Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Foil Sandbox

    1

    Lets your agent run anything in a 25 ms copy-on-write branch of the repo, with secrets hidden, network allowlisted, and nothing reaching your folder until you review the diff and commit.

    Free

    Security scanned
    Foil Sandbox

    Foil Sandbox

    Example session with this skill installed

    Run the install script from this new dependency in a branch called "test-install". Hide my .env files and block all network access. Show me the diff when done.

    • Read your context and instructions
    • Compiled the foil sandbox

    I have executed the install script within a protected copy-on-write branch. The environment was restricted with no network access and all .env files were hidden from the process.

    Sandbox Execution Results: test-install

    File PathActionDescription
    package-lock.jsonModifiedUpdated dependency tree
    package.jsonModifiedAdded new-dep to dependencies
    node_modules/.bin/new-depCreatedBinary installed
    .envHiddenProcess attempted to list but was denied
    audit.logCreated0 network requests attempted
    --- a/package.json
    +++ b/package.json
    @@ -12,5 +12,6 @@
       "dependencies": {
    -    "existing-pkg": "^1.0.0"
    +    "existing-pkg": "^1.0.0",
    +    "new-dep": "^2.4.1"
       }
     }
    

    Next steps

    1. Run foil run -b test-install -- npm test to verify the installation works as expected.
    2. Use foil commit test-install to apply these changes to your actual repository.
    3. Use foil abort test-install if you want to discard these changes entirely.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Development involves running code you didn't write and making changes that shouldn't touch your disk until they are verified. This skill enables your agent to execute commands in a copy-on-write branch of your repository.

    What it does

    • Instant branching creates a copy-on-write environment in roughly 25ms regardless of repository size.
    • Strict isolation blocks network access, hides sensitive files like .env, and restricts writes to the branch.
    • Reviewable diffs allows the agent to generate full patches or summaries of changes before any commit to the real folder.
    • Parallel execution supports running multiple attempts of a task simultaneously to select the most efficient passing result.
    • Audit logging tracks blocked network requests, accessed files, and attempted modifications for security reviews.

    How it works

    1. Initialize a branch using foil run -b NAME to execute commands in a protected workspace.
    2. Apply isolation by adding flags like --strict, --no-network, or --hide to protect credentials and system paths.
    3. Inspect the changes using foil diff or foil diff --patch to verify what the command modified.
    4. Finalize or discard by using foil commit to merge changes into the actual folder or foil abort to wipe them.

    Frameworks & tools

    Built with Rust. Compatible with Linux (kernel 5.12+) and macOS 12+. Works with any language or package manager including npm, cargo, and python.

    Why this beats prompting it yourself

    Manual prompts cannot enforce filesystem-level isolation or network blocks. This skill ensures the agent physically cannot touch your sensitive files or call home, providing a hardware-backed safety layer that text instructions alone lack.

    Use cases

    • Test untrusted PRs by running test suites in a zero-network, read-only sandbox.
    • Safe refactoring to see the full impact of a major code migration before applying it.
    • Secret management to run commands while explicitly hiding .env and SSH keys.
    • Automated fixing to try three different logic approaches and pick the one with the smallest diff.

    Known limitations

    Does not support nested sandboxes on macOS due to Seatbelt limitations. Requires Linux kernel 5.12 or higher for OverlayFS support.

    Requires Linux kernel 5.12+ or macOS 12+. Seatbelt sandboxes on macOS cannot be nested. Commands requiring root or Docker inside the branch are not supported.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    GitHub

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    Allowed Hosts

    raw.githubusercontent.com
    Listedtoday

    What's inside

    Frequently Asked Questions

    Foil sandbox creates a virtual copy-on-write branch of your repository in about 25ms, allowing your AI agent to test code or refactor files in a secure environment without affecting your actual local storage or sensitive credentials.

    The skill is compatible with Linux (kernel 5.12+) and macOS 12+, and it supports any programming language or tool including Node.js, Python, and Rust.

    Unlike prompts that rely on the agent's 'good behavior,' this skill uses hardware-backed filesystem isolation and network blocks to physically prevent the agent from accessing your .env files or making unauthorized web calls.

    Yes, you can initialize multiple branches simultaneously using `foil run -b`, allowing your agent to try different logic paths in parallel and select the one with the cleanest diff.

    Your purchase includes the full Rust-based binary, integration documentation for your AI agents, and access to all future version updates including performance optimizations and security patches.

    Foil provides a `foil diff` command that lets you review every single modification the agent made in the sandbox before you choose to either `commit` the changes to your disk or `abort` to wipe them.

    New in Security