# Plan vs Act modes **URL:** \ **Category:** Guides\ **Created:** [January 22, 2025, 11:11am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550 "2025-01-22T11:11:08Z")\ **Posts on this page:** 20\ **Page:** 2
**Author:** ![DaleLJefferson](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/daleljefferson/32/20009_2.png) [@DaleLJefferson](https://forum.cursor.com/u/DaleLJefferson)\ **Post date:** [January 27, 2025, 8:34am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/21 "2025-01-27T08:34:01Z")
The strangest part of Cursor at the moment is the 4 operating modes 1. Chat 2. Chat with codebase 3. Compose normal 4. Compose agent Each have their own features and limitations and you can’t transition from one mode to another. It would be so much simpler to just have two 1. Plan 2. Act With a simple transition between the two modes ---
**Author:** ![youbistark](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/youbistark/32/28041_2.png) [@youbistark](https://forum.cursor.com/u/youbistark)\ **Post date:** [January 27, 2025, 10:26am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/22 "2025-01-27T10:26:54Z")
Thank you for this wonderful prompt, for token usage if you use two chat to do plan and act it will be more expensive ? or it’s the same since it’s just splitted? ---
**Author:** ![DaleLJefferson](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/daleljefferson/32/20009_2.png) [@DaleLJefferson](https://forum.cursor.com/u/DaleLJefferson)\ **Post date:** [January 27, 2025, 10:58am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/23 "2025-01-27T10:58:51Z")
Each request will be charged as per your plan but in my experience I use less requests because I catch issues early with the planning process. Both these use 3 requests Plan → Plan → Act vs Act → Fix → Fix In theory you can specify everything and create a meticulous plan with no way the AI can mess up and do it in one request. But I really want to get the AI doing the work, I give it a vague idea of what I want to happen and the AI puts a plan together and I refine it. ---
**Author:** ![youbistark](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/youbistark/32/28041_2.png) [@youbistark](https://forum.cursor.com/u/youbistark)\ **Post date:** [January 27, 2025, 11:12am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/24 "2025-01-27T11:12:13Z")
this is why i love your prompt he just do a plan without edit anything and then i affine his plan 🙂 ---
**Author:** ![stix121](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/stix121/32/16797_2.png) [@stix121](https://forum.cursor.com/u/stix121)\ **Post date:** [January 27, 2025, 2:41pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/25 "2025-01-27T14:41:45Z")
This has been a game changer for me, thank you! ---
**Author:** ![tomchambers2](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/tomchambers2/32/12476_2.png) [@tomchambers2](https://forum.cursor.com/u/tomchambers2)\ **Post date:** [January 29, 2025, 10:49am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/26 "2025-01-29T10:49:56Z")
I would really like to see a plan/act mode. I have switched over to cline but I’d switch back for this. Yes you can put it in the rules, but I find the rules always gets watered down over the chat, whereas if it’s in a particular mode each prompt I don’t have to remind it. ---
**Author:** ![condor](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/condor/32/73148_2.png) [@condor](https://forum.cursor.com/u/condor)\ **Post date:** [January 29, 2025, 3:00pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/27 "2025-01-29T15:00:26Z")
There is no issue with the chat staying in the plan or act mode in cursor. you do not have to remind it, i verified it. ---
**Author:** ![tomchambers2](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/tomchambers2/32/12476_2.png) [@tomchambers2](https://forum.cursor.com/u/tomchambers2)\ **Post date:** [January 29, 2025, 3:11pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/28 "2025-01-29T15:11:58Z")
That’s not my experience. I am always having to stop it from zooming off. ---
**Author:** ![DaleLJefferson](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/daleljefferson/32/20009_2.png) [@DaleLJefferson](https://forum.cursor.com/u/DaleLJefferson)\ **Post date:** [January 29, 2025, 4:21pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/29 "2025-01-29T16:21:14Z")
My understanding is Cursor uses a really small context (For performance and cost) much smaller than the Sonnet 200k limit. If you add any amount of files to the context or continue a compose session it will aggressively drop context. The plan mode will be the first to go, doing @.cursorrules or @plan.mdc if you are using the new style will force it to remember. The default prompt makes it really eager to write code, until Plan mode is built this is the best you can do. ---
**Author:** ![heyitschien](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/heyitschien/32/22494_2.png) [@heyitschien](https://forum.cursor.com/u/heyitschien)\ **Post date:** [January 30, 2025, 5:49am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/30 "2025-01-30T05:49:23Z")
I’ve been testing the Plan/Act mode while building a front-end web application, and I’m thoroughly enjoying the process. It’s amazing to see the confidence level displayed and watch the agent conduct proper investigations to increase its confidence rate. Thank so much @Dale for sharing this! It’s such a beautiful and effective process. I’ll continue working with it and look forward to seeing where it leads. ---
