socratic-tutor

socratic-tutor is a skill for Claude Code from Jellypod-Inc/school-skills. It costs 147 tokens per session (2,761 once invoked), scanned A, original, MIT.

A question-led tutor that helps a student work toward an answer without giving it away. Socratic tutoring teaches through one guiding question at a time.

In plain words
What is it for?
Guiding students through difficult problems, explaining why an approach works, finding mistakes, and preparing to solve similar questions independently.
Why use it?
It supports understanding and problem-solving rather than simply supplying homework or exam answers. It is intended for learning requests, not direct-answer requests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the school-skills plugin — 7 skills shipped together

Good fit Guiding students through difficult problems, explaining why an approach works, finding mistakes, and preparing to solve similar questions independently.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jellypod-inc/school-skills/socratic-tutor
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.

Any agent
npx skills add Jellypod-Inc/school-skills --skill socratic-tutor
Clone the repo
git clone --depth 1 https://github.com/Jellypod-Inc/school-skills

Made for: Claude Code.

Or install school-skills, the plugin that ships this one along with the rest of its 7 skills.

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 socratic-tutor

README.md
[![agentmods](https://agentmods.dev/badge/skills/jellypod-inc/school-skills/socratic-tutor/github.svg)](https://agentmods.dev/skills/jellypod-inc/school-skills/socratic-tutor)
Your own site
<a href="https://agentmods.dev/skills/jellypod-inc/school-skills/socratic-tutor"><img src="https://agentmods.dev/badge/skills/jellypod-inc/school-skills/socratic-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 socratic-tutor

Your own site · 80×15
<a href="https://agentmods.dev/skills/jellypod-inc/school-skills/socratic-tutor"><img src="https://agentmods.dev/badge/skills/jellypod-inc/school-skills/socratic-tutor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,761 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 $0.00147 $0.02761
Opus 5 $0.00073 $0.01380
Sonnet 5 $0.00029 $0.00552
Haiku 4.5 $0.00015 $0.00276

Measured 11d ago against content hash 9bd5a6a09e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

socratic-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 11d 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.

skills/socratic-tutor/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

socratic-tutor

A tutoring skill that teaches how to think, not what to answer. One guiding question at a time. Never hands over solutions unless the student has already derived them.

When to use this skill

Trigger when the user's phrasing signals "I'm stuck and want to learn how to think about this" rather than "give me the answer." Also activates when a teacher explicitly requests Socratic tutoring.

Student trigger phrasings

  • "help me understand [concept]"
  • "I'm stuck on my [subject] homework"
  • "explain [topic] step by step"
  • "I don't know how to start this problem"
  • "can you tutor me through this"
  • "walk me through how to [solve/balance/prove]"
  • "I don't get why this works"
  • "help me figure out my mistake"
  • "teach me to solve [problem type]"
  • "I need to understand [topic] for my exam"

Teacher trigger phrasings

  • "tutor my student on [topic], don't just give the answer"
  • "Socratic-style tutor this [grade] through [topic]"
  • "I want a tutoring session for my [kid] on [topic]"

Anti-triggers — DO NOT invoke this skill

  • "just give me the answer"
  • "write this essay for me"
  • "solve this problem" (no learning framing)
  • "what's 17 × 23" (direct computation)

For anti-trigger phrasings, hand off to direct answer or to quiz-generator / worksheet.

Inputs

  • Student question (required) — the problem/prompt/concept. Free text, paste, or photo.
  • Subject/course (required, infer if not stated).
  • Grade level (required, infer from phrasing).
  • Attempted work (strongly encouraged — ask on turn 1 if missing).
  • Learning goal (optional) — "test tomorrow," "understand the why."
  • Session memory — remember prior turns; avoid re-asking; track progress.

Grade-inference heuristics (check before asking)

Phrasing cue Likely level
"my homework," "Miss/Mr. ___ said," simple vocab, emoji K-8 (lean young)
"AP ___," "honors," "PSAT/SAT practice" 9-12
Calculus, matrices, orgo, micro/macro, "syllabus" college
"for my dissertation," "my PI," "thesis chapter" grad
Adult-phrasing + no school markers ("I'm trying to learn Python") adult self-study — lighter Socratic frame

Read the full file on GitHub · 186 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. 11d ago First seen · 186 lines · 147 tokens per session scan A 9bd5a6a09e46

Subscribe to this mod's changes

socratic-tutor is a skill published in the GitHub repository Jellypod-Inc/school-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 147 tokens to every session and 2,761 once invoked, about $0.0007 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.

Related

Other skills, from other repositories