learn-anything CLAUDE.md

learn-anything CLAUDE.md is an instructions file for coding agents from ChenChenyaqi/learn-anything. It costs 1,046 tokens per session, scanned A, original, MIT.

Repository instructions for Learn Anything, a command-line tool that turns AI coding assistants into interactive learning tutors. They describe its commands, project layout, supported tools, and test and build commands.

In plain words
What is it for?
Use them when changing the Learn Anything CLI, its localized outputs, or its learning workflows such as practice, review, quizzes, and topic explanations.
Why use it?
They help contributors understand the codebase and run the correct build, test, development, and lint tasks across its packages.

Instructions file

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 instructions/chenchenyaqi/learn-anything/claude-md
Clone the repo
git clone --depth 1 https://github.com/ChenChenyaqi/learn-anything

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-anything CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chenchenyaqi/learn-anything/claude-md.svg)](https://agentmods.dev/instructions/chenchenyaqi/learn-anything/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chenchenyaqi/learn-anything/claude-md"><img src="https://agentmods.dev/badge/instructions/chenchenyaqi/learn-anything/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,046 This file is loaded in full into every session.
When invoked 1,046 The same file — it is already loaded in full.
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 $0.01046 $0.01046
Opus 5 $0.00523 $0.00523
Sonnet 5 $0.00209 $0.00209
Haiku 4.5 $0.00105 $0.00105

Measured 5d ago against content hash a6f6d926a4fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-anything CLAUDE.md 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 5d 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.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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Learn Anything is a CLI tool (learn-anything) that generates skill and command files for AI coding assistants, turning them into interactive learning tutors. It supports 30+ AI tools (Claude Code, Cursor, Gemini CLI, Codex, Copilot, Windsurf, etc.) and outputs localized files in en and zh-CN.

The generated skills implement 6 learning workflows: topic (initialize a subject), explain (recursive Socratic deep-dive), practice (TDD-style exercises), review (spaced repetition), status (knowledge map visualization), and quiz (two-stage generation and grading).

Commands

pnpm build          # Compile TypeScript via tsc (runs node build.js in each package)
pnpm dev            # tsc --watch (all packages)
pnpm test           # Run all tests once (vitest run) across all packages
pnpm test:watch     # Run tests in watch mode (vitest) across all packages
pnpm lint           # ESLint on packages/
# Per-package commands:
pnpm -F learn-anything-cli build     # Build only the CLI package
pnpm -F learn-anything-cli test      # Test only the CLI package

Architecture (monorepo)

packages/
  cli/                  # Published as `learn-anything-cli`
    src/
      cli/index.ts          # Commander.js CLI: `learn-anything init [path]` and `learn-anything update [path]`
      core/
        init.ts             # InitCommand — orchestrates tool detection, interactive selection,
                            #   skill generation, and command generation
        config.ts           # AI_TOOLS array (30+ tools with skillsDir mappings), LEARN_DIR
        command-generation/ # Adapter pattern: each tool has an adapter that knows its file format
                            #   and directory conventions (Claude → .claude/commands/, YAML frontmatter;
                            #   Gemini → .gemini/commands/, TOML; Codex → ~/.codex/prompts/)
          types.ts          # CommandContent, ToolCommandAdapter, GeneratedCommand interfaces
          registry.ts       # CommandAdapterRegistry — maps tool IDs → adapters
          generator.ts      # generateCommand / generateCommands — applies adapter to content
          adapters/         # claude.ts, cursor.ts, codex.ts, gemini.ts
        templates/
          types.ts          # SkillTemplate, CommandTemplate interfaces
          skill-templates.ts # Re-exports all 6 workflow template getters
          workflows/        # learn-topic.ts, learn-explain.ts, learn-practice.ts,
                            #   learn-review.ts, learn-status.ts, learn-quiz.ts
                            #   Each exports getXxxSkillTemplate(locale) and getXxxCommandTemplate(locale)
        shared/
          skill-generation.ts  # Aggregates templates; generateSkillContent() writes YAML frontmatter
      i18n/
        index.ts            # getMessages(locale), detectSystemLocale(), resolveLocale()
        types.ts            # LocaleMessages, SkillsMessages, CLIMessages, InitMessages types
        locales/
          en.ts, zh-CN.ts   # Top-level locale messages (CLI strings, init messages)
          skills/{en,zh-CN}/ # Per-workflow skill/command content (topic.ts, explain.ts, etc.)
      utils/
        file-system.ts      # ensureDir, writeFile, fileExists, dirExists, removeDir
        interactive.ts      # isInteractive() — checks process.stdin/stdout.isTTY
  gui/                  # Placeholder for future GUI (private, not published)

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. 5d ago First seen · 73 lines · 1,046 tokens per session scan A a6f6d926a4fc

Subscribe to this mod's changes

learn-anything CLAUDE.md is an instructions file published in the GitHub repository ChenChenyaqi/learn-anything (431 stars, last pushed 6d ago), licensed MIT. It adds 1,046 tokens to every session, about $0.0052 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 2026-08-30.