**Author:** ![Vanals](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/vanals/32/23335_2.png) [@Vanals](https://forum.cursor.com/u/Vanals)\ **Post date:** [January 30, 2025, 10:36pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/31 "2025-01-30T22:36:42Z")
Amazing! Thank you @DaleLJefferson I am just a bit confused about what is the latest best way to work: 1. An .mdx inside .cursor/rules/\*\*.mdx? With: ```auto There are two modes Plan Mode: This mode is read only, you should focus on information gathering, asking questions, and architecting a solution, output a plan Act Mode: This mode is read/write. You can make changes to code and perform actions If it seems the user wants you to do something that would require Act Mode, you should ask the user to switch to Act mode by typing "Act" - they will have to manually do this themselves. You do not have the ability to switch to Act Mode yourself, and must wait for the user to do it themselves once they are satisfied with the plan. You will start in plan mode Read files, check assumptions and include a confidence percent, if the score is less than 95% propose questions or actions to increase the score. ``` or… a single `mdc` file with the same Prompt? with same description? Am a bit confused if you could help! 1. Where the Rules for AI sits in all this Act Plan mode approach? Do you still use it? Do you still writ anything in the .cursorrules file? ![Screenshot 2025-01-30 at 22.42.59](https://us1.discourse-cdn.com/cursor1/original/3X/0/6/06146fe13098a1de8f4e12d3514864a94f3a23b0.png) 1. Lastly… In base of hat you use the chat… composer or agent? how do you navigate between these modes? if you do? Thank you ---
**Author:** ![voarsh](https://avatars.discourse-cdn.com/v4/letter/v/e36b37/32.png) [@voarsh](https://forum.cursor.com/u/voarsh)\ **Post date:** [January 31, 2025, 2:21am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/32 "2025-01-31T02:21:14Z")
I’ve just used it as a “global” system prompt and it seems to work well enough. This isn’t folder/file specific files, so it doesn’t need the new complex globbing? ---
**Author:** ![DaleLJefferson](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/daleljefferson/32/20009_2.png) [@DaleLJefferson](https://forum.cursor.com/u/DaleLJefferson)\ **Post date:** [January 31, 2025, 4:05pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/33 "2025-01-31T16:05:23Z")
Update: I’ve managed to really optimise this prompt, I’ve got it down to a single line. I’ve added this to my `Cursor Settings` \> `General` \> `Rules for AI` . “Ask the user for feedback before making any changes, you are here to advise and will only act when given explict permission to do so.” ---
**Author:** ![Vanals](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/vanals/32/23335_2.png) [@Vanals](https://forum.cursor.com/u/Vanals)\ **Post date:** [January 31, 2025, 8:56pm UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/34 "2025-01-31T20:56:48Z")
So is not doing anymore Plan and Act modes? why you think is better with ONLY that? I assume you adding it in the settings prompt? no files. PS: I tried it with deepseek r1 but didn’t feel like was followin the rules properly… I am switching back to cloude 3.5 for now ---
**Author:** ![decsters01](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/decsters01/32/10082_2.png) [@decsters01](https://forum.cursor.com/u/decsters01)\ **Post date:** [February 2, 2025, 7:42am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/35 "2025-02-02T07:42:16Z")
I usually do this in chat and then use the composer agent requests ---
**Author:** ![youbistark](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/youbistark/32/28041_2.png) [@youbistark](https://forum.cursor.com/u/youbistark)\ **Post date:** [February 3, 2025, 8:57am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/36 "2025-02-03T08:57:48Z")
i use the plan mode from @DaleLJefferson and it’s so much better, we need to have it natively on cusor or atleast pin this topic ---
**Author:** ![T1nker-1220](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/t1nker-1220/32/21166_2.png) [@T1nker-1220](https://forum.cursor.com/u/T1nker-1220)\ **Post date:** [February 6, 2025, 3:52am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/37 "2025-02-06T03:52:56Z")
![image](https://us1.discourse-cdn.com/cursor1/original/3X/3/4/3408b8d33d0ae39154400ae354d723ed309431ac.png) when I am on plan mode it’s everything okay but when I tried to say ![image](https://us1.discourse-cdn.com/cursor1/original/3X/8/6/8641e58eeb5ab4c6f2b70d6f7d858ec1ff2d7e69.png) ACT mode it’s not remembering anything from the plan ---
**Author:** ![joefaron](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/joefaron/32/19412_2.png) [@joefaron](https://forum.cursor.com/u/joefaron)\ **Post date:** [February 6, 2025, 4:27am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/38 "2025-02-06T04:27:30Z")
I’m curious what your eventual pre act context looks like… is it TDD centered? Any other hints? ---
**Author:** ![SamPeng87](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/sampeng87/32/21983_2.png) [@SamPeng87](https://forum.cursor.com/u/SamPeng87)\ **Post date:** [February 7, 2025, 8:51am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/39 "2025-02-07T08:51:23Z")
I tried this workflow, and it works very well. Especially the new tool \*.mdc. There’s no need to keep adding multiple mdcs in the context. For example, for global ones like this, you can define a notepads. Using them together, it enforces the use of plan.mdc. However, the prerequisite for the entire workflow to work is that the conversation should not be too long. If it gets too long, you might forget the whole plan. This is a limitation of the AI model. There isn’t a very good way to handle it. ---
**Author:** ![SamPeng87](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/sampeng87/32/21983_2.png) [@SamPeng87](https://forum.cursor.com/u/SamPeng87)\ **Post date:** [February 7, 2025, 10:04am UTC](https://forum.cursor.com/t/plan-vs-act-modes/43550/40 "2025-02-07T10:04:53Z")
After using it for a day, I feel that the cursor itself needs to provide better support. There is a serious issue: different models have inconsistent understanding of context. For example, sometimes o3-mini can only perform 1 round of planning, while Claude can do multiple rounds. Other times, it’s the opposite. I believe that the official team should debug a fixed prompt for the workflow to accomplish this task effectively. [Previous page](https://forum.cursor.com/t/plan-vs-act-modes/43550.md?page=1) [Next page](https://forum.cursor.com/t/plan-vs-act-modes/43550.md?page=3)