Repo Prompt by @pvncher - the context engineering tool to help you get the most out of your ai subscriptions.

Filter
Exclude
Time range
-
Minimum likes
Repo Prompt CE is pretty good
It’s awesome and they just dropped a community edition. Integrates with all the inference providers, runs swarms of agents, does deep analysis and planning. Great way to implement large things without losing the plot
2
8
5,338
Repo prompt is now opensource!
Happy to announce that @RepoPrompt Community Edition is now live on @github Repo Prompt started as a tool for copy pasting, but soon stumbled into a world of context engineering. Today, it has evolved into an extremely capable multi agent orchestration tool, by inverting traditional harness design to make an mcp server the primary agent, so that underlying cli harnesses can be swapped out. This version of the app has been designed specially to thrive in the age of opensource driven by coding agents. This means that many of the legacy features you might think of Repo Prompt for have been removed to maximize the potential of its tools for parallel agents. While this is a Mac native app, the project structure was redesigned to shed the need for xcode, taking heavy inspiration from @steipete’s work. The repo borrows from @badlogicgames’s example of keeping a list of approved contributors, but adds a twist where all previous customers who opted in are automatically whitelisted. I really think this repo can serve as a learning baseline for many to build novel agent experiences, without having to maintain complete harnesses, and while its currently Mac only, work is underway to deliver a composable core that can power cross platform apps just as well. If you want to get involved with development, please join the amazing repo prompt discord community!
1
2
23
8,853
It’s still worth it because the credits kick in when you hit rate limits
1
3
228
Try out the best orchestration tool around, that supports all your models out of the box!
As models get smarter and more capable, you will get diminishing returns prompting them yourself. Enter "Orchestrate" a powerful new workflow in @RepoPrompt that allows you to combine the strengths of GPT 5.5 and Opus 4.7 in ways no other tool makes possible.
2
17
13,720
Never been a better time to give Repo Prompt a try!
This is @RepoPrompt 2.0 A fully integrated agent, that makes it seamless to use RP's powerful MCP tools, with a built-in oracle and context builder. A first class experience showcasing how much better and efficient your agents can be with good context engineering tools.
1
13
8,759
This is by far the biggest ever update for @RepoPrompt It is easier than ever to use, and there's never been a better time to try it.
Just released @RepoPrompt 2.0! - New built in Agent mode, making full use of the RP MCP tools - First class support for Codex, leveraging it's app server. - Good support for Claude Code + Gemini CLI as well! - Brand new onboarding making the app easier than ever to use.
2
15
4,366
You can also export the prompt and use whatever browser automation tools you like (eg: claude --chrome) to manage prompting Pro. The mcp tools give you deep control over the app
2
40
Awesome codex skill using rp-cli down below!
my new favorite way to build context in large codebases or complicated tasks. Use @RepoPrompt rp-cli skill, and combine with codex's new subagents feature, go try it out, way quicker to find context. my repoprompt skill below 🔽
5
1,114
Repo prompt’s apply_edits tool kept working when Codex’ apply_patch tool did not
Tools are such a big differentiator in your agent experience. Giving them the right "stuff" matters a great deal. Here, we are using @RepoPrompt to save so much context and work.
4
892
Replying to @erd0xbc
It's actually planned for 1.6 :)
1
3
193
Give this a try! Works incredible for code reviews
Replying to @gmickel
Also added support for @RepoPrompt's new prompt export (v1.5.61). Run a @ID_AA_Carmack-level review, export the full context to a file, paste into the LLM of your choosing. github.com/gmickel/gmickel-c…
2
3
1,795
Give these commands a try if you haven't already! They transform how much you can do with @RepoPrompt from the comfort of your terminal
Replying to @KeshTFE @RepoPrompt
These commands serve effectively the same purpose when combined with the rp-cli. Give them a try
1
2
7
1,805
Replying to @F_AI_Mouse
hah! RP Has a lot of those other tools built in - can go harder!
3
70
Replying to @F_AI_Mouse
Glad it's been going well!
1
6
316
Replying to @KeshTFE
If you can submit a trace over DM, it's very helpful. I have some CPU perf improvements coming in the next update, but it's always helpful to see what specifically is causing this for you.
2
507
Replying to @lgandecki
You don't need to copy anymore! As of Friday, Claude can pass it's report to the context builder over mcp!
2
1
13
671
It is being worked on, but it'll likely be the V2 that ships on Mac/Linux.
1
2
49
Replying to @this_is_moody
The number one thing I really recommend people do with Repo Prompt, especially at first, is leverage the context builder, either with gemini, claude or codex clis. They can help you build detailed, token efficient prompts to find all context required for a task. Then I recommend using Chatgpt (ideally with 5.1 pro) to draft a plan that you can feed cursor or other models. The app recently allows you to connect gemini and codex clis as providers too, so you can directly generate the plan with 5.1 high in the chat, using your chatgpt subscription. A good architectural plan makes an enormous difference, and that comes from optimizing the context in your plan prompt as best as you can. Regarding the mcp, cursor recently added toll truncation which causes misgivings with tool responses. What do recommend using it for in cursor, is, if ever you have a complex task, you can prompt cursor to use the chat tool to get a second opinion or plan. It can serve as an oracle that the model can go back and forth with. Hope that helps!
2
87
Replying to @mikez93 @FactoryAI
If you've got claude code setup, I highly recommend enabling the new agent edit mode for pro edit, using claude code to handle edits more accurately!
2
8
598