Tooling·Originally published Aug 19

👀43views

🔥88Impact Score

Cursor upgrades cloud agents with /goal tracking, PR event hooks, and isolated VM subagents

Cursor upgraded its cloud agents to persist long-lived objectives via /goal commands, auto-subscribe to PR discussions and CI events, and spawn subagents inside isolated VM sandboxes. Each subagent runs on a fresh repository clone for parallel testing without dirtying the working branch.

Key Takeaways

✓Introduces /goal state machines allowing cloud agents to drive multi-hour refactors to completion.
✓Watches GitHub PR comments and CI webhooks to automatically apply requested review changes.
✓Subagents execute inside isolated VM sandboxes for parallel, safe hypothesis testing.

⚡

Key Decision Metrics at a Glance

TL;DR Verdict

🏆 Benchmark RankRank

No model benchmark in this story · see current rankings

Full Leaderboard→

💰 Cost & PlansCompare

API & Subscription

Compare Plans↗

🛠️ Ecosystem & IDERules

Cursor Composer (Agent Mode)

Setup IDE Rules↗

🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗

Up NextCursor Cloud Agents Can Now Build and Share Interactive Canvases for Live Dashboards and Technical Reports

Read Now→

About this article: compiled by the AICoder newsroom with AI assistance, based on the official and press sources cited above and checked against human-set editorial standards; vendor-reported figures are attributed as such.

🧭

AI Coding Ecosystem & Action Hub

Integrated benchmark rankings, plan discounts & IDE rules

🎯Mentioned Models & Agents

🤖 Agent★ Pro

Cursor Composer (Agent Mode)

🏆 Rank 🛠️ Rules ↗

🌐 Vendor

Cursor (Anysphere)

San Francisco, USA

Side-by-side comparison

→

💰

Pricing & Plans

21 vendors cost comparison

→

🛠️

Rules Generator

Cursor / Claude Code rules

→

📰

Up Next & Recommended Stories

View All News→

NEXT ➔

Next Featured Story

Cursor Cloud Agents Can Now Build and Share Interactive Canvases for Live Dashboards and Technical Reports

Read Now→

Tooling6d ago

Cursor marketplace served a tampered Claude Code 2.1.313 extension with an SSH backdoor, affecting at most 5,000 users

Cursor posted a security notice on X at 07:46 UTC on Oct 30: version 2.1.313 of Anthropic.claude-code in its VS Code extension marketplace was a maliciously modified build, not developed by Anthropic, available from about 2:27am to 1:35pm PT on Oct 29 and affecting at most 5,000 users. The payload collects host details, adds an attacker SSH key, tries to open a reverse SSH tunnel and installs persistence. Cursor pulled the version, shut down and rebuilt the marketplace, rotated keys and had the attacker server taken offline; it asks users to update Claude Code for VS Code to 2.1.314 and follow the check and cleanup steps in its blog post.

Tooling8d ago

Cursor Design Mode adds Annotate: point, draw and edit text on your running app to send visual prompts to agents

On Oct 27 Cursor announced Annotate for Design Mode: in the Agents Window browser you can click elements, box an area, draw markup, edit text in place or tweak CSS, and each note is sent to the agent with element details and a screenshot so it can edit the code. The post says you can also review designs at different screen sizes. It needs Cursor 3.24.18 or later, and the shortcut is Cmd+Shift+D.

Tooling9d ago

Cursor adds DeepSeek V4.1 Flash: all four effort levels sit on the CursorBench 4.0 cost frontier, with Max scoring 47.7% at $0.98 per task

Cursor announced on Oct 26 (UTC) that DeepSeek V4.1 Flash is now available in Cursor and can be turned on under Cursor Settings > Models. Cursor says every effort level sits on the CursorBench cost frontier, from $0.60 to $0.98 per task, with no model scoring higher at those prices. The official CursorBench 4.0 leaderboard lists DeepSeek V4.1 Flash 1017 at 47.7% on Max ($0.98 per task), 46.3% on Medium ($0.80), 45.6% on High ($0.77) and 44.9% on Low ($0.60). The top score on the board, Opus 5.5 Max, is 57.8% but costs $13.43 per task.

🔥

Trending Radar

TOP 5

Ranked by reader attention & deep impact

Explore All 1,200+ Radar News→

←Back to news list

Discussion & Comments

Connect with AI developers to exchange benchmark insights.

No comments yet. Be the first to share your thoughts!

Cursor upgrades cloud agents with /goal tracking, PR event hooks, and isolated VM subagents

Key Takeaways

Key Decision Metrics at a Glance

Turn your technical choice into a development budget

AI Coding Ecosystem & Action Hub

Cursor Composer (Agent Mode)

Cursor (Anysphere)

Up Next & Recommended Stories

Cursor Cloud Agents Can Now Build and Share Interactive Canvases for Live Dashboards and Technical Reports

Cursor marketplace served a tampered Claude Code 2.1.313 extension with an SSH backdoor, affecting at most 5,000 users

Cursor Design Mode adds Annotate: point, draw and edit text on your running app to send visual prompts to agents

Cursor adds DeepSeek V4.1 Flash: all four effort levels sit on the CursorBench 4.0 cost frontier, with Max scoring 47.7% at $0.98 per task

Trending Radar

OpenAI gives ChatGPT Pro and Business subscribers up to $500 a month in API credits to build apps and agents

OpenAI unveils three AI-produced results: a claimed refutation of the Exponential Time Hypothesis, local smoothing in every dimension, and an existence proof for QCD

X discussion: viral posts claim Anthropic "quietly killed" Claude's reverse engineering with the REA toolkit after a Samsung TV firmware teardown went viral; no official statement yet

Artificial Analysis launches Coding Agent Index v2.0: FrontierCode from Cognition replaces DeepSWE, and Claude Code with Opus 5.5 leads at 61.7

Shanghai AI Lab Releases Sage-A1.5: A 35B MoE Agentic Model Advancing Long-Horizon Software and Scientific Discovery

Discussion & Comments