One tip:

Cursors composer-1 model is pretty fast. Which means you could also try to run the above prompt via cursor CLI.

Link to the repo:
github.com/regenrek/op...

Instead of switching between MCP servers like chrome devtools, context7, linear... you create a single workflow (e.g., frontend_tools) that orchestrates them. Your MCP client (Cursor, Claude Code) sees minimal needed tools.

Install & Usages here:
github.com/regenrek/co...

Multiple way to serve context. But you always should keep an eye on your context window and don't pollute it with unnecessary or wrong information. Thats your "job" as agentic engineer.

- The agent is able to read linters
- The agent has access to externals tools served via CLI/MCP
- The agent has memory of your past decisions
- The agent has access to tasks written in .md

What does high context mean?

- The agent is able to run tests against your codebase.
- The agent has access logs
- The agent has rules available (AGENTS .md)
- The agents has access to semantic search (thats why its still useful to index your codebase)
- The agents has relevant docs available

To explain: With better models and a codebase that serves as context you can just talk to the model.

The less context you have, the more specific your prompt should be.

You'll receive findings (high, medium, low), including an analysis of missing tests for the given plan.

The changelog contains a complete list of all updates.

composer-alpha-1 is now my go model for fast ask/answer/edit tasks.

GPT-5 is still excellent for solving complex, high-level problems (especially GPT-Pro and Deep Research), but it’s not ideal for quick edits.

Using both models together has given me my most productive workflow so far.

Summary: I've tested the new version for a few days and really enjoyed using the new composer model.

Compared to Claude Sonnet and GPT-5, it feels closer to Sonnet but with much better code understanding and results inside Cursor. (Not talking about CC Sonnet)