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 BlackBeltTechnology/pi-agent-dashboard --skill youtube-srtgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/youtube-srt)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/youtube-srt"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/youtube-srt/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/blackbelttechnology/pi-agent-dashboard/youtube-srt"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/youtube-srt.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 | $0.00096 | $0.01303 |
| Opus 5.5 | $0.00038 | $0.00521 |
| Sonnet 5.5 | $0.00019 | $0.00261 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
youtube-srt 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube SRT → catalog
Two stages. Stage 1 is generic (any channel/video). Stage 2 is the model-catalog pipeline
that produced docs/models/ from @theAIsearch.
Prerequisites
yt-dlpon PATH (pipx install yt-dlp; if pipx complains about uv:pipx install --backend pip yt-dlp).python3(stdlib only) for stage 2. No API keys — YouTube captions are free.
Stage 1 — fetch subtitles
S=packages/video-transcription/.pi/skills/youtube-srt/scripts
$S/yt-srt.sh -s now-6months "https://www.youtube.com/@theAIsearch" # channel, date window
$S/yt-srt.sh "https://www.youtube.com/watch?v=VIDEO_ID" # single video
$S/yt-srt.sh -o ~/somewhere -l "de.*,de" -n 50 "https://youtube.com/playlist?list=..."
| Flag | Meaning | Default |
|---|---|---|
-o DIR |
output dir | ~/Documents/Media/youtube/<@handle> (or misc) |
-s SINCE |
lower upload-date bound (YYYYMMDD, now-6months, today-30days) — stops at first older video |
none |
-l LANGS |
yt-dlp --sub-langs |
en.*,en |
-n MAX |
max playlist items scanned | 200 |
Output per video: <YYYYMMDD>_<id>_<title>.<lang>.srt + .txt ([mm:ss] line, rolling
auto-caption duplicates removed, ~4× smaller — feed THIS to LLMs). index.tsv = id, date,
duration, url, title. Manual subs preferred, auto-captions fallback; when both en-orig and en
exist only en-orig is kept.
Idempotent: .archive.txt skips fetched IDs; IDs whose subtitles failed (HTTP 429) are removed
from the archive and the script prints WARN: N video(s) without subtitles → just rerun later.
Stage 2 — model catalog (docs/models/)
- Fetch:
$S/yt-srt.sh -s <window> "https://www.youtube.com/@theAIsearch". - Batch: in
<out>/extract/,ls ../*.txt | sort | split -l 6 -a 1 - batch-(~6 videos ≈ 60k tokens per batch; for an incremental update list only the new.txtfiles and pick unused batch letters). - Extract: one
general-purposesubagent per batch (host cap ≈ 2 concurrent), prompt:Working dir: <out>. Read extract/PROMPT.md and follow it exactly. Batch file extract/batch-X; write extract/X.jsonl.PROMPT.mdholds the schema below; copy it from an existing<out>/extract/PROMPT.mdor recreate from this section. - Render:
python3 $S/build-catalog.py <out>/extract docs/models→README.md, one<category>.mdper function,local-hardware.md(tiers T0–T5),models.jsonl(merged, one model per line). Hand-curatedpicks.mdis never touched by the renderer — refresh it via DocScribe when data changes.
What ships with it
2 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.
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.
- 11d ago First seen · 74 lines · 96 tokens per session scan A 84cd2d6e9731
youtube-srt is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,303 once invoked, about $0.0004 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 2026-10-05.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.
goga-define-requirements
Define the product requirements that describe what the product must do to deliver the established user experience and achieve the agreed product goals.