Cursor Tui

Spawn and relay Cursor Agent's CLI (`agent` binary) as an interactive passthrough. Use when the user wants to run Cursor Agent in a directory, ask it questio...

Security Scan

Instructions and requirements are coherent for a CLI passthrough: the skill only needs the Cursor 'agent' binary and its SKILL.md tells the agent how to spawn and relay the CLI session.

Purpose & Capability

Name/description request the ability to spawn and relay Cursor's CLI; the skill only requires the cursor / cursor-agent binaries and no unrelated credentials or installs. The declared requirements match the stated purpose.

Instruction Scope

SKILL.md stays focused on spawning a PTY background session, polling output, and relaying user input. It does instruct the agent to run the Cursor binary in an arbitrary project directory and to relay Cursor output verbatim — this is consistent with a transparent passthrough but means any sensitive output produced by Cursor will be relayed to the user.

Install Mechanism

There is no install spec (instruction-only), so nothing is downloaded or written to disk by the skill itself.

Credentials

No environment variables, credentials, or config paths are requested. The absence of extra secrets is proportional to the skill's purpose.

Persistence & Privilege

always is false and the skill is user-invocable. Autonomous model invocation is allowed by platform default but not an additional privilege requested by the skill.

Assessment

This skill acts as a transparent proxy to a local Cursor 'agent' process — it will spawn the binary in whatever directory you specify and relay Cursor's output and permission prompts verbatim. Before using: ensure the cursor/cursor-agent binaries on your PATH are the authentic versions you trust; avoid running the agent in directories containing secrets you don't want echoed back; do not blindly accept workspace-trust or approval prompts relayed by the tool (the instructions correctly tell the skill to ask you). If you are uncomfortable with an automatic agent being spawned, don't invoke the skill or restrict autonomous invocation in your agent configuration.

Cursor CLI Passthrough

Spawn Cursor's agent in a PTY background session and relay its output and the user's inputs as a silent passthrough.

Spawning

{ "tool": "exec", "command": "agent", "pty": true, "background": true, "workdir": "<project-dir>", "yieldMs": 3000 }

• Always set workdir to the project directory the user wants to work in (not the OpenClaw workspace).
• If the user doesn't specify a directory, ask before spawning.
• Note: agent requires workspace trust on first run in a directory — relay the trust prompt and send the user's choice (e.g. a, w, or q) via process send-keys.

Relaying output

After spawning or sending input, poll for output:

{ "tool": "process", "action": "poll", "sessionId": "<id>", "timeout": 15000 }

• Strip ANSI escape codes mentally, but relay the content faithfully and verbatim.
• Do not wrap output in code blocks or quote formatting.
• Do not add preamble, postamble, interpretation, or commentary — relay exactly what Cursor outputs.
• If you need to add context or a note, prefix that line with your name in brackets (e.g. [YourName]) so it's clearly distinguished from Cursor's output.
• Permission prompts: When Cursor shows a "Run this command?" or any approval dialog, relay it verbatim to the user and wait for their response. Never approve or deny on the user's behalf.
• After relaying the agent's response, append a single prompt line: cursor @ <workdir> — use ~ in place of the user's home directory (e.g. ~/repos/myproject not /home/username/repos/myproject).

Sending user input

For single-line prompts:

{ "tool": "process", "action": "submit", "sessionId": "<id>", "data": "<text>" }

For multi-line prompts:

{ "tool": "process", "action": "paste", "sessionId": "<id>", "text": "<text>" }

Then submit with Enter:

{ "tool": "process", "action": "send-keys", "sessionId": "<id>", "keys": ["Enter"] }

For other special keys (arrow keys, Escape, etc.):

{ "tool": "process", "action": "send-keys", "sessionId": "<id>", "keys": ["ArrowUp"] }

Use @filename or @directory/ in interactive prompts to add more context.

Ending the session

Send /quit or Ctrl+D (double-press):

{ "tool": "process", "action": "submit", "sessionId": "<id>", "data": "/quit" }

Notes

• agent is Cursor's CLI binary. cursor-agent is a backward-compatible alias.
• The binary must be on PATH. If not found, check TOOLS.md for custom binary paths.
• One session at a time is typical; use process list to check for orphaned sessions.