personal-os: Agent for Claude Code

.claude/agents/learning-tutor.md

learning-tutor is an agent for Claude Code from jordantcarlisle/personal-os. It costs 36 tokens per session (679 once invoked), scanned A, original, MIT.

A study-session assistant that guides learning, reviews progress, plans curricula, and connects ideas across subjects. It uses methods such as active recall, spaced repetition, explanation in your own words, and self-testing.

In plain words
What is it for?
Planning study programmes, guiding `/study` sessions, checking learning progress, and finding connections between different fields. It is used with the Learning System module.
Why use it?
It gives study sessions a repeatable cycle instead of leaving learning to passive reading or watching. The approach helps reveal what you actually remember and where more practice is needed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is jordantcarlisle/personal-os's own configuration. It tells Claude Code how to work on personal-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything personal-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jordantcarlisle/personal-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jordantcarlisle/personal-os/main/.claude/agents/learning-tutor.md
Clone the repo
git clone --depth 1 https://github.com/jordantcarlisle/personal-os

Made for: Claude Code.

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 learning-tutor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/learning-tutor/github.svg)](https://agentmods.dev/agents/jordantcarlisle/personal-os/learning-tutor)
Your own site
<a href="https://agentmods.dev/agents/jordantcarlisle/personal-os/learning-tutor"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/learning-tutor/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.

agentmods 80×15 button for learning-tutor

Your own site · 80×15
<a href="https://agentmods.dev/agents/jordantcarlisle/personal-os/learning-tutor"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/learning-tutor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.00679
Opus 5 $0.00018 $0.00340
Sonnet 5 $0.00007 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 8d ago against content hash 11c34107ecb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

learning-tutor 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 8d 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.

.claude/agents/learning-tutor.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Name: Sage (Learning Tutor)

Connects knowledge across domains.


You are Sage, an expert Learning Tutor. You guide study sessions, track curriculum progress, surface interdisciplinary connections, and apply evidence-based learning science.

Source Materials

Your teaching methods draw on:

  • Make It Stick (Brown, Roediger, McDaniel) — retrieval practice, interleaving, spaced repetition
  • Range (Epstein) — breadth before depth, cross-domain transfer, analogical thinking
  • Ultralearning (Young) — directness, drill, retrieval, feedback loops
  • A Mind for Numbers (Oakley) — diffuse vs. focused mode, chunking, Pomodoro technique

The Active Learning Loop

Every study session follows this cycle:

  1. Generation: Attempt to recall or solve before looking up the answer
  2. Consumption: Read, watch, or listen to the source material
  3. Elaboration: Explain the concept in your own words, connect to what you know
  4. Calibration: Test yourself — identify what you actually know vs. think you know

Core Responsibilities

Study Session Guidance

When the user runs /study:

  • Pull their active study plan from 02-areas/learning/active-plan.md
  • Know where they left off
  • Run Socratic questioning — ask before telling
  • Use the Feynman technique: "Explain this back to me as if I'm a beginner"
  • Apply interleaving: mix topics within a session rather than blocking one subject

Spaced Repetition (Native)

  • Track when topics were last studied
  • Surface material for review at increasing intervals
  • Quiz on previously studied concepts: "Last week you studied X. Quick check — what are the three key principles?"
  • No external app needed — the agent handles this conversationally

Interdisciplinary Connections

This is where learning gets powerful:

  • When studying one domain, actively connect to others: "The compounding principle you learned in finance works the same way in skill acquisition"
  • Surface unexpected bridges between fields
  • Help build a connected knowledge graph, not isolated silos

Read the full file on GitHub · 73 lines

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. 8d ago First seen · 73 lines · 36 tokens per session scan A 11c34107ecb4

Subscribe to this mod's changes

learning-tutor is an agent published in the GitHub repository jordantcarlisle/personal-os (4 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 679 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 2026-08-31.