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 axel-pm/watch-n-learn --skill watch-and-learngit clone --depth 1 https://github.com/axel-pm/watch-n-learnWrote 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/axel-pm/watch-n-learn/watch-and-learn)<a href="https://agentmods.dev/skills/axel-pm/watch-n-learn/watch-and-learn"><img src="https://agentmods.dev/badge/skills/axel-pm/watch-n-learn/watch-and-learn/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/axel-pm/watch-n-learn/watch-and-learn"><img src="https://agentmods.dev/badge/skills/axel-pm/watch-n-learn/watch-and-learn.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 | $0.00127 | $0.01761 |
| Opus 5 | $0.00063 | $0.00881 |
| Sonnet 5 | $0.00025 | $0.00352 |
| Haiku 4.5 | $0.00013 | $0.00176 |
Grade A, and why
watch-and-learn 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
watch-and-learn
Turn a video that demonstrates a procedure into a reusable Claude Code skill (or a small set of them), then prove the skill works. The video is the teacher; the output is a skill someone can invoke later without watching anything.
Watching is local and free: scripts/watch.py extracts keyframes (PNG) + a labelled contact sheet and transcribes the audio (PyAV + faster-whisper, no API keys, no torch). See references/watching.md for how the engine works and its options.
Placeholders:
<this-skill>= this skill's own directory (where this SKILL.md lives).<file-or-URL>= the video you're processing.
Prerequisites (one-time per machine, usually already done)
watch.py self-locates its toolchain venv and re-execs into it — no activation, and a plain python3 invocation is fine (it finds the venv via $VIDEO_WATCH_TOOLS, a tools/venv up the directory tree, or ~/.video-watch-tools/venv, which is where the bundled installer puts it). You normally do nothing here.
Only if watch.py reports the toolchain is missing (a fresh machine) do you install it once:
bash <this-skill>/scripts/install-tools.sh # creates the venv at ~/.video-watch-tools (av, Pillow, faster-whisper, yt-dlp)
First transcription downloads the Whisper base model (~150 MB), cached thereafter.
Workflow
1. Qualify — is this worth a skill?
Before spending on a full watch, decide whether the video actually teaches a reusable, transferable procedure worth capturing. Do it cheaply: run watch.py --transcript-only (for a talk/narrated video) or just read the title + description, and judge against references/qualifying.md. Proceed if it's a real how-to you'd invoke later; STOP and say why (suggesting notes or a reference doc instead) if it's opinion, a one-off, too trivial, or already covered by an existing skill. Escape hatch: an obviously strong tutorial doesn't need belabouring — note it in one line and move on.
2. Watch — send an agent
Run the watch step in a subagent (the Agent tool), not the main thread: a video digest is 15–25 images plus a transcript, and you don't want that flooding the main context. (No subagent capability in your harness? Run it inline, then summarize into the procedure spec below and drop the raw frames from context before continuing — same result, you just manage the context yourself.) Tell the subagent to:
What ships with it
8 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.
- references/procedure-spec-template.md 1.5 KB
- references/qualifying.md 2.9 KB
- references/skill-authoring.md 2.5 KB
- references/validation-checklist.md 1.8 KB
- references/watching.md 4.6 KB
- scripts/install-tools.sh 1.7 KB runs code
- scripts/validate_skill.py 4.4 KB runs code
- scripts/watch.py 16 KB runs code
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.
- 10d ago First seen · 76 lines · 127 tokens per session scan A f436a64aa16f
watch-and-learn is a skill published in the GitHub repository axel-pm/watch-n-learn (9 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 1,761 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
examples
Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.
intro
Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.
interactive-product-tour
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of…