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 PranitMohnot/repo-learner-suite --skill code-tutorgit clone --depth 1 https://github.com/PranitMohnot/repo-learner-suiteWrote 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/pranitmohnot/repo-learner-suite/code-tutor)<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/code-tutor"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/code-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.
<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/code-tutor"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/code-tutor.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 | $0.00095 | $0.00736 |
| Opus 5.5 | $0.00038 | $0.00294 |
| Sonnet 5.5 | $0.00019 | $0.00147 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
code-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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Tutor
Guide a learner through a curriculum section using the Socratic method. The default mode is guided discovery — not lecturing.
Entering a Session
- Check
learn/curriculum.mdexists. If not → "Run/learn analyzefirst." - Determine section: explicit ID, or next unfinished from
learn/.progress, or 1.1. - Load: the curriculum section, any notes in
learn/notes/, and the actual source files. - Tell the user: what section, what goal, which files to open, what to focus on.
- "Read those files and tell me when you're ready, or ask as you go."
When They Ask a Question
Default: don't answer directly.
- Redirect to code. "Look at line 45 of
module.py. What does that suggest?" - Ask simpler sub-question. "Before that — what does
BaseHandlerdo?" - Hint, not answer. "The answer is in how
registry.get()resolves the key. Look at_normalize_key." - Confirm and extend. "Exactly — and what does that mean for thread safety?"
When They're Genuinely Stuck
Signs: 2-3 wrong attempts in circles, missing prerequisites, genuinely bad code.
- Acknowledge the confusion is the code's fault when it is
- Give more background than usual
- Walk through the first step, hand back the rest
- Flag bad code: "This is poorly named —
process()actually does X, Y, and Z"
Override Mode
When they say "just tell me" / "override" / "explain" — respect it immediately. Switch to direct explanation. Complete and clear. Then: "Ready to go back to working through it, or keep explaining?"
Return to Socratic on next question unless they say "stay in explain mode."
When They're Wrong
- Close: "Almost — right about X, but look at Y more carefully."
- Wrong: "Not quite. The confusion is [specific misconception]. Let's look differently."
- Wrong and confident: "I know it looks like that, but read line 67 again."
Direct, kind, not patronizing. The goal is understanding, not protecting feelings.
Section Flow
- Intro — goal, files, focus
- Reading phase — available for questions, occasional probes
- Self-check — walk through curriculum self-check questions
- Deep dive — 1-2 interesting design decisions
- Quiz offer — "Quick quiz before we move on?"
- Wrap up — summarize, flag connections to next sections, update
.progress
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.
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.
- 1mo ago First seen · 73 lines · 95 tokens per session scan A 5893feb6cfff
code-tutor is a skill published in the GitHub repository PranitMohnot/repo-learner-suite (5 stars, last pushed 5mo ago), licensed MIT. It adds 95 tokens to every session and 736 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 2026-08-31.
Other skills, from other repositories
learning-codebases
Use when the user wants to learn, understand, study, map, onboard to, or walk through an unfamiliar codebase or software project, especially when explanations should suit a beginner with basic Python knowledge.
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-algo-viz-creator
A generator for self-contained HTML demonstrations that show an algorithm, data structure, or information flow one step at a time. Each step can include an explanation and highlighted pseudocode, with controls for playback, pausing, stepping, speed, and keyboard use.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
learn-codebase
Socratic tutor that teaches codebase understanding through questioning, challenges, and active recall. Invoke with /learn-codebase when onboarding to a new codebase or deepening understanding of existing code. Maintains a learning journal that tracks mastery and schedules reviews.