What is cursor-cdp-control?

A command-line connection for controlling the Cursor code editor through Chrome DevTools Protocol, a browser-style debugging interface. It can work with both Cursor's standalone Agent window and its editor chat panel.

Use it to check Cursor's connection, list windows, start chats, switch models or projects, browse chat history, take screenshots, and create agents. Cursor must be started with remote debugging enabled.

It lets you operate Cursor from a terminal instead of switching between the terminal and the editor. This is useful for checking windows, sending prompts, reading chats, and managing projects from scripts or commands.

How toheart/cursor-agent configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to toheart/cursor-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/toheart/cursor-agent/main/.cursor/skills/cursor-cdp-control/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/toheart/cursor-agent

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/toheart/cursor-agent/cursor-cdp-control/github.svg)](https://agentmods.dev/skills/toheart/cursor-agent/cursor-cdp-control)

Your own site

<a href="https://agentmods.dev/skills/toheart/cursor-agent/cursor-cdp-control"><img src="https://agentmods.dev/badge/skills/toheart/cursor-agent/cursor-cdp-control/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/toheart/cursor-agent/cursor-cdp-control"><img src="https://agentmods.dev/badge/skills/toheart/cursor-agent/cursor-cdp-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,020 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00112	$0.01020
Opus 5.5	$0.00045	$0.00408
Sonnet 5.5	$0.00022	$0.00204
Haiku 4.5	$0.00011	$0.00102

Measured 2mo ago against content hash 6e50ce5ac095, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cursor-cdp-control 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 2mo 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.

.cursor/skills/cursor-cdp-control/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor CDP Control

Control Cursor IDE via opencli cursor commands using Chrome DevTools Protocol (CDP).

All commands auto-detect window type:

Agent window - Cursor 3 standalone Agent window (title = "Cursor Agents")
Editor window - Traditional editor with embedded Chat panel

Prerequisites

1. Launch Cursor with CDP port enabled

Close all Cursor instances first, then relaunch:

# Windows
"C:\Program Files\cursor\Cursor.exe" --remote-debugging-port=9226

# macOS
/Applications/Cursor.app/Contents/MacOS/Cursor --remote-debugging-port=9226

Notes:

Must close all Cursor windows before launching (Electron single-instance lock)
Default port is 9226; customize with --port argument
Do not use the cursor CLI tool (it invokes cli.js, not the GUI)

2. Install plugin dependencies

cd ~/.opencli/plugins/ksh-plugin-cursor && npm install

3. Verify connection

opencli cursor status

Command Reference

Command	Description	Example
`cursor status`	CDP connection status	`opencli cursor status`
`cursor list`	List all windows (Agent/Editor)	`opencli cursor list`
`cursor new-chat`	Open a new Agent/Chat tab	`opencli cursor new-chat`
`cursor project`	List available projects (Agent only)	`opencli cursor project`
`cursor project-switch`	Switch project by fuzzy match (Agent only)	`opencli cursor project-switch "llm-wiki"`
`cursor send`	Send prompt and wait for reply	`opencli cursor send "refactor this code"`
`cursor read`	Read current Chat content	`opencli cursor read --limit 10`
`cursor history`	Browse chat history sessions	`opencli cursor history "test"`
`cursor model`	List available models	`opencli cursor model`
`cursor model-switch`	Switch model by fuzzy match	`opencli cursor model-switch "sonnet"`
`cursor screenshot`	Capture screenshot	`opencli cursor screenshot chat`

See references/commands.md for detailed parameters.

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/commands.md 4.8 KB

Changes

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.

2mo ago First seen · 112 lines · 112 tokens per session scan A 6e50ce5ac095

Subscribe to this mod's changes

cursor-cdp-control is a skill published in the GitHub repository toheart/cursor-agent (68 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,020 once invoked, about $0.0004 per session on Opus 5.5. 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.

Building agents

cursor-cdp-control next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cursor-cdp-controltoheart/cursor-agent	Skill	68	5mo ago	Apache-2.0	A	112	Cursor
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

cursor-agent: Skill for Cursor