
"
# Continuar para Step 4 normalmente
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.
- 9d ago First seen · 224 lines · 72 tokens per session scan A 942038e41df9
youtube-summarizer is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 6d ago), licensed MIT. It adds 72 tokens to every session and 1,843 once invoked, about $0.0004 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.
Other skills, from other repositories
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
hindsight-recall
Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.