What is stoop CLAUDE.md?

Project-specific instructions for Stoop, a platform that deploys static websites with subdomains, user identity, authentication, and a per-site realtime database without requiring site-side backend code. They describe its Bun workspaces monorepo, services, commands, and data contracts.

Working on Stoop's web app, command-line tool, shared core package, Cloudflare services, database migrations, local development, type checks, linting, tests, and browser end-to-end tests.

Agents working in this repository need to know its workspace layout, technologies, commands, and conventions before changing code. These notes provide that context and help keep shared contracts consistent.

How mislavjc/stoop configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mislavjc/stoop. 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/mislavjc/stoop/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mislavjc/stoop

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/mislavjc/stoop/claude-md/github.svg)](https://agentmods.dev/instructions/mislavjc/stoop/claude-md)

Your own site

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

Per session 885 This file is loaded in full into every session.

When invoked 885 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	$0.00885	$0.00885
Opus 5.5	$0.00354	$0.00354
Sonnet 5.5	$0.00177	$0.00177
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash fb606d448a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stoop 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 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stoop Agent Notes

Stoop is a Shopify Quick-style instant deployment platform on Cloudflare: uploaded static sites get subdomains, identity, auth, and a per-site realtime database without site-side backend code. This is a Bun-workspaces monorepo with Cloudflare Workers, D1, R2, Durable Objects, TanStack Start SSR, Better Auth, Effect, and Alchemy v2 IaC.

Workspace Layout

apps/web is the platform app: Worker entry, TanStack Start dashboard, Alchemy stack, D1 migrations, R2 deploys, and the ProjectDB Durable Object.
packages/core (@stoop/core) owns effect/Schema contracts and the typed client shared by the dashboard and CLI.
packages/cli (@stoop/cli) provides the stoop binary for device-login, deploy, and open commands. It uses effect/unstable/cli and builds a Node target bundle with Bun.

Commands

Install dependencies with bun install.
Run local dev with bun run dev from the repo root.
Run checks with bun run typecheck, bun run lint, and bun test.
Run browser E2E with bun run e2e; use bun run e2e:install once to install Chromium. Set E2E_BASE_URL=https://stoop.localhost to include live app smoke tests against bun run dev.
Package scripts should be invoked with bun run --cwd <workspace> <script> or the root scripts already defined in package.json.

Treat bun run typecheck, bun run lint, and relevant bun test coverage as the baseline before work is done. For browser-visible behavior, add or run an E2E test as well.

Effect Conventions

Keep request routing as plain fetch/Workers code at the edge, then move platform behavior into Effect programs. apps/web/src/platform.ts:43 is the boundary: routePlatform() builds a program and runs it through errorsToResponses and defectsTo500.
Domain failures are tagged errors from apps/web/src/errors.ts:3: Unauthenticated, Forbidden, NotFound, BadRequest, and Conflict. Map them to HTTP responses only at the platform boundary.
Wrap infrastructure calls with the local io() helper (apps/web/src/platform.ts:127). D1/R2/DO failures are defects unless the code deliberately translates them into a domain error.
Prefer Effect.gen(function* () { ... yield* ... }) for multi-step platform flows, matching createProject, deploy, and deleteProject in apps/web/src/platform.ts.

Read the full file on GitHub · 77 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.

2mo ago First seen · 77 lines · 885 tokens per session scan A fb606d448a90

Subscribe to this mod's changes

stoop CLAUDE.md is an instructions file published in the GitHub repository mislavjc/stoop (1 stars, last pushed 3mo ago), licensed MIT. It adds 885 tokens to every session, about $0.0035 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.

Backend and APIs Databases agent-skills bun claude-skills cloudflare-workers deployment-platform durable-objects

stoop CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
stoop CLAUDE.mdmislavjc/stoop	Instructions file	1	3mo ago	MIT	A	885	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

stoop: Instructions file for Claude Code