kb: Skill for Claude Code

.agents/skills/kb-yt-channel/SKILL.md

kb-yt-channel is a skill for Claude Code, Codex from compozy/kb. It costs 73 tokens per session (1,567 once invoked), scanned A, original, MIT.

A workflow for turning a YouTube channel into an organized knowledge-base topic using video transcripts. It handles finding videos, collecting captions or transcripts, resuming interrupted work, and validating the resulting topic.

In plain words
What is it for?
Use it to ingest a channel’s newest videos or full upload history into a knowledge base, with chosen transcript methods and language settings.
Why use it?
It removes the manual work of selecting many channel videos, obtaining their text, avoiding duplicates, and organizing the material. YouTube may limit caption downloads, so the workflow also accounts for throttling and retries.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is compozy/kb's own configuration. It tells Claude Code and Codex how to work on kb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kb configures →

View source ↗ compozy/kb
Reuse

Borrowing it

Nothing to install: this file belongs to compozy/kb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/compozy/kb/main/.agents/skills/kb-yt-channel/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/compozy/kb

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kb-yt-channel

README.md
[![agentmods](https://agentmods.dev/badge/skills/compozy/kb/kb-yt-channel.svg)](https://agentmods.dev/skills/compozy/kb/kb-yt-channel)
Your own site
<a href="https://agentmods.dev/skills/compozy/kb/kb-yt-channel"><img src="https://agentmods.dev/badge/skills/compozy/kb/kb-yt-channel.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,567 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01567
Opus 5 $0.00036 $0.00783
Sonnet 5 $0.00015 $0.00313
Haiku 4.5 $0.00007 $0.00157

Measured 8d ago against content hash 22574f388a5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kb-yt-channel 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ingest-channel.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/kb-yt-channel/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB YouTube Channel

This skill is a thin wrapper around the native kb ingest channel command. kb owns the ingest mechanics — channel resolution, video enumeration, resume/dedup, bounded concurrency, throttling, adaptive backoff, retries, native-language captions, and STT. The skill's scripts/ingest-channel.py owns the KB-side organization: scaffolding the topic under yt-channels/, maintaining category docs, patching CLAUDE.md, building wiki indexes, writing the run report, and validating the topic.

Required Inputs

  • Channel or playlist URL, such as https://www.youtube.com/@aiDotEngineer.
  • Topic slug, such as ai-dot-engineer.
  • Topic title and domain.
  • Video selection: either --limit N for the newest uploads or --all for the full uploads list.
  • Transcript policy: --transcribe captions, auto, or stt.

Caption language defaults to the original-language track (--sub-langs orig) and is handled natively by kb ingest channel. Pass a comma list like --sub-langs pt,en only to override it.

Rate limits and large channels (read before --all or --limit > ~10)

YouTube throttles caption downloads per IP (HTTP 429). kb ingest channel already paces itself with bounded concurrency, inter-request throttling, and adaptive exponential backoff (configured via [youtube].bulk_concurrency, [youtube].bulk_throttle, [youtube].bulk_retries, [youtube].bulk_backoff_max). For anything beyond a handful of videos, also give kb better network identity via its config/env — not via this script:

  1. Cookies — set YOUTUBE_COOKIES_FILE (or [youtube].cookies_file) to a logged-in YouTube session. Prefer a secondary Google account.
  2. Impersonation — install curl_cffi into the yt-dlp environment so it can present a browser TLS fingerprint. Homebrew yt-dlp: /opt/homebrew/opt/yt-dlp/libexec/bin/python -m pip install curl_cffi.
  3. Residential proxy — set YOUTUBE_PROXY to a rotating residential proxy (datacenter IPs are blocked). Pin to one country to avoid account-geo flags.
  4. Pacing — raise --throttle (e.g. 5s) and/or keep --concurrency low (1) on a bare IP. --concurrency N (>1) is only safe behind a rotating proxy; respect the proxy plan's concurrent-connection cap.

Read the full file on GitHub · 96 lines

Files

What ships with it

4 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.

Changes

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.

  1. 8d ago First seen · 96 lines · 73 tokens per session scan A 22574f388a5f

Subscribe to this mod's changes

kb-yt-channel is a skill published in the GitHub repository compozy/kb (108 stars, last pushed 18d ago), licensed MIT. It adds 73 tokens to every session and 1,567 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens