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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill jove-youtube-feed-pipelinegit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-youtube-feed-pipeline)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-youtube-feed-pipeline"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-youtube-feed-pipeline/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/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-youtube-feed-pipeline"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-youtube-feed-pipeline.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 | $0.00167 | $0.01476 |
| Opus 5.5 | $0.00067 | $0.00590 |
| Sonnet 5.5 | $0.00033 | $0.00295 |
| Haiku 4.5 | $0.00017 | $0.00148 |
Grade A, and why
jove-youtube-feed-pipeline 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JoVE YouTube → Brain Feed Pipeline
The proven, repeatable process for turning YouTube content into queryable brain knowledge. Built + battle-tested across Rounds 1–3 (~8,500 transcripts).
The architecture (do NOT deviate)
Enumerate + gate for FREE; pay Apify only for transcripts.
yt-dlp --flat-playlistenumerates a channel/playlist (FREE, no API key). Resolves @handles → channel IDs. This also powers the gate + top-N selection.- Pre-flight gate (
workers/preflight_channel.py --source ytdlp, $0 — gpt-4.1 + metadata): identity check + junk filter + cost forecast → GO/NO-GO before any spend. - Apify (
workers/apify_youtube_ingest.py) transcribes GO channels via thesupreme_coder/youtube-transcript-scraperactor (~$0.0005/captioned video, pay-per-result). Modes:--channel,--playlist,--video,--watch;--top-n Ncaps giants; omit for full. Idempotent viadata/youtube_channels.jsonregistry. Token:APIFY_API_TOKENin.env(free tier $5/mo). workers/connect_youtube.py --allenriches: filter (8-voice relevance) → NER (gpt-4.1) → LanceDB index → related-linker → link-to-[[JoVE]]. Idempotent (skips connected).- LanceDB = the vector leg → queryable via
workers/ask_brain.py. - Pinecone archive (jove-memory / conversations namespace) — wrap-up summary of the round for future recall.
The 8 stakeholder voices (ranking lens)
Rank channels by voice fidelity (a real end-user speaks) × strategic weight to Dhiraj's mandate (author acquisition + editorial workflow + biopharma).
🎓 young researcher · 🔬 PI/author · 🖋 editor/reviewer · 🏭 biopharma/R&D · 📚 librarian/buyer · 👩🏫 instructor · 💰 grants · ⚔️ competitor.
Source of truth: vault/context/jove/youtube-import-runbook.md (v3).
Running a feed round (autonomous, batched)
- Build a scope file like
data/round3_scope.json: batches → channels{name, ref (channel_id|@handle|playlist_id|video_id), mode (channel|playlist|video), expect}. Group by voice/priority.expectis the gate's identity string — make it accurate (a too-narrow expect causes false NO-GO). - Use the batch runner pattern (
data/round3_runner.py): for each batch → ingest all channels →connect_youtube --all→ validate (errors=0, fragments<500 or HALT) → next. Idempotent + resumable. - Launch detached:
PYTHONPATH=. nohup .venv/bin/python data/round3_runner.py &. Supervise via ScheduleWakeup (resume-proof), NOT a background bash watcher (those die on session resume). - On completion: scorecard + ask_brain sanity query + Pinecone archive.
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.
- 1mo ago First seen · 55 lines · 167 tokens per session scan A f841ca324584
jove-youtube-feed-pipeline is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 21d ago), licensed MIT. It adds 167 tokens to every session and 1,476 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…
faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance…
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.