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/arcboxlabs/arcbox/claude-mdgit clone --depth 1 https://github.com/arcboxlabs/arcboxWrote 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/arcboxlabs/arcbox/claude-md)<a href="https://agentmods.dev/instructions/arcboxlabs/arcbox/claude-md"><img src="https://agentmods.dev/badge/instructions/arcboxlabs/arcbox/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 | $0.03168 | $0.03168 |
| Opus 5 | $0.01584 | $0.01584 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
arcbox 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines for Coding Agents
Project Overview
ArcBox is a high-performance container and virtual machine runtime in Rust, targeting macOS (primary) and Linux. The goal is to surpass OrbStack on every metric.
The project is in alpha. Breaking changes (internal or user-facing) are acceptable — always prioritize consistency, coherence, and long-term maintainability, even if that means large-scale rewrites.
Performance Targets
| Metric | Target | OrbStack |
|---|---|---|
| Cold boot | <1.5s | ~2s |
| Warm boot | <500ms | <1s |
| Idle memory | <150MB¹ | ~200MB |
| Idle CPU | <0.05% | <0.1% |
| File I/O | ≥100% of the best competitor guest² | 75-95% (vs native, their claim) |
| Network throughput | >50 Gbps | ~45 Gbps |
¹ Host cost is the high-water mark of guest-touched pages, not the
configured memory_mb: a fresh idle 16 GB VZ VM measured ~718MB of
host phys_footprint (2026-08-01). But no macOS backend reclaims, so
that mark is a one-way ratchet — the guest freeing 3GB leaves the host
paying for it forever. Only HV can ever release it (VZ guest RAM lives
in Apple's XPC process, unreachable by madvise). Evidence in
engine/arcbox-engine/src/vm_lifecycle/balloon/mod.rs.
² Same-context comparison (container vs container, same-day pairing).
Cache-hot native is not a valid denominator for FUSE metadata —
methodology and current numbers in docs/fs-perf-limits.md.
Platform Priority
- P0: macOS Apple Silicon
- P1: macOS Intel
- P2: Linux x86_64/ARM64
Project Structure
common/— shared error types, constants, asset utilitiesvirt/— Virtualization.framework bindings, cross-platform hypervisor traits, VMM, VirtIO devices, VirtioFS, networking (NAT/DHCP/DNS)rpc/— protobuf definitions, gRPC services, vsock/unix transportruntime/— container state, OCI image/runtimeengine/— embeddable, daemon-free engine library (boot assets, machine images, VM/machine lifecycle, agent client; growing per the architecture charter in the company repo)computer/— agent-computer domain layer: transport-free sandbox protocols behind theSandboxHostseamapp/— core orchestration, API server, Docker Engine API compat, thin CLI (abctl, notarcbox), daemon binary (arcbox-daemon), facade crateguest/— in-VM agent (cross-compiled for Linux)tests/— test resources and fixture build scripts.agents/skills/— shared Claude Code skills (symlinked from.claude/skills/)docs/— supplementary documentation (boot assets, daemon lifecycle)
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 · 194 lines · 3,168 tokens per session scan A 9b7c64e47512
arcbox CLAUDE.md is an instructions file published in the GitHub repository arcboxlabs/arcbox (2,893 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,168 tokens to every session, about $0.0158 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 2026-08-30.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
SmolVM AGENTS.md
Instructions for CelestoAI/SmolVM, covering smolvm context, 🚀 project overview, 🧪 development, key commands and release checklist.
icloud-docker AGENTS.md
Instructions for mandarons/icloud-docker, covering icloud docker, quick reference, commands, architecture overview and key conventions.
MultiGen CLAUDE.md
Instructions for lingyuanli/MultiGen, covering claude.md, architecture, development commands, full stack (docker) and api (local).
Shinken CLAUDE.md
Instructions for Meirtz/Shinken, covering claude.md — guide for ai coding sessions in this repo, ⛔ the one hard rule: this is a public open-source project, layout, development commands and architecture (how the pieces connect).
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.