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 agentmods add skills/sliamh11/deus/add-youtube-transcriptnpx skills add sliamh11/Deus --skill add-youtube-transcriptgit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/add-youtube-transcript)<a href="https://agentmods.dev/skills/sliamh11/deus/add-youtube-transcript"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-youtube-transcript.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00581 |
| Opus 5 | $0.00018 | $0.00291 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade B, and why
add-youtube-transcript scanned grade B 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 5d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat .mcp.json 2>/dev/null What it actually says
Add YouTube Transcript
This skill adds YouTube transcript extraction capability to Deus via an MCP server. Once installed, the agent can fetch captions and subtitles from any YouTube video using the get_transcript tool.
Phase 1: Pre-flight
Check if already configured
Check if .mcp.json already has a youtube-transcript entry:
cat .mcp.json 2>/dev/null
If youtube-transcript is already present, inform the user it's already installed and skip to Phase 3 (Verify).
Phase 2: Install and Configure
Install the MCP server package
npm install --save-dev @kimtaeyoon83/mcp-server-youtube-transcript
Configure MCP
Read the current .mcp.json and add the youtube-transcript server entry. The final .mcp.json should include:
{
"mcpServers": {
"youtube-transcript": {
"command": "npx",
"args": ["-y", "@kimtaeyoon83/mcp-server-youtube-transcript"]
}
}
}
If .mcp.json already has other servers configured, merge the new entry — do not overwrite existing servers.
Build
npm run build
Phase 3: Verify
Test the MCP server starts
npx @kimtaeyoon83/mcp-server-youtube-transcript --help 2>&1 || echo "Server binary accessible"
Tell the user:
YouTube transcript extraction is now available. The agent can fetch captions from any YouTube video.
Usage: Ask the agent to get a transcript from a YouTube URL, or use the
get_transcripttool directly with a video URL or ID.Supported options:
url— YouTube video URL or video IDlang— Language code (default: "en", e.g., "ko", "he", "es")
Removal
To remove YouTube transcript support:
-
Remove the MCP server entry from
.mcp.json:# Edit .mcp.json and remove the "youtube-transcript" key from mcpServers -
Uninstall the package:
npm uninstall @kimtaeyoon83/mcp-server-youtube-transcript -
Rebuild:
npm run build
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.
- 5d ago First seen · 90 lines · 37 tokens per session scan B 0d50586a0bc9
add-youtube-transcript is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 581 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memcord
Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.
roadmap-build
Build or repair a roadmap that agents can actually execute, not just read. Produces a single validated YAML source of truth, generated views, definitions of done with evidence kinds, a task pool linked on two axes, an idea intake queue, and three standing checks that keep it honest. Use when asked to "build a…
GTD for Datacore
Getting Things Done — task capture, inbox processing, and org-mode management.
Research for Datacore
Automated research — source processing, podcast generation, and knowledge extraction.
Outbox for Datacore
Content routing — archive to server, search archived content.
research-status
Check research queue counts, recent podcasts, knowledge base growth, and Readwise items.