cursor-agent

cursor-agent is an agent for coding agents from felipeinf/cursor-for-claude. It costs 23 tokens per session (273 once invoked), scanned A, original, MIT.

A handoff tool that sends a substantial coding task from Claude Code to Cursor through the local cursor-agent command-line tool.

In plain words
What is it for?
Use it to start, continue, resume, or run a fresh Cursor task, including background or read-only runs.
Why use it?
It lets Cursor carry out delegated coding work while preserving the task wording and selected run options.

Agent

Part of the cursor plugin — 2 skills, 5 commands, 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/felipeinf/cursor-for-claude/cursor-agent
Clone the repo
git clone --depth 1 https://github.com/felipeinf/cursor-for-claude

Or install cursor, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 agent.

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.

agentmods badge for cursor-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipeinf/cursor-for-claude/cursor-agent.svg)](https://agentmods.dev/agents/felipeinf/cursor-for-claude/cursor-agent)
Your own site
<a href="https://agentmods.dev/agents/felipeinf/cursor-for-claude/cursor-agent"><img src="https://agentmods.dev/badge/agents/felipeinf/cursor-for-claude/cursor-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00273
Opus 5 $0.00012 $0.00137
Sonnet 5 $0.00005 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 3d ago against content hash 4b14c8b649a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-agent 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 3d 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.

plugins/cursor/agents/cursor-agent.md · 25 lines

What it actually says

You are a thin forwarding wrapper around the Cursor companion task runtime.

Use exactly one Bash call:

node "${CLAUDE_PLUGIN_ROOT}/scripts/cursor-companion.mjs" task ...

Forward the user's request to task, stripping only Claude-side routing flags from the natural-language prompt. Default to write-capable Cursor runs. Add --read-only only when the user requested read-only behavior. Map --continue to task --continue, --resume <id> to task --resume <id>, and --fresh to a fresh task call without resume flags. Pass through --background, --wait, --model, --mode, --read-only, and --sandbox as companion flags. Preserve the user's task text as-is apart from stripping routing flags. Do not inspect files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do follow-up work. Return stdout verbatim. Do not add commentary before or after it.

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.

  1. 3d ago First seen · 25 lines · 23 tokens per session scan A 4b14c8b649a2

Subscribe to this mod's changes

cursor-agent is an agent published in the GitHub repository felipeinf/cursor-for-claude (7 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 273 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Related

Other agents, from other repositories

critic

Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.

codecast-sh/codecast · 28 tokens

architecture-reviewer

Analyzes codebase architecture for structural issues, dependency direction, modularity, and separation of concerns. Use after significant refactors or when starting work on an unfamiliar codebase.

faizkhairi/claude-code-blueprint · 39 tokens

devops-engineer

Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.

faizkhairi/claude-code-blueprint · 29 tokens

frontend-specialist

Expert frontend engineer for building UI components, pages, forms, state management, and client-side logic. Adapts to any frontend framework based on project context.

faizkhairi/claude-code-blueprint · 36 tokens

project-architect

Designs system architecture, plans features, breaks work into tasks, and makes technology decisions. Use when starting new projects or designing new features.

faizkhairi/claude-code-blueprint · 32 tokens

t-800-cloud-hub-lead

Оркестратор отдела Cloud Hub Automation Setup: discovery памяти проекта, план Blank Hub + Client, selective fan-out analyst|prompt|pack|smoke, materialization gate в {memory}/cloud-hub/. Use when /t800-cloud-hub или /t800-hub-setup, настройка универсальных Cursor Automations Hub+Client, черновики…

Khar-AG/t-800-agent · 131 tokens