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.
git clone --depth 1 https://github.com/DoIT-Artificial-Intelligence/youtube-to-docsWrote 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/plugins/doit-artificial-intelligence/youtube-to-docs/gemini-extension)<a href="https://agentmods.dev/plugins/doit-artificial-intelligence/youtube-to-docs/gemini-extension"><img src="https://agentmods.dev/badge/plugins/doit-artificial-intelligence/youtube-to-docs/gemini-extension/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/plugins/doit-artificial-intelligence/youtube-to-docs/gemini-extension"><img src="https://agentmods.dev/badge/plugins/doit-artificial-intelligence/youtube-to-docs/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
youtube-to-docs 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 13d 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.
What it actually says
{
"identifier": "youtube-to-docs",
"name": "youtube-to-docs",
"description": "Convert YouTube videos into structured docs, summaries, audio, and visual assets for easier discovery.",
"version": "1.0.0",
"mcpServers": {
"youtube-to-docs": {
"command": "uv",
"args": [
"--project",
"${extensionPath}",
"run",
"--all-extras",
"python",
"-m",
"youtube_to_docs.mcp_server"
]
}
}
}What ships with it
35 files beside gemini-extension.json 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.
- scripts/generate_sbom.py 9.2 KB runs code
- scripts/performance/README.md 1.4 KB
- scripts/performance/time_to_summary.py 4.4 KB runs code
- scripts/prices/gemini_prices_web.py 5.7 KB runs code
- scripts/prices/README.md 246 B
- scripts/reauthenticate_google.py 1.8 KB runs code
- scripts/reauthenticate_sharepoint.py 3.1 KB runs code
- scripts/regression/README.md 6.6 KB
- scripts/regression/regression_aws_polly.py 1.1 KB runs code
- scripts/regression/regression_aws_transcribe.py 1.2 KB runs code
- scripts/regression/regression_aws_translate.py 2.2 KB runs code
- scripts/regression/regression_core.py 17 KB runs code
- scripts/regression/regression_en_full.py 1.3 KB runs code
- scripts/regression/regression_es_no_yt_summary.py 2.6 KB runs code
- scripts/regression/regression_flash_lite_image.py 1.6 KB runs code
- scripts/regression/regression_gcp_stt_long.py 1.1 KB runs code
- scripts/regression/regression_gcp_stt.py 979 B runs code
- scripts/regression/regression_gcp_translate.py 2.0 KB runs code
- scripts/regression/regression_gcp_tts.py 1.0 KB runs code
- scripts/regression/regression_gemini_image_comparison.py 1.8 KB runs code
- scripts/regression/regression_gemma.py 2.4 KB runs code
- scripts/regression/regression_huggingface_playlist.py 1.3 KB runs code
- scripts/regression/regression_huggingface.py 2.8 KB runs code
- scripts/regression/regression_post_process.py 1.2 KB runs code
- scripts/regression/regression_scc_stt.py 3.9 KB runs code
- scripts/regression/regression_scc_youtube_speakers.py 3.1 KB runs code
- scripts/regression/regression_scc_youtube.py 2.7 KB runs code
- scripts/regression/regression_sharepoint.py 1.2 KB runs code
- scripts/regression/regression_translate_infographic.py 2.3 KB runs code
- scripts/regression/regression_translate_tts.py 2.2 KB runs code
- scripts/regression/regression_translate.py 2.0 KB runs code
- scripts/regression/regression_two_vids_verbose.py 734 B runs code
- scripts/regression/regression_two_vids.py 704 B runs code
- scripts/regression/regression_workspace_es.py 1.6 KB runs code
- scripts/regression/regression_workspace.py 1.5 KB runs code
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.
- 13d ago First seen · 20 lines scan A 9e88c71ba132
youtube-to-docs is a plugin published in the GitHub repository DoIT-Artificial-Intelligence/youtube-to-docs (51 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-02.
Other plugins, from other repositories
accessibility-agents
WCAG 2.2 AA enforcement. Six router skills dispatch the specialist team; hooks block UI edits until the accessibility lead has reviewed.
excessibility
LiveView introspection and accessibility testing skills for Phoenix. Use htmlsnapshot() to capture state at any point, axe-core for WCAG compliance, timeline analysis for debugging.
a11y-audit
Accessibility audits for Shopify stores: scans the storefront against WCAG 2.2 AA with pa11y (axe-core + HTMLCodeSniffer) and Lighthouse, samples by theme template, attributes every finding to the theme, the injecting app (Rebuy, Okendo, Klaviyo, ...), or the collision between them, re-measures contrast in the settled.
claude-skills marketplace
Agent settings configuring schemaversion, skills.
webability-accessibility
Scan pages and HTML for WCAG 2.2 / ADA / Section 508 issues, get framework-aware fixes, and verify them. Free hosted MCP server from WebAbility.
motionspec
Verified web motion for AI-built sites: write a MotionSpec JSON spec, validate it against a strict schema, and compile deterministic GSAP/CSS with reduced-motion support and performance budgets enforced by construction. Reports WCAG 2.2.2 pause-path candidates (reduced-motion guard = 2.3.3, AAA). Includes a…