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 diillson/chatcli --skill youtubegit clone --depth 1 https://github.com/diillson/chatcliWrote 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/diillson/chatcli/youtube)<a href="https://agentmods.dev/skills/diillson/chatcli/youtube"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/youtube/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/diillson/chatcli/youtube"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/youtube.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00543 |
| Opus 5.5 | $0.00026 | $0.00217 |
| Sonnet 5.5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
youtube 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.
What it actually says
YouTube
Keyless YouTube access via yt-dlp (no API key). Detect: command -v yt-dlp ffmpeg (Unix) /
Get-Command yt-dlp -ErrorAction SilentlyContinue (Windows). Install: brew install yt-dlp ffmpeg
/ pipx install yt-dlp / choco install yt-dlp.
Metadata (no download)
yt-dlp --dump-json --no-warnings "URL" | python3 -c "import sys,json;d=json.load(sys.stdin);print(d['title'],'-',d['uploader'],'-',d['duration_string'])"
Transcript / subtitles (best for summarizing)
yt-dlp --skip-download --write-auto-subs --sub-langs "en,pt" --sub-format vtt -o "%(id)s" "URL"
This writes a .vtt; read it with @read, strip timestamps, and summarize. Prefer manual subs
(--write-subs) when available, auto-subs (--write-auto-subs) otherwise.
Download
yt-dlp -f "bestaudio" -x --audio-format mp3 "URL" # audio only
yt-dlp -f "bv*+ba/b" -o "%(title)s.%(ext)s" "URL" # best video+audio
"Summarize this video" workflow
- Get metadata (title/author/length).
- Pull the transcript (subs). If none exist, say so — don't fabricate.
- Read the transcript and produce a structured summary (key points + timestamps if useful).
Rules
- Respect copyright/ToS: download only what the user is entitled to; default to transcript-only for summarization.
ffmpegis required for audio extraction/merging — check it in Step 0.
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 · 54 lines · 64 tokens per session scan A cd2979391647
youtube is a skill published in the GitHub repository diillson/chatcli (93 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 543 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.