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 agentmods add instructions/axel-pm/watch-n-learn/agents-mdgit 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/instructions/axel-pm/watch-n-learn/agents-md)<a href="https://agentmods.dev/instructions/axel-pm/watch-n-learn/agents-md"><img src="https://agentmods.dev/badge/instructions/axel-pm/watch-n-learn/agents-md.svg" alt="Measured on agentmods" 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 | $0.00628 | $0.00628 |
| Opus 5 | $0.00314 | $0.00314 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
watch-n-learn AGENTS.md 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — using Watch & Learn with any AI coding agent
This file is a short guide for AI coding agents (and the people running them). Watch & Learn is packaged as a Claude Code plugin, but the skill inside it is written in an open format that several other agents understand too. Here's how to use it wherever you work.
What's in this repo
skills/watch-and-learn/— the skill itself: aSKILL.md(plain instructions), a couple of Python scripts, and some reference notes. This folder is the portable part. Everything else is packaging.
The skill takes a how-to video and turns it into a reusable skill your agent can follow later. It watches the video locally (still frames plus a transcript), writes up the procedure, and checks that the result actually works.
Install, by agent
Claude Code — install it as a plugin:
/plugin marketplace add axel-pm/watch-n-learn
/plugin install watch-and-learn@wnl
OpenAI Codex, and other agents that read the open skill format — copy (or symlink) the skill folder into the place that agent looks for skills. For Codex and several others, that's an .agents/skills/ folder in your project or home directory:
git clone https://github.com/axel-pm/watch-n-learn
mkdir -p ~/.agents/skills
cp -R watch-n-learn/skills/watch-and-learn ~/.agents/skills/
Any other agent — you can still use it. Point your agent at skills/watch-and-learn/SKILL.md and tell it to follow the steps. The instructions are plain Markdown and the scripts are plain Python, so nothing is locked to one vendor.
What it needs to run
- Python 3 on the machine.
- A one-time setup the first time:
bash skills/watch-and-learn/scripts/install-tools.sh. This installs the local video tools (for reading frames and transcribing audio) into~/.video-watch-tools. It needs internet once, and downloads a ~150MB transcription model on first use. After that it runs offline for local video files. - No API keys, no paid services.
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.
- 6d ago First seen · 43 lines · 628 tokens per session scan A 4d6c0fce3e42
watch-n-learn AGENTS.md is an instructions file published in the GitHub repository axel-pm/watch-n-learn (9 stars, last pushed 1mo ago), licensed MIT. It adds 628 tokens to every session, about $0.0031 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 instructions, from other repositories
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
chealth CLAUDE.md
Instructions for danielithomas/chealth, covering claude.md, project purpose, language & tooling, build & test and architecture.
C0BALT_CUT CLAUDE.md
Claude Code instructions for jperrello/C0BALT_CUT, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.
odoo-superpowers CLAUDE.md
Claude Code instructions for omas-odoo/odoo-superpowers, covering odoo superpowers — values & conventions, who this is for, hard rules (machine-enforced), core values and skills.
claude-goal-scaffold CLAUDE.md
Claude Code instructions for wilwaldon/claude-goal-scaffold, covering project: [your project name], stack, structure, design direction and content source.
super-spec CLAUDE.md
Claude Code instructions for lbk-open/super-spec, a project described as: Agent Skills that take a requirement — or a production alert — to a reviewed pull request: multi-agent TDD coding, a parallel review panel with severity-graded verdicts, living OpenSpec-compatible specs, and per-language guardrails.