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 rules/cdbattags/ai/sandbox-domainsgit clone --depth 1 https://github.com/cdbattags/aiWrote 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/rules/cdbattags/ai/sandbox-domains)<a href="https://agentmods.dev/rules/cdbattags/ai/sandbox-domains"><img src="https://agentmods.dev/badge/rules/cdbattags/ai/sandbox-domains.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 | $0.00444 | $0.00444 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
sandbox-domains 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.
What it actually says
Cursor Sandbox Network Allowlist
CRITICAL: Every Cursor workspace should have a sandbox-domains.txt file at the workspace root with an allowlist of network domains for sandbox commands.
What It Does
When you run shell commands in Cursor, they run in a sandbox with restricted network access. The sandbox-domains.txt file tells Cursor which domains to allow through the sandbox firewall.
Without this file, commands that need network access (like pnpm install, git clone, API calls, etc.) will fail with network errors.
Required File Location
<workspace-root>/sandbox-domains.txt
Standard Allowlist for Development Projects
Create the file with this baseline (adjust based on your project's needs):
api.github.com, github.com, uploads.github.com, objects.githubusercontent.com, raw.githubusercontent.com, gist.githubusercontent.com, api.digitalocean.com, api.pulumi.com, luarocks.org, api.spotify.com, ws.audioscrobbler.com, pypi.org, files.pythonhosted.org, crates.io
Common Additions by Project Type
Node.js / JavaScript:
registry.npmjs.org, registry.yarnpkg.com
Python:
pypi.org, files.pythonhosted.org
Rust:
crates.io, static.crates.io, index.crates.io
Cloud providers:
api.digitalocean.com, storage.googleapis.com, s3.amazonaws.com
Package CDNs:
cdn.jsdelivr.net, unpkg.com, esm.sh
Verification
If you're getting network errors in shell commands, check:
- Does
sandbox-domains.txtexist at workspace root? - Are the required domains listed (comma-separated, single line)?
- Did you reload the workspace after adding it?
Gitignore
This file should be in .gitignore — it's workspace-specific configuration, not project code. Each developer may need different domains based on their toolchain.
Add to .gitignore:
sandbox-domains.txt
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 · 68 lines · 444 tokens per session scan A 18cb93370e47
sandbox-domains is a cursor rule published in the GitHub repository cdbattags/ai (4 stars, last pushed 6mo ago), licensed MIT. It adds 444 tokens to every session, about $0.0022 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 cursor rules, from other repositories
10-feature-development
Feature implementation workflow and engineering mindset.
11-template-conventions
Reusable building blocks shipped with this template - use them instead of writing new ones.
03-ui
UI, layout, theming and localization standards.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.
01-tech-stack
Android tech stack and project standards.