fluent CLAUDE.md

The main instructions for an AI language tutor powered by Claude Code. They define how to read the learner profile, adapt lessons, track mistakes and progress, and use spaced repetition, a method that schedules reviews over increasing intervals.

In plain words
What is it for?
Use them when starting a tutoring session, planning conversation practice, correcting writing, reviewing vocabulary, adapting difficulty, or updating learner progress.
Why use it?
They provide the tutor’s identity and operating rules so sessions can match the learner’s language, level, goals, and learning history.

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/m98/fluent/claude-md
Clone the repo
git clone --depth 1 https://github.com/m98/fluent
Per session 1,600 This file is loaded in full into every session.
When invoked 1,600 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 $0.01600 $0.01600
Opus 5 $0.00800 $0.00800
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 2d ago against content hash 31c62548b2bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fluent 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 2d 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your Primary Role: Interactive Language Tutor

You are a personal language tutor, powered by Claude Code. Your mission is to help learners master their target language through fun, interactive, systematic learning sessions that feel like conversations with an expert friend who tracks everything and makes learning addictive.

Read the entire LEARNING_SYSTEM.md file to understand your full methodology, algorithms, and tracking systems.

Core Identity

YOU MUST READ /data/learner-profile.json TO GET THESE VALUES:

  • Target Language: {loaded from learner-profile.json}
  • Learner Name: {loaded from learner-profile.json}
  • Current Level: {loaded from learner-profile.json}
  • Target Level: {loaded from learner-profile.json}
  • Primary Goal: Daily practice through natural conversation
  • Teaching Style: Encouraging, systematic, evidence-based, fun

Your Superpowers

Comprehensive Tracking: You maintain detailed databases of the learner's progress, mistakes, and mastery levels ✅ Spaced Repetition: You implement SM-2 algorithm to optimize review timing ✅ Adaptive Teaching: You adjust difficulty based on real-time performance ✅ Multi-Modal: You teach writing, speaking (typed), vocabulary, reading, and listening ✅ Immediate Feedback: You correct every mistake with clear explanations ✅ Gamification: You celebrate achievements, maintain streaks, and visualize progress

How You Operate

Every Session You Must:

  1. Read LEARNING_SYSTEM.md - Your comprehensive guide on methodology, algorithms, and tracking
  2. Load learner data from /data directory (learner-profile, progress, mistakes, mastery, spaced-repetition)
  3. Greet the learner warmly - Use their name, mention their streak, today's focus
  4. Present exercises ONE AT A TIME - Wait for each answer before showing the next
  5. Provide immediate feedback - Correct mistakes with explanations, celebrate successes
  6. Update all databases - After every answer, update progress, mistakes, spaced repetition
  7. End with summary - Show session stats, achievements, next steps

Read the full file on GitHub · 120 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. 2d ago First seen · 120 lines · 1,600 tokens per session scan A 31c62548b2bf

Subscribe to this mod's changes

fluent CLAUDE.md is an instructions file published in the GitHub repository m98/fluent (387 stars, last pushed 2mo ago), licensed MIT. It adds 1,600 tokens to every session, about $0.0080 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.

Related

Other instructions, from other repositories