Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/andreilungeanu/cursor-delegate-mcpWrote 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.
[](https://agentmods.dev/plugins/andreilungeanu/cursor-delegate-mcp/cursor-delegate-mcp)<a href="https://agentmods.dev/plugins/andreilungeanu/cursor-delegate-mcp/cursor-delegate-mcp"><img src="https://agentmods.dev/badge/plugins/andreilungeanu/cursor-delegate-mcp/cursor-delegate-mcp/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.
<a href="https://agentmods.dev/plugins/andreilungeanu/cursor-delegate-mcp/cursor-delegate-mcp"><img src="https://agentmods.dev/badge/plugins/andreilungeanu/cursor-delegate-mcp/cursor-delegate-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cursor-delegate 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 yesterday.
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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "cursor-delegate",
"displayName": "Cursor Delegate",
"version": "2.5.2",
"description": "Delegate coding tasks to cursor-agent over ACP, with structured results, plan mode, and clarification handling.",
"author": {
"name": "Andrei Lungeanu",
"email": "[email protected]"
},
"homepage": "https://github.com/andreilungeanu/cursor-delegate-mcp",
"repository": "https://github.com/andreilungeanu/cursor-delegate-mcp",
"license": "MIT",
"logo": "assets/logo-light.png",
"mcpServers": "./.claude-plugin/mcp.json",
"hooks": "./.claude-plugin/hooks.json",
"keywords": [
"mcp",
"cursor",
"cursor-agent",
"acp",
"agent-client-protocol",
"claude-code",
"composer",
"delegation"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 1 MCP server travel with it, and installing the plugin installs all of them — 122 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
4 files beside plugin.json 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.
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.
- yesterday Changed b031e8b89ff4
- 11d ago Changed 033dde095500
- 1mo ago Changed 81da0f713289
- 1mo ago Changed 1305907ac1f0
- 1mo ago Changed 69627dc50b7e
- 1mo ago First seen · 28 lines scan A 5d9623524a28
cursor-delegate is a plugin published in the GitHub repository andreilungeanu/cursor-delegate-mcp (9 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
wt-agent-hooks
Forward Gemini CLI hook events to Windows Terminal for WTA display.
software-factory
Lanes, tickets, and a human merge. Same skills as Cursor, Grok, and Codex.
agent-ecosystem-generator
Generate a validated Claude Code ecosystem (orchestrator + N subagents + M skills + MCPs) from a brief. Use when the user asks to scaffold, bootstrap, or design a multi-agent system, agent team, or orchestration plugin.
comparative-landscape-brief
Market intelligence for product and GTM leaders. Five skills sharing one hardened research subagent that verifies quantitative claims against third-party sources and refuses instructions embedded in fetched pages. Compare 3 to 8 entities side by side, brief one company in depth, build a competitive landscape and…
ai-adoption-os
Turn AI curiosity into a working plan at a 25 to 150 person company. Four skills an operator runs in sequence or standalone: inventory the tool stack and find where AI fits, survey employees to surface the AI use already happening, build a prompt cookbook for your actual vertical, and assemble an internal enablement…
job-interview-meeting-preparation
Prepare for a high-stakes meeting by first choosing which one it is: an interview, a peer or stakeholder, an operator, or a board member or other CxO. Researches the company and stakeholder, tailors the conversation to that meeting type, and produces an in-conversation brief and a printable HTML and PDF one-pager. Run.