learn-this

learn-this is a skill for Claude Code, Codex from sliamh11/Deus. It costs 31 tokens per session (1,541 once invoked), scanned A, original, MIT.

A teaching and memory tool that explains a topic using NotebookLM and saves what the user learned in a shared memory vault. NotebookLM is a document-grounded research assistant.

In plain words
What is it for?
Use it for lightweight lessons whose learning records should remain available across projects and sessions.
Why use it?
It lets future sessions recall the user's previous learning instead of starting from zero.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sliamh11/deus/learn-this
Any agent
npx skills add sliamh11/Deus --skill learn-this
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

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 learn-this

README.md
[![agentmods](https://agentmods.dev/badge/skills/sliamh11/deus/learn-this.svg)](https://agentmods.dev/skills/sliamh11/deus/learn-this)
Your own site
<a href="https://agentmods.dev/skills/sliamh11/deus/learn-this"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/learn-this.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01541
Opus 5 $0.00015 $0.00771
Sonnet 5 $0.00006 $0.00308
Haiku 4.5 $0.00003 $0.00154

Measured yesterday against content hash 768d5d08c447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-this 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 yesterday.

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.

.claude/skills/learn-this/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/learn-this

Teach the user something and make the learning stick across sessions by persisting it into the semantic memory vault, so the next session (and any project) can recall what they already know.

This is the vault-native sibling of /teach. Where /teach builds a directory-based, multi-week course workspace (mission file, lesson HTML, local learning-records), /learn-this keeps no local workspace: it writes each learning as a vault memory node retrievable anywhere via memory_tree.py, and grounds knowledge in NotebookLM rather than parametric guessing.

Relationship to /teach (read this — single source of truth)

  • /teach → a self-contained course workspace in the current directory. Best for a sustained, structured curriculum with rich interactive HTML lessons.
  • /learn-this → lightweight, cross-session learning capture into the global vault + NotebookLM. Best for "teach me X and remember that I learned it" across projects.

Never duplicate a learning record across both. A /teach workspace owns its local learning-records/; /learn-this owns $VAULT/Learning/. If a learning relates to a /teach course, link it with a see_also edge — do not copy it.

Steps

1. Resolve the vault path

Read ~/.config/deus/config.json and use its vault_path. If DEUS_VAULT_PATH is set, use that instead. All paths below use $VAULT for this resolved path. (Same resolution as /checkpoint, /compress, /preserve — keep it portable; never hardcode a personal path.)

2. Establish the mission

Understand why the user wants to learn this — the concrete real-world goal it serves. This grounds every teaching choice. If it is unclear, ask before teaching; a vague mission produces abstract, ungrounded lessons. The mission is captured inside the first learning node (step 6), not in a separate file.

3. Compute the zone of proximal development — from the vault

Query the vault for what the user already knows on this topic:

Read the full file on GitHub · 129 lines

Files

What ships with it

1 file 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. yesterday First seen · 129 lines · 31 tokens per session scan A 768d5d08c447

Subscribe to this mod's changes

learn-this is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,541 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories