Borrowing it
Nothing to install: this file belongs to mblayman/homeschool. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mblayman/homeschool/main/AGENTS.mdgit clone --depth 1 https://github.com/mblayman/homeschoolWrote 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/mblayman/homeschool/agents-md)<a href="https://agentmods.dev/instructions/mblayman/homeschool/agents-md"><img src="https://agentmods.dev/badge/instructions/mblayman/homeschool/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.
<a href="https://agentmods.dev/instructions/mblayman/homeschool/agents-md"><img src="https://agentmods.dev/badge/instructions/mblayman/homeschool/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01666 | $0.01666 |
| Opus 5.5 | $0.00666 | $0.00666 |
| Sonnet 5.5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
homeschool 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 2mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
This repository is a Django app for homeschool planning. Use this file as the first stop for AI-agent work: it captures the commands, architecture, and safety rules that are otherwise spread across the repo.
Stack
- Python 3.13, managed with
uv. - Django 6 app configured from
project/settings.py. - SQLite is the default local database.
- Node 23 is used for Tailwind CSS and Playwright under
frontend/. - Sphinx documentation lives under
docs/.
Key Paths
project/: Django project settings, URL routing, ASGI/WSGI entry points, and test settings.homeschool/: first-party Django apps. Each domain app keeps its models, views, forms, URLs, admin code, and tests together.templates/: Django templates shared by the first-party apps.frontend/: Tailwind source, Node package lockfile, and Playwright e2e tests.static/: static assets checked into the repo. Generated CSS is ignored atstatic/site.css.docs/: Sphinx documentation.hashid_field/: vendored package code. Keep changes here minimal and preserve upstream style unless the task is explicitly about this package.
Setup
Use the repo-local examples rather than inventing environment values.
cp .env.example .env
uv sync
npm --prefix frontend i
make bootstrap
make bootstrap installs frontend dependencies, runs migrations, creates or
updates the local matt superuser, and enables the signup flag. The local login
created by the Makefile is [email protected] with password correcthorse.
Development Commands
make local: run the Django web process, Huey worker, and Tailwind watcher viahonchoandProcfile.uv run manage.py migrate: apply database migrations.uv run manage.py shell: open a Django shell.npm --prefix frontend run build: build minified Tailwind CSS intostatic/site.css.npm --prefix frontend run watch: watch Tailwind CSS during local development.uv run pre-commit run --all-files: run the configured django-upgrade and Ruff hooks.make docs: build Sphinx docs.make build: build the Docker Compose image.
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.
- 2mo ago First seen · 159 lines · 1,666 tokens per session scan A 76ad790af246
homeschool AGENTS.md is an instructions file published in the GitHub repository mblayman/homeschool (244 stars, last pushed yesterday), licensed MIT. It adds 1,666 tokens to every session, about $0.0067 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 2026-08-30.
homeschool AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| homeschool AGENTS.mdmblayman/homeschool | Instructions file | 244 | yesterday | MIT | A | 1,666 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | 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 oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |