schoology-mcp: Instructions file for Claude Code

CLAUDE.md

schoology-mcp CLAUDE.md is an instructions file for Claude Code from dajun666/schoology-mcp. It costs 7,355 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that retrieves Schoology course pages through a browser. MCP is a standard way for AI assistants to call external tools; this server logs in through ClassLink and parses rendered pages instead of using a Schoology API.

In plain words
What is it for?
Use them to install dependencies, store credentials, check the login, inspect course materials, run the MCP server, and perform offline or live checks.
Why use it?
They explain the unusual browser-login process, required setup, available commands, and how to test the scraper.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is dajun666/schoology-mcp's own configuration. It tells Claude Code how to work on schoology-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything schoology-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dajun666/schoology-mcp. 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/dajun666/schoology-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dajun666/schoology-mcp

Made for: Claude Code.

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 schoology-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dajun666/schoology-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dajun666/schoology-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dajun666/schoology-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dajun666/schoology-mcp/claude-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.

agentmods 80×15 button for schoology-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dajun666/schoology-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dajun666/schoology-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,355 This file is loaded in full into every session.
When invoked 7,355 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07355 $0.07355
Opus 5.5 $0.02942 $0.02942
Sonnet 5.5 $0.01471 $0.01471
Haiku 4.5 $0.00736 $0.00736

Measured 1mo ago against content hash bc67cbf2f050, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

schoology-mcp CLAUDE.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 1mo 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.

CLAUDE.md · 507 lines

How it starts

The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP server (stdio) for PAUSD Schoology (pausd.schoology.com), logging in through the ClassLink SSO portal.

It reads Schoology's /v1 REST API using the browser session's cookie. Schoology documents that API as OAuth-1.0a-only, but its own front end calls it with the plain session cookie and so do we — no API key, no signing. The cookie already lives in storage_state.json, so a warm session answers with no browser process at all; Playwright is launched only to re-run the ClassLink SAML flow when the session dies.

A headless-Playwright scraper over the rendered pages is still here as a fallback (parsers.py, browser.py), selected by SCHOOLOGY_API_MODE. It was the only implementation until 2026-09-01. Measured on the real account: 3.4–4.8s per page render against 0.12–0.44s per API call, and check_updates across all five sources went 19.3s → 2.2s.

Commands

source .venv/bin/activate            # required in every new shell
pip install -r requirements.txt && playwright install chromium

python scripts/set_credentials.py    # store password in the OS keyring (once)
python scripts/login_check.py --show-browser   # verify login + dump HTML to dumps/
python scripts/explore_materials.py --course <id>  # dump a course's materials pages
python server.py                     # run the MCP server over stdio
npx @modelcontextprotocol/inspector python server.py   # interactive tool testing
python scripts/check_watch.py --fixtures   # offline regression suite over dumps/
python scripts/check_watch.py --live       # same checks against the real account

There is no linter or build step, and no unit-test framework — check_watch.py --fixtures is the test suite. Run it after touching any parser, transform, fingerprint or health rule. It needs no network and no data in the account, and it covers the regressions that matter (determinism, time-drift, empty-vs-broken, baseline poisoning, first-run silence).

Read the full file on GitHub · 507 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. 1mo ago Changed · +214 lines · +3,342 tokens per session bc67cbf2f050
  2. 2mo ago First seen · 293 lines · 4,013 tokens per session scan A 4a03ccf649d5

Subscribe to this mod's changes

schoology-mcp CLAUDE.md is an instructions file published in the GitHub repository dajun666/schoology-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 7,355 tokens to every session, about $0.0294 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 2026-08-31.

Related

schoology-mcp CLAUDE.md compared with instructions from other repositories

schoology-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
schoology-mcp CLAUDE.mddajun666/schoology-mcpInstructions file11mo agoMITA7,355Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode