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 vre/flow-state --skill youtube-to-markdowngit clone --depth 1 https://github.com/vre/flow-stateWrote 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/vre/flow-state/youtube-to-markdown)<a href="https://agentmods.dev/skills/vre/flow-state/youtube-to-markdown"><img src="https://agentmods.dev/badge/skills/vre/flow-state/youtube-to-markdown/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/vre/flow-state/youtube-to-markdown"><img src="https://agentmods.dev/badge/skills/vre/flow-state/youtube-to-markdown.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 | $0.00039 | $0.00827 |
| Opus 5 | $0.00019 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
youtube-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube to Markdown
Multiple videos: Process one video at a time, sequentially. Do not run parallel extractions. Do not create your own scripts. Channel subfolder naming: Channel Name (channel_id) — always include the channel ID.
Step -1: Detect input type
If input is a channel URL (contains /@, /channel/, /c/, /user/) or a bare channel ID (starts with UC, 24 chars), but NOT watch?v=:
Read and follow ./subskills/channel_browse.md.
Otherwise: Continue to Step 0.
Step 0: Check if extracted before
python3 ./scripts/run.py check "<YOUTUBE_URL>" "<output_directory>"
Output JSON contains video_id. Set BASE_NAME = youtube_{video_id} for all subsequent steps.
Tell the user: "Valitse 'Yes, allow all edits during this session'. Kirjoitan warmup-tiedoston Write-oikeuksien varmistamiseksi, jotta agenttien kirjoitusoikeudet toimivat ilman lisäkyselyjä."
Then Write "# Processing {video_id}\n" to <output_directory>/${BASE_NAME}_warmup.tmp. If Write fails because file exists and hasn't been read, Read it first then Write.
If exists: false: Continue to Step 1.
If exists: true: Read and follow ./subskills/update_flow.md.
Step 1: Choose output
AskUserQuestion:
- question: "What do you want to extract from the video?"
- header: "Output"
- multiSelect: false
- options: A. "Summary + Comments (Recommended)" - Summary cross-analyzed with comments. Timestamped transcript stored for reference. B. "Summary + Comments + Formatted Transcript with Watch Guide" - Option A + cleaned and formatted full transcript with synthesized watch guide → double tokens C. "Summary Only" - Summary of video content. Timestamped transcript stored for reference. D. "Formatted Transcript Only" - Cleaned and formatted full transcript
Step 2: Execute modules
Based on user's choice, read and follow each subskill instruction in ./subskills/{file}.
Concurrency: "|" = run concurrently as parallel foreground agents in one message. Never use run_in_background.
What ships with it
60 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.
- CHANGELOG.md 21 KB
- formats/claim-bullets.md 2.1 KB
- formats/flat-bullets.md 1.2 KB
- formats/step-list.md 2.0 KB
- formats/themed-claims.md 2.2 KB
- injection_defense.py 3.7 KB runs code
- lib/assembler.py 24 KB runs code
- lib/channel_listing.py 11 KB runs code
- lib/check_existing.py 8.6 KB runs code
- lib/comment_extractor.py 7.2 KB runs code
- lib/comment_filter.py 3.3 KB runs code
- lib/comment_merge.py 2.7 KB runs code
- lib/content_safety.py 2.6 KB runs code
- lib/file_ops.py 1.3 KB runs code
- lib/intermediate_files.py 3.1 KB runs code
- lib/paragraph_breaker.py 3.7 KB runs code
- lib/paragraph_breaks.py 7.1 KB runs code
- lib/prepare_update.py 10 KB runs code
- lib/shared_types.py 8.0 KB runs code
- lib/transcript_extractor.py 3.6 KB runs code
- lib/update_metadata.py 1.2 KB runs code
- lib/vtt_deduplicator.py 2.3 KB runs code
- lib/youtube_extractor.py 9.9 KB runs code
- LICENSE 1.1 KB
- pyproject.toml 317 B
- README.md 4.7 KB
- scripts/10_extract_metadata.py 1018 B runs code
- scripts/11_extract_transcript.py 1.0 KB runs code
- scripts/12_extract_transcript_whisper.py 9.1 KB runs code
- scripts/13_extract_comments.py 1.0 KB runs code
- scripts/20_check_existing.py 941 B runs code
- scripts/21_prepare_update.py 997 B runs code
- scripts/22_list_channel.py 3.3 KB runs code
- scripts/23_check_comment_growth.py 2.5 KB runs code
- scripts/30_clean_vtt.py 1018 B runs code
- scripts/31_format_transcript.py 1.3 KB runs code
- scripts/32_filter_comments.py 2.5 KB runs code
- scripts/33_merge_tier2.py 1.6 KB runs code
- scripts/33_split_for_cleaning.py 5.5 KB runs code
- scripts/34_concat_cleaned.py 3.0 KB runs code
- scripts/35_insert_headings_from_json.py 4.0 KB runs code
- scripts/36_resolve_summary.py 861 B runs code
- scripts/37_paragraph_breaks.py 1.1 KB runs code
- scripts/40_backup.py 1.3 KB runs code
- scripts/41_update_metadata.py 1.6 KB runs code
- scripts/50_assemble.py 2.6 KB runs code
- scripts/run.py 4.2 KB runs code
- scripts/templates/comments_standalone.md 52 B
- scripts/templates/comments.md 32 B
- scripts/templates/summary.md 32 B
- scripts/templates/transcript.md 65 B
- scripts/templates/watch_guide.md 14 B
- subskills/channel_browse.md 3.9 KB
- subskills/comment_extract.md 1.8 KB
- subskills/comment_summarize.md 2.9 KB
- subskills/summary_formats.md 2.3 KB
- subskills/transcript_extract.md 1.8 KB
- subskills/transcript_polish.md 7.9 KB
- subskills/transcript_summarize.md 3.2 KB
- subskills/update_flow.md 3.4 KB
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 · 82 lines · 39 tokens per session scan A a67d658f2bfd
youtube-to-markdown is a skill published in the GitHub repository vre/flow-state (12 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 827 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
myslide
Create professional AWS-themed PowerPoint presentations with dark gradient backgrounds, AWS brand colors, and rich visual elements (SVG diagrams, architecture diagrams, icons). Uses the official AWS reInvent 2023 template design system. Supports creating from scratch, editing specific slides conversationally, and…
notion
Notion API for creating and managing pages, databases, and blocks.
pptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary)…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page…
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…