§ 01 · The Hook
The bait, then the rug-pull.
Every AI coding tool wants to own your memory. Claude Code gets CLAUDE.md. Cursor gets .cursorrules. Codex gets its own thing. Vini from Brazil got tired of maintaining them all separately, so he built a single source of truth and a five-step methodology to put humans back in control.
What the video promised.
stated at 00:40“In this video, you are going to see what I am trying to do to fix that stuff for me and for you as well.”delivered at 07:02
Where the time goes.
00:00 – 00:31
01 · The nightmare
Pain named immediately: every AI tool has its own markdown memory schema, creating management chaos for developers using multiple tools.
00:31 – 01:05
02 · Solution intro
Introduces ai-coders/context, an open-source project with a single .context folder that syncs to all tools. MIT license. First English video disclaimer.
01:05 – 02:03
03 · Folder structure + sync
Demo of .context/agents, .context/docs, .context/plans structure. Quick sync command creates symlinks in Claude Code, Cursor, Codex folders. One change propagates everywhere.
02:03 – 02:51
04 · CLI + MCP setup
Two install paths: npx @ai-coders/context interactive wizard, or connect the MCP. Both analyze the codebase and generate context-aware agents, docs, plans.
02:51 – 03:43
05 · Plan workflow
After init, prompt plan [task]. The tool selects which agents to run, which docs to consider, and creates a cross-tool-portable execution workflow with persisted state.
03:43 – 05:52
06 · PREVC methodology
Five-phase structured AI workflow: Plan, Review, Execute, Validate, Confirm. Contrasted against autopilot AI that dumps 500 lines of unwanted code.
05:52 – 07:02
07 · Live demo
Real agent run in Portuguese. Three bugs discovered: TypeScript errors, tech debt, multi-tenancy risk. Three separate PREVC plans generated and linked to the workflow.
07:02 – 07:41
08 · CTA + close
Contribution ask: find bugs, write PRs. First English video acknowledgment. MIT license. AICoders channel intro.
Visual structure at a glance.
Named ideas worth stealing.
03:43acronym
PREVC Workflow System
- P -- Planning
- R -- Review
- E -- Execution
- V -- Validation
- C -- Confirmation
A 5-phase structured AI coding methodology. No code is written until P and R are complete and human-approved. Forces spec-before-code discipline. Portable via the .context memory file.
Steal forAny pitch about structured AI workflows, anti-autopilot positioning, or the argument that developers should own their process
01:05model
ai-coders/context folder model
- .context/agents
- .context/docs
- .context/plans
- .context/skills
Single source of truth for all AI tool context. Sync command creates symlinks in each tool expected location. Change once, propagate everywhere.
Steal forCLAUDE.md architecture, multi-tool context management, OSS product positioning
Lines you could clip.
00:25
“Welcome to the nightmare of markdown files.”
01:34
“One place, one folder to rule them out.”
04:31
“It is you that should be using AI as your copilot -- not you being the copilot of AI.”
04:48
“User: Add authentication. AI: generates 500 lines of code. That is not what I wanted.”
How they spent the runtime.
Hook length25s
Info densityhigh
Filler8%
Things they pointed at.
00:07toolCodex
05:52toolAntigravity (agent runner)
How they asked for the click.
07:02product
“Next step here is for you to help me to validate that tool, to find bugs, to write pull requests, to help us to fix this problem so our lives become better.”
Soft community ask -- no subscribe push, no link card. Contribution-first CTA works well for OSS audiences.
Word for word.
metaphoranalogy
00:00If you are a software developer like me, you have the same problem. You start using Cloud Code, and then you start using Codecs, and then you start using Gemini, Antigravity, Cursor AI, and all of those AI tools that we have right now.
00:13The problem is each of them decided to implement their own way to make memories files, to create and manage agents, to deal with the skills.
00:25So you are in the . Welcome to the nightmare of markdown files. And I don't want you to live in this nightmare, so I have created the AI coders contacts to fix this stuff that all of these tools should be fixing right now.
00:42But as I'm seeing, they don't want to do that. So let's do it together. In this video, you're going to see what I'm trying to do to fix that stuff for me and for you as well.
00:54I have created an open source project to fix that nightmare. English is not my mother language. Disclaimer set.
01:00Let's sign me to it. The proposal here is to have only the dot contacts folder. Inside of that dot contacts folder, you have your agents, your docs, your plans, your skills, your anything else they want to put a name in a markdown file organization.
01:17After we have it configured here, it is pretty straightforward. You would just quick sync with the tool you want to use.
01:25So if you are using CloudCode, quick sync with CloudCode, all your agents will have a sync link in your CloudCode folder.
01:34So, basically, if you change the files inside of context folder, then it will automatically be recognized by cloud that this file has changed as well. Same for the other two. So you got the point.
01:45One place, one folder to rule them out. I just want a comment that I can write in my terminal or an MCP that I can connect in my AI agent and say, hello.
01:57I just want to initialize my context. And that's what I did. So if you prefer to use the CLI, there's an interactive CLI.
02:04We have the AI agents and everything else that you need to have there. It will check your code base, analyze it, and then we'll suggest the next steps for you. Pretty straightforward.
02:14You just need to hit enter enter enter, accept the terms that you never read, and there we go. Or you can just connect the MCP. With the MCP, there are some steps.
02:23First one, install the MCP. Second one, prompt to the agent. Emit the contacts.
