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/raiyanyahya/superlearn/agents-mdgit clone --depth 1 https://github.com/raiyanyahya/SuperlearnWrote 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/raiyanyahya/superlearn/agents-md)<a href="https://agentmods.dev/instructions/raiyanyahya/superlearn/agents-md"><img src="https://agentmods.dev/badge/instructions/raiyanyahya/superlearn/agents-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 | $0.00383 | $0.00383 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
Superlearn 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 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.
What it actually says
Superlearn
Superlearn turns "I want to learn X" into a researched, interactive learning
board served at http://localhost:4321. It ships as a Claude Code plugin and as
a standard Agent Skill for OpenAI Codex, Kilo (formerly Kilo Code), and any
agent that reads SKILL.md.
If the user asks to learn, study, or research a topic
Follow the pipeline in .agents/skills/superlearn/SKILL.md — research first,
plan, iterate until saturated, author and validate the board, serve, keep
iterating. Do not improvise a different flow, and never author a board before
research is saturated. (skills/superlearn/SKILL.md is the same playbook in
its Claude Code plugin edition.)
Working on this repo
- Zero dependencies by design: every script in
scripts/is Python 3.9+ standard library, and the app is one file (app/index.html) with no build step. Keep it that way. - Run the tests with
python3 -m unittest discover -s tests -v. - The board contract lives in
scripts/validate_board.py; if you change it, update the schema documentation inskills/superlearn/SKILL.md(and vice versa) so they never disagree. .agents/skills/superlearn/SKILL.mdmust end with the body ofskills/superlearn/SKILL.mdverbatim — a unit test enforces this. Edit the Claude edition first, then regenerate or mirror the portable copy.- The scrapers must stay polite: identify honestly, tiny request volume, no login walls, no paywall or CAPTCHA circumvention — see "The researched data isn't ours" in the README.
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 · 31 lines · 383 tokens per session scan A 7a072a5988d3
Superlearn AGENTS.md is an instructions file published in the GitHub repository raiyanyahya/Superlearn (109 stars, last pushed 20d ago), licensed MIT. It adds 383 tokens to every session, about $0.0019 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
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.
canvas-lms-mcp AGENTS.md
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.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.
claude-certified-architect-guide CLAUDE.md
Instructions for amitgambhir/claude-certified-architect-guide, covering claude.md, project overview, development, architecture and content pages.