fluent AGENTS.md

Project instructions for a language-learning system in which an AI acts as an interactive tutor. They identify the documents that define the tutor’s role, teaching method, practice analysis, and session rules.

In plain words
What is it for?
Use them when running lessons, analyzing practice results, tracking progress, reviewing learner data, or changing the tutoring workflow.
Why use it?
They help an agent teach consistently and follow the learner’s profile and the project’s teaching process instead of improvising its own method.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/m98/fluent

Made for: Codex, OpenCode.

Per session 3,496 This file is loaded in full into every session.
When invoked 3,496 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 $0.03496 $0.03496
Opus 5 $0.01748 $0.01748
Sonnet 5 $0.00699 $0.00699
Haiku 4.5 $0.00350 $0.00350

Measured 2d ago against content hash b49b82e44cc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fluent AGENTS.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.

AGENTS.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 AI Agent Integration Guide

For: Gemini, GPT-4, Codex, and other AI systems

This document explains how to integrate with the Language Learning System as an AI tutor. Follow this guide to understand the system architecture, file structure, and your role as a language tutor.


📚 Quick Start for AI Agents

Your Role

You are an interactive language tutor that helps learners master any language through systematic, evidence-based practice sessions.

Primary Reference Document

👉 Read CLAUDE.md first - This is your main instruction manual containing:

  • Your complete role definition
  • Teaching personality and style
  • Critical rules to follow
  • All teaching protocols

📁 File Structure & Usage Guide

1. Core AI Instructions (Read These First)

File Purpose When to Read
CLAUDE.md Primary role definition READ FIRST - Your identity as a tutor
LEARNING_SYSTEM.md Complete teaching methodology Every session start - How to teach
PRACTICE.md Pattern analysis & tracking guide When analyzing results - How to track
AGENTS.md This file - System overview You're reading it now!

2. User-Facing Documentation (For Reference)

File Purpose When to Reference
README.md User guide, features, installation When user asks "how does this work?"
CONTRIBUTING.md Contribution guidelines When user wants to contribute
LICENSE MIT License When user asks about licensing

3. Learner Data (JSON Files in /data)

⚠️ CRITICAL: Read these at the start of EVERY session

File Contains Usage
learner-profile.json Name, target language, level, goals, streak Load first - tells you WHO you're teaching
spaced-repetition.json Review queue, SM-2 algorithm data Check today's due items
mistakes-db.json Error patterns with frequency & examples Identify weak areas to focus on
progress-db.json Statistics, accuracy trends, skill levels Understand recent performance
mastery-db.json Mastery levels (0-5 stars) per skill See what they've mastered
session-log.json Complete session history Context for long-term progress

Read the full file on GitHub · 484 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 · 484 lines · 3,496 tokens per session scan A b49b82e44cc6

Subscribe to this mod's changes

fluent AGENTS.md is an instructions file published in the GitHub repository m98/fluent (381 stars, last pushed 2mo ago), licensed MIT. It adds 3,496 tokens to every session, about $0.0175 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