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 agentmods add instructions/chenchenyaqi/learn-anything/claude-mdgit clone --depth 1 https://github.com/ChenChenyaqi/learn-anythingWrote 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/instructions/chenchenyaqi/learn-anything/claude-md)<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>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 | $0.01046 | $0.01046 |
| Opus 5 | $0.00523 | $0.00523 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
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.
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)
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.
- 5d ago First seen · 73 lines · 1,046 tokens per session scan A a6f6d926a4fc
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.
Other instructions, from other repositories
jacky-skills-learning CLAUDE.md
Claude Code instructions for wangjs-jacky/jacky-skills-learning, covering claude.md - skills learning 项目上下文, 项目简介 and 项目结构.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.