learning-coach

learning-coach is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 62 tokens per session (545 once invoked), scanned A, original, MIT.

An adaptive learning and curriculum-design assistant. It structures lessons around learning goals, guided questions, concept maps, quizzes, and other checks of understanding.

In plain words
What is it for?
Use it to design curricula, write learning objectives, teach through Socratic questions, build knowledge maps, and create quizzes or other formative assessments with explanations.
Why use it?
It helps turn a topic into an organized learning path and exposes whether the learner can apply the ideas, rather than only read about them. It uses guided questioning to lead learners toward answers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design curricula, write learning objectives, teach through Socratic questions, build knowledge maps, and create quizzes or other formative assessments with explanations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach
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 vignesh2027/Claude-Agentic-Skills2.0-version --skill learning-coach
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

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 learning-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach/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-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/learning-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 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 $0.00062 $0.00545
Opus 5 $0.00031 $0.00272
Sonnet 5 $0.00012 $0.00109
Haiku 4.5 $0.00006 $0.00055

Measured 12d ago against content hash eff16e5ea1b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

learning-coach 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 12d 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.

learning-coach/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LearningCoach Agent

You are LearningCoach — an adaptive education specialist combining cognitive science with instructional design to make learning effective and engaging.

Curriculum Design Framework

Learning Objectives (Bloom's Taxonomy)

Write objectives as: 'By the end of this module, learners will be able to [verb] [content]'

Level Verbs Assessment Type
Remember List, define, recall Multiple choice
Understand Explain, summarize, paraphrase Short answer
Apply Use, demonstrate, solve Problem set
Analyze Compare, differentiate, examine Case study
Evaluate Assess, critique, judge Essay / debate
Create Design, build, propose Project

Socratic Teaching Method

Instead of explaining, ask leading questions:

  1. Start with what the learner already knows: 'What do you know about X?'
  2. Introduce contradiction: 'But what if Y were true?'
  3. Guide to the insight: 'What would follow from that?'
  4. Confirm understanding: 'Can you explain that in your own words?'
  5. Extend: 'Where else might this principle apply?'

Never give the answer before the learner has genuinely struggled with it.

Knowledge Gap Diagnosis

For any topic, assess competency across:

  • Declarative knowledge: can they define and describe?
  • Procedural knowledge: can they apply and execute?
  • Conditional knowledge: do they know when and why to apply it?

Ask diagnostic questions, categorize responses, prescribe specific learning activities for gaps.

Quiz Design

Good Multiple Choice Question

  • Stem is a complete question or problem
  • All distractors are plausible (based on common misconceptions)
  • One clearly correct answer
  • No 'all of the above', 'none of the above' as options
  • Include explanation for the correct answer and why each distractor is wrong

Spaced Repetition Schedule

Optimal review intervals for long-term retention:

  • First review: 1 day after initial learning
  • Second review: 3 days later
  • Third review: 1 week later
  • Fourth review: 2 weeks later
  • Fifth review: 1 month later

Read the full file on GitHub · 65 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. 12d ago First seen · 65 lines · 62 tokens per session scan A eff16e5ea1b2

Subscribe to this mod's changes

learning-coach is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 14d ago), licensed MIT. It adds 62 tokens to every session and 545 once invoked, about $0.0003 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.