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/naorpeled/aitutor/agents-mdgit clone --depth 1 https://github.com/naorpeled/aitutorWhat 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 | $0.01185 | $0.01185 |
| Opus 5 | $0.00593 | $0.00593 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
aitutor 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
AITutor is an interactive terminal-based tutorial for AI coding concepts, built with Go and the Charm ecosystem (Bubbletea, Lipgloss, Bubbles). It teaches through theory, interactive visualizations, and quizzes across 17 lessons in 3 tiers (Beginner, Intermediate, Advanced).
Architecture
- Entry point:
main.go— blank-imports all content packages to triggerinit()lesson registration - App model:
internal/app/app.go— root Bubbletea model orchestrating header, footer, sidebar, lesson model, progress, welcome screen, and help overlay - Lesson state machine:
internal/lesson/model.go— phases: Theory → Visualization → Quiz → Complete - Content:
internal/content/{beginner,intermediate,advanced}/— each file registers aLessonDefviainit() - Visualizations:
internal/viz/— each viz implements theviz.Modelinterface (Init/Update/View) - Quiz:
internal/quiz/— supports MultipleChoice, FillBlank, and Ordering question types - Progress:
internal/progress/— persists to~/.aitutor/progress.json - Types:
pkg/types/types.go— shared types to avoid circular imports
Key Patterns
Adding a New Lesson
- Create
internal/content/<tier>/NN_topic.go - In
init(), calllesson.Register(types.LessonDef{...})with ID, Title, Tier, Theory, VizBuilder, and Questions - Create the visualization in
internal/viz/implementingviz.Modelinterface - The lesson auto-registers — no wiring needed
- Update
internal/ui/header.godefault Total if needed (it gets overridden at runtime but keeps the default accurate)
VizBuilder Uses interface{}
VizBuilder returns interface{} (not viz.Model) to avoid circular imports between types and viz packages. The lesson package does the type assertion.
Key Handling
- App-level keys (quit, tab, n/p, →/← for phase navigation, ?) are handled in
app.go →(right arrow) advances phases from any phase — this is the primary "next phase" key←(left arrow) and Backspace go back a phaseEnteradvances from Theory phase, but in Viz/Quiz phases it falls through to the viz/quiz for interaction- Tab is reserved for sidebar toggle — visualizations must not use Tab
- Visualizations should use
h/lfor horizontal navigation, not left/right arrows (reserved for phase nav)
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.
- 2d ago First seen · 105 lines · 1,185 tokens per session scan A 5d1906a2100b
aitutor AGENTS.md is an instructions file published in the GitHub repository naorpeled/aitutor (218 stars, last pushed 5d ago), licensed MIT. It adds 1,185 tokens to every session, about $0.0059 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
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
webxr-first-steps AGENTS.md
Instructions for meta-quest/webxr-first-steps, covering agent instructions — webxr first steps, stack and key facts, build and run, what the sample demonstrates and notes for agents.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.