What is mcp-academy AGENTS.md?

A project instruction document for StudioMeyer Academy, a learning service for coding agents. It explains how to discover lessons and search content, choose a language, connect to the service, and respect personal-data and permission boundaries.

Use it when connecting to or working with the StudioMeyer Academy service. It guides discovery, language selection, authentication, and safe handling of personal data and credits.

It tells an agent which public resources and current service descriptions to use instead of inventing courses, prices, credits, or availability. It also separates public access from actions that need a person’s permission.

How studiomeyer-io/mcp-academy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to studiomeyer-io/mcp-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/studiomeyer-io/mcp-academy/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/studiomeyer-io/mcp-academy

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/studiomeyer-io/mcp-academy/agents-md/github.svg)](https://agentmods.dev/instructions/studiomeyer-io/mcp-academy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/studiomeyer-io/mcp-academy/agents-md"><img src="https://agentmods.dev/badge/instructions/studiomeyer-io/mcp-academy/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/studiomeyer-io/mcp-academy/agents-md"><img src="https://agentmods.dev/badge/instructions/studiomeyer-io/mcp-academy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 784 This file is loaded in full into every session.

When invoked 784 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00784	$0.00784
Opus 5.5	$0.00314	$0.00314
Sonnet 5.5	$0.00157	$0.00157
Haiku 4.5	$0.00078	$0.00078

Measured 6d ago against content hash 0401fd05ece9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-academy 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 6d 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 · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StudioMeyer Academy for coding agents

Kurz auf Deutsch: Lernen ist kostenlos. Persönliche Daten und Credits benötigen die ausdrücklich freigegebenen Berechtigungen eines Menschen.

StudioMeyer Academy offers free public learning paths, lessons, search and library content. German is the default; use locale: "en" or "es" when requested. Start with academy_start, then follow the live registry and schemas. Do not invent courses, offers, credit prices or availability.

Connections and discovery

Public MCP: https://mcp.studiomeyer.academy/mcp?access=free
Personal MCP with OAuth: https://mcp.studiomeyer.academy/mcp
REST operation registry: https://studiomeyer.academy/v1
OpenAPI: https://studiomeyer.academy/v1/openapi.json
Authentication walkthrough: https://studiomeyer.academy/auth.md
Agent Plugins manifest: plugin.json, with the remote Streamable HTTP server in mcp.json.

Read current tools/list and output schemas. The default public tool list stays intact; aliases are declared by the service. The optional offline library is a historical snapshot, not current service availability.

Identity and permission boundaries

Normal OAuth uses public clients, PKCE S256 and exact registered redirect URIs. A human selects learn:read for personal records and learn:write for saving learning activity. credits:spend is unchecked by default and never follows from either learning scope. Inspect actual permissions with academy_my_access after connecting.

Where AS metadata advertises agent_auth, anonymous agent registration grants no personal scopes. An anonymous token permits public content only. The human-claim ceremony requires the intended person's verified email, the agent's code and explicit learning-scope consent in the same browser. Claiming never grants spending. External identity assertions, service-auth identities and security-event delivery are not advertised or accepted as substitutes for human approval.

Read the full file on GitHub · 35 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.

6d ago First seen · 35 lines · 784 tokens per session scan A 0401fd05ece9

Subscribe to this mod's changes

mcp-academy AGENTS.md is an instructions file published in the GitHub repository studiomeyer-io/mcp-academy (1 stars, last pushed 6d ago), licensed MIT. It adds 784 tokens to every session, about $0.0031 per session on Opus 5.5. 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 2026-11-01.

Building agents Learning and teaching ai-education anthropic built-in-mallorca claude learning mcp

mcp-academy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-academy AGENTS.mdstudiomeyer-io/mcp-academy	Instructions file	1	6d ago	MIT	A	784	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-academy: Instructions file for Codex