02:28That's pretty much it. It will generate the files you just saw in my screen. But the thing is, these files, they are already mapped to understand your code base.
02:36Your agents are for your code base. They are not, like, just general agents. They are not general skills.
02:42They are not general docs. Next step, this will set up the context and field according with the code base. With the context ready, you need to prompt plan and then the task you want to implement.
02:53So, for example, plan develop a new authentication method for me using AI context. This will create a new plan for you, but not just a random plan generated by AI.
03:06It will line up the agents that need to be used for this. It will figure out what files of your documentation need to be considered for this plan, and, also, it will create a workflow of execution.
03:20So if you start doing that in Cloud Code, you can continue doing that in Codecs. You can continue doing that in Corsair. No matter which tool you're using, if you want just to switch then, it's straightforward.
03:31We have a memory that's persisted with exactly this step. It stopped it and which agent should go ahead and develop the feature in this step. Once you have planned the workflow, you have reviewed everything, that's pretty much it.
03:44You can just hit start workflow and let AI work for you. And for the workflow system, I'm using something that I call Prevs. In Portuguese, it's Prevs.
03:53It is a method that I have been using for years already since 2023 to develop software to use AI at all. Because first step, b, you plan.
04:06R, you review your plan. So, basically, you will iterate with AI until your plan looks correct for you, until it looks legit, and then you move forward. Moving forward, we have three steps, execute, validate, and confirm.
04:21So in the execution step, it will execute the code. In the validation step, it will validate for you. The idea here, it is not for you to run everything on autopilot.
04:31The idea is for you to understand what's going on, to review step by step, to be assisted by AI. It is you that should be using AI as your copilot and and not you being the copilot of AI. Here's a quick example.
04:44Most of AI coding workflows look like this. User, add authentication. Then AI generates 500 lines of code.
04:52That's not what I wanted. That's you, user, and that's your workflow right now. But with this method, you will have p, what type of auth, OAuth, JWT, session, what providers?
05:06R, here's the architecture. Dependencies, x, y, z. Risk is z.
05:10Do you want to approve that? Do you want to move forward? You understand what's going on.
05:14You understand the plan. You will review that with AI. Execution, implementing the approved design, implemented the approved feature.
05:22Validation, all 15 tests are passing, and the security of it is passing, is complete. And see, it is deployed, or depending on your workflow, you can confirm and you can manually do that.
05:35The idea is if you start doing something on Cloud Code and you are out of credits, you can just move away to Codecs and continue it exactly from where you were. Same thing. If you want to move to another tool, that's the same idea.
05:48We'll have a memory file that will keep the track of the progress in your workflow. And here's an example on antigravity.
05:55Basically, I just said, this is in Portuguese, in it is context. And then it started working, writing the files for me.
06:03Next step, I wrote, write a plan to identify bugs and initiate an workflow in Previz. And then it started it and run every tools that were that were necessary, and then we have the plans.
06:16As I was validating and checking the plans, I noticed that we had more than one problem. We had three problems.
06:23The first one, we have type errors. The second one, attack depth.
06:28And the third one, a most tenancy risk. Three different problems. Three different plans.
06:33So I asked, hey. Let's generate three different plans for it and link it to the current workflow. And that's it.
06:42That happened. And then I said, okay. Let's jump into the execution process and execute the plan.
06:49And that's what Integraft is doing for me right now. I won't spend more time here. I want this to be as simple as the tool is.
06:56So next step here is for you to help me to validate that tool, to find bugs, to write pull requests, to help us to fix this problem so our lives become better.
07:08Okay? This is my first YouTube video in English. This is my first open source project that is actually becoming bigger than I imagined.
07:15As I mentioned in the very beginning, when I started this, it was something it was something more for me and my colleagues, and then it started getting bigger. And now I'm organizing this in a structured way for collaborating with you guys. You're welcome.
07:29If you have experience, you're welcome. If you want to just like four kids, you're welcome as well. This is MIT license, and this is AICoders channel.
07:38I'm Vinny from Brazil. It's nice to meet you.
§ · For Joe
Steal PREVC. Own your context.
Builder playbook
The developer who controls the spec controls the build -- PREVC is just that discipline made executable by AI.
- PREVC is a named framework you can drop into any tutorial or pitch: Plan, Review, Execute, Validate, Confirm. Five phases, no ambiguity.
- The .context folder model is directly applicable to JoeFlow CLAUDE.md -- one source of truth, synced everywhere via symlinks.
- The add-authentication-then-500-unwanted-lines example is a universal pain point. Use it as a hook for any AI workflow content.
- The you-are-the-copilot line is ready to clip at 4:31. Standalone, punchy, no setup needed.
- Vini built for himself first, then opened it -- framing the CTA as help-fix-this-problem rather than subscribe. Worth mirroring for OSS and tool launches.
§ · For You
Stop letting AI drive.
For developers using AI coding tools
If you have ever asked AI to add authentication and gotten 500 lines of code you did not want, PREVC is the fix -- it makes you specify before you execute.
- Before asking AI to write any code, write the spec yourself: what type, what dependencies, what risks. This is phase P.
- Review the AI proposed architecture before approving execution. Five minutes here saves hours of rewriting.
- Use the .context folder approach to keep your agents, docs, and plans in one place -- no more hunting through .claude/, .cursor/, and .codex/ separately.
- The start-in-Claude-Code-continue-in-Codex portability is real -- but only if your workflow state lives in a shared memory file, not inside the tool.
