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/woodstocksoftware/student-progress-tracker/claude-mdgit clone --depth 1 https://github.com/woodstocksoftware/student-progress-trackerWrote 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/woodstocksoftware/student-progress-tracker/claude-md)<a href="https://agentmods.dev/instructions/woodstocksoftware/student-progress-tracker/claude-md"><img src="https://agentmods.dev/badge/instructions/woodstocksoftware/student-progress-tracker/claude-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 | $0.01661 | $0.01661 |
| Opus 5 | $0.00830 | $0.00830 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
student-progress-tracker 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Student Progress Tracker MCP Server
Tech Stack
- Language: Python 3.12
- Framework: FastMCP (Model Context Protocol SDK)
- Database: SQLite3 (local file:
data/student_progress.db, configurable viaSTUDENT_PROGRESS_DBenv var) - Dependencies:
mcp>=1.0.0,python-dateutil>=2.8.0
Project Structure
student-progress-tracker/
├── run_server.py # MCP server entry point (stdio transport)
├── src/
│ └── student_progress/
│ ├── __init__.py
│ ├── __main__.py # Alternate entry: python -m src.student_progress
│ ├── server.py # MCP tool definitions (21 tools)
│ ├── database.py # SQLite schema + queries (10 tables)
│ └── validators.py # Input validation functions
├── tests/
│ ├── test_database.py # Database unit tests (57 tests)
│ ├── test_server.py # Server tool tests (81 tests)
│ └── test_validators.py # Validator unit tests (38 tests)
├── data/
│ └── student_progress.db # SQLite database (auto-created, gitignored)
├── requirements.txt
└── pyproject.toml # Linting config (ruff)
Running the Server
# Activate virtualenv
source venv/bin/activate
# Run directly
python run_server.py
# Or as a module
python -m src.student_progress
# Custom database path
STUDENT_PROGRESS_DB=/path/to/db.sqlite python run_server.py
Connecting to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"student-progress": {
"command": "/path/to/student-progress-tracker/venv/bin/python",
"args": ["/path/to/student-progress-tracker/run_server.py"]
}
}
}
Connecting to Claude Code
Add to .claude/settings.json or project's .mcp.json:
{
"mcpServers": {
"student-progress": {
"command": "/path/to/student-progress-tracker/venv/bin/python",
"args": ["/path/to/student-progress-tracker/run_server.py"]
}
}
}
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.
- 4d ago First seen · 169 lines · 1,661 tokens per session scan A 5c6bf25cfb97
student-progress-tracker CLAUDE.md is an instructions file published in the GitHub repository woodstocksoftware/student-progress-tracker (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,661 tokens to every session, about $0.0083 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.
Other instructions, from other repositories
book-to-skill AGENTS.md
AGENTS.md instructions for virgiliojr94/book-to-skill, covering agents.md, project intent, sources of truth, non-negotiable rules and execution loop.
book-to-skill CLAUDE.md
Claude Code instructions for virgiliojr94/book-to-skill, a project described as: Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
paper_notes AGENTS.md
AGENTS.md instructions for AkihikoWatanabe/paper_notes, a project described as: Daily notes on AI papers.
MindTrain AGENTS.md
Instructions for shigella520/MindTrain, covering repository instructions, mindtrain target architecture, training and content integrity, safety and integrity and fast release workflow.
flashcards-open-source-app AGENTS.md
Instructions for kirill-markin/flashcards-open-source-app, covering flashcards-open-source-app, product direction, platform plan, testing philosophy and release gates and monitoring.
SkillNet AGENTS.md
AGENTS.md instructions for ANFAIA/SkillNet, covering agents.md, project, stack, repo structure and current phase: v1 and v2 always available.