cursor-bridge
v6.0.8Evidence-backed Cursor Context Engine search and bounded Cursor Agent execution, including a UI-suppressed minimal runtime.
By VanyangyangLicense: MIT78 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 3 skill or MCP entries
- Source updated
- Oct 2, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install cursor-bridge for Codex and Claude Code
codex plugin marketplace add Vanyangyang/cursor-bridge
codex plugin marketplace upgrade vanyangyang
codex plugin add cursor-bridge@vanyangyangPaste and run these commands in a terminal with Codex. They add and refresh the vanyangyang catalog, then install this plugin.
Compatibility: the page URL and API slug “cursor-bridge” remain stable.
- Codex:
cursor-bridge@agent-plugin-marketplace→cursor-bridge@vanyangyang
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/Vanyangyang/cursor-bridgeClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/cce-routing/SKILL.md├── skills/cursor-delegate/SKILL.md└── .mcp.json
Included Skills2
Use Cursor Bridge's read-only cursor_context_engine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for questions such as where something is implemented, what owns state, how a project flow works, or when local search would otherwise guess paths or repeat blind queries; for these semantic questions, try CCE before generic context-mode or grep discovery. Do not use when a known exact file or symbol can answer the question through direct reading or exact search, for content already loaded in context, trivial single-file edits, tests, logs, builds, Git work, external documentation, or when the user opts out of Cursor. Verify returned path:line evidence in the real files.
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session, including phrases such as '持续会话', '同一个 Cursor 会话', or 'continue the Cursor session'. Generic '继续' is not enough to reuse a session. Poll each turn compactly by task_id, then retrieve its normal terminal reply with detail=result and verify it in the primary agent. Do not use when the user opts out, cursor_do is unavailable or administrator-disabled, or for product direction, architecture decisions, exclusive GUI operations, formal verification verdicts, governance state decisions, or unbounded investigation.
MCP servers1
- command
- node
- args
- ./dist/cursor-bridge.mjs
- cwd
- .
Plugin manifests2
{
"name": "cursor-bridge",
"version": "6.0.8",
"description": "Evidence-backed Cursor Context Engine search and bounded Cursor Agent execution, including a UI-suppressed minimal runtime.",
"author": {
"name": "Vanyangyang"
},
"repository": "https://github.com/Vanyangyang/cursor-bridge",
"license": "MIT",
"mcpServers": {
"cursor-bridge": {
"command": "node",
"args": [
"./dist/cursor-bridge.mjs"
],
"cwd": ".",
"default_tools_approval_mode": "approve"
}
},
"interface": {
"displayName": "Cursor Bridge",
"shortDescription": "Evidence-backed CCE search and bounded, optionally continuous cursor_do execution.",
"longDescription": "Use Cursor's indexed Agent as an adaptive Cursor Context Engine. State the intent once; Cursor chooses the necessary investigation depth and returns compact path:line evidence instead of guessed locations. When execution is useful, cursor_do supports isolated FIFO or independent Agent tasks plus explicit persistent sessions for continued delivery to the same verified Agent. The supervising host retains scope, review, and final control. User-facing prose follows the task language while machine fields remain stable. Minimal runtime keeps CCE and execution tools available while hiding the Windows Cursor UI.",
"developerName": "Vanyangyang",
"category": "Developer Tools",
"capabilities": [
"Interactive"
],
"defaultPrompt": [
"Find where this project implements a behavior and return verified path:line evidence.",
"Delegate one clearly bounded implementation task to Cursor and verify the real changes.",
"Initialize CCE workspace to C:\\absolute\\project\\path."
],
"websiteURL": "https://github.com/Vanyangyang/cursor-bridge"
}
}{
"name": "cursor-bridge",
"version": "6.0.8",
"description": "Evidence-backed Cursor Context Engine search and bounded, explicitly continuous Cursor Agent execution, including a UI-suppressed minimal runtime.",
"author": {
"name": "Vanyangyang"
},
"license": "MIT",
"repository": "https://github.com/Vanyangyang/cursor-bridge"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[cursor-bridge on Agent Plugins Marketplace](https://pluginsmp.com/plugins/cursor-bridge)