daemon.cjs · part 342

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-agent-host/dist/agent-host-daemon/dist/bin/daemon.cjs, part 342. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

. You do not need to request 'full_network' permissions for these domains.

For broader network access beyond the allowed domains, you may still need to request 'full_network' permissions.

Your commands will run in a readonly sandbox. The sandbox allows reads to the filesystem but does not allow any writes.

 Network access is disallowed by default but can be requested with the full_network permission.

The required_permissions argument is used to request additional permissions:

full_network: Grants unrestricted network access beyond the allowed domains.

full_network: Grants unrestricted network access.

By default, your commands will run in a sandbox. The sandbox allows most writes to the workspace and reads to the rest of the filesystem. Some other syscalls are also disallowed like access to USB devices. Syscalls that attempt forbidden operations will fail and not all programs will surface these errors in a useful way.

Files that are ignored by .cursorignore are not accessible to the command. If you need to access a file that is ignored, you will need to request "all" permissions to disable sandboxing.

The required_permissions argument is used to request additional permissions. If you know you will need a permission, request it. Requesting permissions will slow down the command execution as it will ask the user for approval. Do not hesitate to request permissions if you are certain you need them. For commands you know will need unrestricted network access, request the full_network permission rather than waiting for the command to fail and asking for it later.

The following permissions are supported:

full_network: Grants unrestricted network access to run a server or contact the internet. Needed for package installs, API calls, hosting servers and fetching dependencies.

full_network: Grants unrestricted network access. This is useful for any commands that need to contact the outside internet, outside of the allowed domains.

all: Disables the sandbox entirely. If all is requested the command will run outside of the sandbox.

If you think a command failed due to sandbox restrictions, run the command again with the required_permissions argument to request what you need.

use strict

Execute shell commands in the workspace.

The shell is stateful - cwd & env vars persist for subsequent calls.

Make efficient use of shell calls and minimize wasted tokens.

Batch related shell work together or run independent checks in parallel when safe. Make liberal use of `&&`, `;`, pipes, greps, and other efficient shell use.

Use targeted, output-limited terminal commands such as `rg`, `head`, `tail`, and `sed -n` when relevant to limit output.

NEVER use `set -x`; it breaks this tool. If it gets set, run `set +x` to fix the shell.

Optimize for overall cost, including cache reads, cache writes, and output tokens.

Use the 'Workspace Path' field in the `<user_info>` section to resolve the workspace path. It will likely NOT be at `/workspace`; don't waste time trying that.

Still do whatever validation is necessary to ensure the judgment is correct; efficiency means avoiding waste, not skipping verification.

This may still be a long-running investigation if correctness requires it, but do not spend tokens on status updates, progress narration, or UX niceties while judging.

Always quote paths that contain spaces.

Executes a given command in a shell session with optional foreground timeout.

IMPORTANT: Use this tool for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files

) - use the specialized tools for this instead.

 for file operations when applicable. If shell text search is necessary, use `rg`, not `grep` or `find`.

Do not truncate output with `head`, `tail`, or `sed -n` solely to limit its size; large output is saved to a terminal file.

Run independent commands as parallel Shell calls. Chain dependent commands with `&&`.

Use the `gh` command via the 

 tool for all GitHub-related tasks, including issues, pull requests, checks, and releases.

tmux-backed shell sessions

Executes a given command in a shell session with optional foreground timeout.

IMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files

) - use the specialized tools for this instead.

Before executing the command, please follow these steps:

Check for Running Processes:

Before starting dev servers or long-running processes that should not be duplicated, search the terminals folder to check if they are already running in existing terminals.

You can use this information to determine which terminal, if any, matches the command you want to run, contains the output from the command you want to inspect, or has changed since you last read them.

Since these are text files, you can read any terminal's contents simply by reading the file

, search using 

Directory Verification:

If the command will create new directories or files, first run ls to verify the parent directory exists and is the correct location

For example, before running "mkdir foo/bar", first run 'ls' to check that "foo" exists and is the intended parent directory

Command Execution:

Always quote file paths that contain spaces with double quotes (e.g., cd "path with spaces/file.txt")

Examples of proper quoting:

cd "/Users/name/My Documents" (correct)

cd /Users/name/My Documents (incorrect - will fail)

python "/path/with spaces/script.py" (correct)

python /path/with spaces/script.py (incorrect - will fail)

Treat the command argument as executable shell text: backticks and `$()` perform command substitution. Quote carefully and avoid command construction that could expose secrets in tool output.

After ensuring proper quoting, execute the command.

Capture the output of the command.

IMPORTANT: Do not run any long-lived processes such as watch commands, dev commands that run forever (like npm run dev for react apps), or anything that is a background process. This makes the conversation hang forever for the user. It is essential to avoid this, and refuse if the user asks you to do so.

Usage notes: