What is openschool CLAUDE.md?

Project instructions for OpenSchool, a self-hosted school management system with a Go backend and a React frontend in one repository. A monorepo is a single repository containing several related applications.

Use them when working on OpenSchool features, bugs, setup, PostgreSQL, the backend API, or the frontend.

They give a coding agent the project structure, setup steps, and design decisions it needs before making changes. This reduces repeated investigation and helps avoid changing deliberate behavior.

How openschool-org/openschool configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to openschool-org/openschool. 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/openschool-org/openschool/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/openschool-org/openschool

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/openschool-org/openschool/claude-md/github.svg)](https://agentmods.dev/instructions/openschool-org/openschool/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/openschool-org/openschool/claude-md"><img src="https://agentmods.dev/badge/instructions/openschool-org/openschool/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/openschool-org/openschool/claude-md"><img src="https://agentmods.dev/badge/instructions/openschool-org/openschool/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,197 This file is loaded in full into every session.

When invoked 2,197 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	$0.02197	$0.02197
Opus 5.5	$0.00879	$0.00879
Sonnet 5.5	$0.00439	$0.00439
Haiku 4.5	$0.00220	$0.00220

Measured today against content hash ad66e9768f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openschool 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 today.

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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 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.

Project Overview

OpenSchool is a self-hosted school management system. It is a monorepo with two workspaces:

backend/ - Go REST API (Gin framework)
frontend/ - React SPA (Vite, TypeScript, Carbon Design System)

For anything beyond a quick fix, read further before making changes:

docs/FEATURES.md - current feature list by module
docs/ARCHITECTURE.md - component layout, full data model, external interfaces
docs/adr/ - why behind non-obvious decisions (e.g. why positions aren't ThunderID roles, why the current-academic-year invariant exists) - check here before "fixing" something that looks wrong but is deliberate

Backend

Setup & Running

cd backend

# Start PostgreSQL
docker compose up -d

# Copy and configure environment
cp .env.example .env

# Run the API (migrations run automatically on startup)
go run ./cmd/api/main.go

The server starts on :8080. Migrations in db/migrations/ are applied via golang-migrate on every startup.

Building & Testing

cd backend
go build ./...
go vet ./...
go test ./...
go test ./path/to/package  # single package

CI (.github/workflows/backend-ci.yml) also runs staticcheck (blocking) and, informationally (not yet blocking - see the workflow file for why), govulncheck and a dead-code scan.

Database Workflow (sqlc)

SQL queries live in db/queries/. After editing queries or migrations, regenerate Go code:

cd backend
sqlc generate

Never edit files in db/sqlc/ directly - they are generated. Schema is inferred from db/migrations/.

Architecture

cmd/api/main.go - entry point: loads env, runs migrations, connects DB, inits JWKS, starts Gin router
internal/config/ - loads .env via godotenv
internal/database/ - DSN builder, pgxpool connection, golang-migrate runner
internal/middleware/ - AuthMiddleware (validates ThunderID-issued JWTs against JWKS) and RequireRole (per-route role gating)
db/migrations/ - numbered up/down SQL migrations (golang-migrate format)
db/queries/ - raw SQL queries annotated for sqlc
db/sqlc/ - generated type-safe query code (do not edit)

Read the full file on GitHub · 146 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.

today Changed · +3 tokens per session ad66e9768f87
1mo ago Changed · +8 tokens per session 7ad0bf2af75f
1mo ago Changed · -2 lines · -78 tokens per session 1c944ad7e821
1mo ago Changed · -3 lines · -129 tokens per session 187503862f7f
1mo ago Changed · +9 lines · +599 tokens per session 0dd5ffbc4276
1mo ago Changed · +1 lines · +23 tokens per session 455903b6dd80
1mo ago Changed 0e0f085e0d3a
2mo ago First seen · 141 lines · 1,771 tokens per session scan A 343e67481789

Subscribe to this mod's changes

openschool CLAUDE.md is an instructions file published in the GitHub repository openschool-org/openschool (40 stars, last pushed today), licensed Apache-2.0. It adds 2,197 tokens to every session, about $0.0088 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.

openschool CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openschool CLAUDE.mdopenschool-org/openschool	Instructions file	40	today	Apache-2.0	A	2,197	Claude Code
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	today	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

openschool: Instructions file for Claude Code