moodle-downloader-mcp: Skill for Claude Code

.grok/skills/moodle-agent/SKILL.md

moodle-agent is a skill for Claude Code, Codex from stojandev/moodle-downloader-mcp. It costs 104 tokens per session (986 once invoked), scanned A, original, MIT.

Instructions for downloading and syncing Moodle courses for offline study and AI agents. Moodle is an online learning platform used by schools and universities to provide courses and materials.

In plain words
What is it for?
Use them to set up one or more Moodle sites, authenticate safely, list and download courses or files, sync course materials, and build a local AI wiki from the downloads.
Why use it?
They turn a vague request to download Moodle content into a defined process while avoiding assumptions about the school, login details, or username. They also help preserve downloaded course knowledge as an AI-readable reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is stojandev/moodle-downloader-mcp's own configuration. It tells Claude Code and Codex how to work on moodle-downloader-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 moodle-downloader-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stojandev/moodle-downloader-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/stojandev/moodle-downloader-mcp/main/.grok/skills/moodle-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stojandev/moodle-downloader-mcp

Made for: Claude Code, Codex.

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 moodle-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/stojandev/moodle-downloader-mcp/moodle-agent/github.svg)](https://agentmods.dev/skills/stojandev/moodle-downloader-mcp/moodle-agent)
Your own site
<a href="https://agentmods.dev/skills/stojandev/moodle-downloader-mcp/moodle-agent"><img src="https://agentmods.dev/badge/skills/stojandev/moodle-downloader-mcp/moodle-agent/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 moodle-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/stojandev/moodle-downloader-mcp/moodle-agent"><img src="https://agentmods.dev/badge/skills/stojandev/moodle-downloader-mcp/moodle-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00104 $0.00986
Opus 5 $0.00052 $0.00493
Sonnet 5 $0.00021 $0.00197
Haiku 4.5 $0.00010 $0.00099

Measured 11d ago against content hash 7cb1406ceff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

moodle-agent 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 11d 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.

.grok/skills/moodle-agent/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

moodle-agent — agent runbook

You may be unfamiliar with this project. Follow this skill end-to-end.
Agent entry: README.agents.md · full: docs/AGENT_GUIDE.md · wiki: docs/WIKI.md

Goal: user says “download my Moodle stuff” → you run the CLI; only ask for credentials if auth is missing. After download, build LLM wiki so later sessions stay cheap.

Universal rules (read this)

  • No default school. Always get the Moodle base URL from the user.
  • Username format is school-specific (email, student id, LDAP, index number, …).
    Never invent a format. Ask: “What do you type on the login page?”
  • Password is never stored — only a webservice token.
  • Multi-site: separate profiles via init --name <profile>.

1) Binary / MCP

CLI:  moodle-agent          (after pip install -e . / venv)
MCP:  moodle-agent-mcp      (optional stdio server)

Prefer MCP tools when connected. Fallback: CLI with --json.
If binary missing: python -m venv .venv && pip install -e .

2) Hard rules

  • Always --json when parsing. stdout = JSON, stderr = progress.
  • Exit: 0 ok, 1 fail, 2 bad usage.
  • Never print password/token. Never hang on interactive prompts.
  • Shell $ in password → single quotes.
  • After materials exist: prefer _wiki/ over re-reading every binary every session.
  • Personal use only.

3) Auth gate

moodle-agent setup --json
moodle-agent config --json
moodle-agent whoami --json

If not authenticated → ask once for:

  1. Moodle URL (e.g. https://moodle.example.edu)
  2. Username (as on their portal)
  3. Password or webservice token

Optional (no password):

moodle-agent probe --url "https://moodle.example.edu" --json

Init:

export MOODLE_URL="https://moodle.example.edu"
export MOODLE_USER="..."
export MOODLE_PASS='...'
moodle-agent init --out ./courses --force --json
# options: --name profile --name-style preserve|latinica|ascii
#          --course-dir-style fullname|fullname_id|classic
#          --username-hint "use university email"

Read the full file on GitHub · 112 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. 11d ago First seen · 112 lines · 104 tokens per session scan A 7cb1406ceff6

Subscribe to this mod's changes

moodle-agent is a skill published in the GitHub repository stojandev/moodle-downloader-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 986 once invoked, about $0.0005 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 2026-08-31.