teach-me AGENTS.md

teach-me AGENTS.md is an instructions file for Codex, OpenCode from smileynet/teach-me. It costs 3,757 tokens per session, scanned B, original, MIT.

A set of instructions for an agent workspace designed to teach software and technical topics. It defines where learning materials, skills, notes, reference projects, and helper tools belong.

In plain words
What is it for?
Use it when building or maintaining an agent that teaches, quizzes, explains jargon, creates diagrams, or checks visual learning materials.
Why use it?
It gives learning-focused agent tasks a shared layout and workflow, so teaching content and saved knowledge have predictable places.

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/smileynet/teach-me/agents-md
Clone the repo
git clone --depth 1 https://github.com/smileynet/teach-me

Made for: Codex, OpenCode.

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 teach-me AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/smileynet/teach-me/agents-md.svg)](https://agentmods.dev/instructions/smileynet/teach-me/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/smileynet/teach-me/agents-md"><img src="https://agentmods.dev/badge/instructions/smileynet/teach-me/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,757 This file is loaded in full into every session.
When invoked 3,757 The same file — it is already loaded in full.
Security scan B 2 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 $0.03757 $0.03757
Opus 5 $0.01878 $0.01878
Sonnet 5 $0.00751 $0.00751
Haiku 4.5 $0.00376 $0.00376

Measured today against content hash 5e23ae7620e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

teach-me AGENTS.md scanned grade B with 2 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 today.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- PowerShell mangles complex inline shell-arg strings — inline JSON (`curl -d '{...}'`), `->`, backslashes, and long `git commit -m`/`tkt close --resolution` bodies get corrupted or misparsed. Use a file instead: `--data

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Validating work | Validate from the user's perspective (Playwright click-through, curl the endpoint, load the page). Prefer linters, syntax checkers, and templates over formal test suites. Only write maintained tests f
AGENTS.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — teach-me

Test bed for learning-oriented agent skills. Refined here, then ported to crew-research for global deployment.

Workspace Layout

workspace/          — THE user's live learning workspace (gitignored, auto-created on first serve)
.kiro/skills/       — agent skills (teach, quiz-me, wait-what, jargon, visual-qa, theme, etc.)
.kiro/steering/     — visual-teaching guidelines
.memory/            — persistent knowledge (CONTEXT.md glossary, ADRs, research findings)
.scratch/           — ephemeral (gitignored) — only visual-qa output regenerated on run
.references/        — cloned reference repos (gitignored, rehydrate via mise run rehydrate)
tools/              — project scripts (draw-diagram, visual-qa, theme-preview, render-diagrams, sr-*)
tools/lib/          — Python helpers (preact_page.py for generating Preact HTML shells)
palettes/           — color palette definitions (JSON)
assets/             — shared: style.css, CSS variables, SVG patterns
assets/vendor/      — vendored Preact + Signals + HTM + dagre (self-hosted, no CDN)
assets/components/  — Preact components (MapView, TopicCard, QuizView, etc.)
assets/services/    — signal services (generation.js SSE stream)
assets/scaffolds/   — content-pattern examples (boilerplate is in tools/lib/page_template.py)
.tickets/           — local ticket tracking
library/           — public topic library (shipped, growing; served by default on a fresh clone — ADR 0012). Committed lessons/maps/reference per domain.

workspace/ is the single live workspace per machine — all topics (maps, lessons, quizzes, reference docs, learning records) go here. Gitignored (user-local); auto-created on first mise run serve. Lessons are organized by domain: lessons/{domain-slug}/NN-slug.html, per-domain numbering from 01; quizzes and maps parallel this (lessons/{domain-slug}/quiz/, lessons/{domain-slug}/{domain}-map.html).

Skills

Skill Trigger What it does
teach /teach, "teach me", "next lesson" Multi-session learning with stateful workspace
generate-topic /generate-topic, "generate lesson", "complete topic" Full pipeline: research → lesson → post-process → verify (parallel subagents)
quiz-me /quiz-me, "test me" Socratic dialog — learner explains, agent probes
wait-what /wait-what, "I don't understand" Re-explain when comprehension fails
jargon /jargon, "annotate terms" Post-authoring: annotate domain jargon with tooltips
visual-qa "visual qa", "check the ui" Exercise components, capture screenshots, report
theme "theme", "colors", "palette" Preview, validate, and apply color palettes
draw-diagram "draw diagram", "generate SVG" Generate inline SVG teaching diagrams
browse-and-verify "validate link", "check this URL" Dispatch browser agent for URL validation

Read the full file on GitHub · 149 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. today Changed · -4 lines · -42 tokens per session 5e23ae7620e9
  2. 4d ago First seen · 153 lines · 3,799 tokens per session scan B 5ee19fb4749d

Subscribe to this mod's changes

teach-me AGENTS.md is an instructions file published in the GitHub repository smileynet/teach-me (3 stars, last pushed today), licensed MIT. It adds 3,757 tokens to every session, about $0.0188 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.