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/devanhurst/hackbox/claude-mdgit clone --depth 1 https://github.com/devanhurst/hackboxWhat 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 | $0.04287 | $0.04287 |
| Opus 5 | $0.02143 | $0.02143 |
| Sonnet 5 | $0.00857 | $0.00857 |
| Haiku 4.5 | $0.00429 | $0.00429 |
Grade A, and why
hackbox 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 yesterday.
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 — 319 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
Hackbox is a real-time multiplayer game platform (think Jackbox): a host (a third-party game, typically a Unity build, not in this repo) drives UI onto players' phones and receives their interactions, all relayed in real time.
The platform runs entirely on Cloudflare — Durable Objects for real-time sync, D1 for durable history, and several Workers. There is no always-on server and (for the live path) no managed database.
History: Hackbox was migrated off a Node/Express/Socket.io + Postgres service (on Render, at
app.hackbox.ca) onto Cloudflare. That legacy service has since been shut down and its code removed from this repo — there is no backwards-compatible fallback transport any more. All work goes in the Cloudflare Workers below.
Monorepo layout
| Dir | Worker | What it is |
|---|---|---|
relay/ |
hackbox-relay |
The realtime core: a Room Durable Object (partyserver) holding live member state + a replay cache, and writing permanent history to D1. |
api/ |
hackbox-api |
A Hono Worker — the HTTP front door (POST /api/rooms, room existence probes). |
client/ |
hackbox-client |
The Vue 3 player SPA, served as a static-assets Worker. |
admin/ |
hackbox-admin |
A Nuxt 3 admin dashboard (Access-protected) reading room/member history from D1 + live presence from the relay. |
db/ |
— | The Cloudflare D1 schema (schema.sql) — permanent room/member history. |
docs/ |
— | The public docs site (Nuxt Content, hackbox.ca/docs). Source under docs/content/. |
Routing — apex path prefixes, not subdomains
All Workers are served under the apex hackbox.ca via path prefixes rather than
api./relay. subdomains (subdomains get reset by some users' SNI-filtering
middleboxes; the apex is the durable fix). Order matters — more specific routes
win:
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.
- yesterday First seen · 319 lines · 4,287 tokens per session scan A 0aa7a6d26a39
hackbox CLAUDE.md is an instructions file published in the GitHub repository devanhurst/hackbox (5 stars, last pushed 27d ago), licensed MIT. It adds 4,287 tokens to every session, about $0.0214 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.