Track personal finances with a Claude Code assistant
How Mr.Malone showed me I could build a financial assistant using only English, Markdown, and Claude Code. Task: How Mr.Malone showed me I could build a financial assistant using only English, Markdown, and Claude Code Karpathy already predicted it in 2024, “English is the hottest programming language”. I have to admit that while I agreed with the claim then, I wouldn’t have expected that we would have come such a long way in a bit less that two years. To me, and many others, the release of Opus 4.5 into Claude code was that moment where English really became the best way to interact with computers. You described what you wanted and Claude code would get you working code that did what you wanted. But after some experiments I’ve been doing the past few days, I not only think that English is the hottest programming language, I also think that agents have made programming languages and applications obsolete. Let me try to explain to you why. I am glad to be a mess I’ve always been a mess managing my personal finances and investments. I’ve tried everything, and I’ve always failed at it. Open-source and SaaS personal finance apps like homebank that I could use out-of-the-box. Open-source and SaaS personal finance apps like homebank that I could use out-of-the-box. Writing my own web app with a simple web interface that allowed me to track expenses and make updates over my portfolio. This is actually the one that led to better results for me, but the fact that I had to squeeze maintenance work for the app, even if minimal, along with my daily responsibilities resulted in me not doing it, and ending up abandoning the app (and thus the habit) Writing my own web app with a simple web interface that allowed me to track expenses and make updates over my portfolio. This is actually the one that led to better results for me, but the fact that I had to squeeze maintenance work for the app, even if minimal, along with my daily responsibilities resulted in me not doing it, and ending up abandoning the app (and thus the habit) An excel sheet with monthly expense tracking and portfolio performance. This is what I am using now, but updating the sheet every month is taking me close to what took me to add the few changes and features needed for my app.. So I was back to square one. An excel sheet with monthly expense tracking and portfolio performance. This is what I am using now, but updating the sheet every month is taking me close to what took me to add the few changes and features needed for my app.. So I was back to square one. But we live in the world of Baselight, LLMs, coding agents, and agentic social networks. There had to be a better way. And not only had I found it, in the process I came to a realisation: Agents may be all we need! Where it all started It all started when I was reading a post from Lyn Alden’s newsletter where she was describing how the overnight financing markets were running into liquidity shortages, and that the Fed would likely begin balance sheet expansion in the not-too-distant future. I then thought, “wow, it’d be cool if I could track these signals myself in some way, and this data must be public through the FED data”. So I went into Baselight and asked the question that you see in the image below. Bingo! We had what I needed. I then asked Baselight to make an analysis about recent events where the FED had to step in to inject emergency liquidity into the repo markets. It came up with this cool table and descriptive. I was doing this analysis between diaper change and diaper change, while having in the back of my mind the urge to find a better way to handle my personal finances. Lyn Alden, Ray Dalio, and all these renowned macro investors back their investment decisions and portfolio allocation in a lot of macroeconomic data. When it occurred to me. What if I use claude code to create a financial assistant that helps me make better investment decisions leveraging all the data that we have in Baselight? That is how it all started, by connecting the Baselight MCP to Claude code. Since then, things started escalating quickly. The Birth of Mr. Malone After the first prompt I quickly realised that I could not only use Claude code connected to Baselight to help me make better financial decisions, I could also provide it with all my financials so that it could help me keep track of them, evaluate together my financial health, and make investment decisions using my own personal context instead of making them in the void.; tools: Claude Code. Human role: The original post does not say how a person stayed involved.; limitations: Prerequisites include access to Claude Code, a Baselight account with MCP support, and a private Git repository for version control. Sensitive data must be encrypted via Git hooks before pushing, as noted by the author's privacy concerns. Integration uncertainty exists regarding the stability of MCP connections and the potential for LLM hallucinations in financial analysis. Human approval is strictly required before executing any real-world financial transactions based on agent outputs..
Tools
Published on Agent Work Atlas:
Overview
How Mr.Malone showed me I could build a financial assistant using only English, Markdown, and Claude Code
Workflow
How Mr.Malone showed me I could build a financial assistant using only English, Markdown, and Claude Code Karpathy already predicted it in 2024, “English is the hottest programming language”. I have to admit that while I agreed with the claim then, I wouldn’t have expected that we would have come such a long way in a bit less that two years. To me, and many others, the release of Opus 4.5 into Claude code was that moment where English really became the best way to interact with computers. You described what you wanted and Claude code would get you working code that did what you wanted. But after some experiments I’ve been doing the past few days, I not only think that English is the hottest programming language, I also think that agents have made programming languages and applications obsolete. Let me try to explain to you why. I am glad to be a mess I’ve always been a mess managing my personal finances and investments. I’ve tried everything, and I’ve always failed at it. Open-source and SaaS personal finance apps like homebank that I could use out-of-the-box. Open-source and SaaS personal finance apps like homebank that I could use out-of-the-box. Writing my own web app with a simple web interface that allowed me to track expenses and make updates over my portfolio. This is actually the one that led to better results for me, but the fact that I had to squeeze maintenance work for the app, even if minimal, along with my daily responsibilities resulted in me not doing it, and ending up abandoning the app (and thus the habit) Writing my own web app with a simple web interface that allowed me to track expenses and make updates over my portfolio. This is actually the one that led to better results for me, but the fact that I had to squeeze maintenance work for the app, even if minimal, along with my daily responsibilities resulted in me not doing it, and ending up abandoning the app (and thus the habit) An excel sheet with monthly expense tracking and portfolio performance. This is what I am using now, but updating the sheet every month is taking me close to what took me to add the few changes and features needed for my app.. So I was back to square one. An excel sheet with monthly expense tracking and portfolio performance. This is what I am using now, but updating the sheet every month is taking me close to what took me to add the few changes and features needed for my app.. So I was back to square one. But we live in the world of Baselight, LLMs, coding agents, and agentic social networks. There had to be a better way. And not only had I found it, in the process I came to a realisation: Agents may be all we need! Where it all started It all started when I was reading a post from Lyn Alden’s newsletter where she was describing how the overnight financing markets were running into liquidity shortages, and that the Fed would likely begin balance sheet expansion in the not-too-distant future. I then thought, “wow, it’d be cool if I could track these signals myself in some way, and this data must be public through the FED data”. So I went into Baselight and asked the question that you see in the image below. Bingo! We had what I needed. I then asked Baselight to make an analysis about recent events where the FED had to step in to inject emergency liquidity into the repo markets. It came up with this cool table and descriptive. I was doing this analysis between diaper change and diaper change, while having in the back of my mind the urge to find a better way to handle my personal finances. Lyn Alden, Ray Dalio, and all these renowned macro investors back their investment decisions and portfolio allocation in a lot of macroeconomic data. When it occurred to me. What if I use claude code to create a financial assistant that helps me make better investment decisions leveraging all the data that we have in Baselight? That is how it all started, by connecting the Baselight MCP to Claude code. Since then, things started escalating quickly. The Birth of Mr. Malone After the first prompt I quickly realised that I could not only use Claude code connected to Baselight to help me make better financial decisions, I could also provide it with all my financials so that it could help me keep track of them, evaluate together my financial health, and make investment decisions using my own personal context instead of making them in the void.
Reported result
The author reports that this approach eliminated the maintenance burden of previous custom apps and Excel sheets, allowing for easier tracking of financial health and investment decisions. However, no quantitative metrics or verified financial outcomes are provided. A measurable acceptance check would be: 'Verify that the agent successfully retrieves and formats at least three distinct macroeconomic data points from Baselight into a Markdown report without manual intervention.'
Human role
The original post does not say how a person stayed involved.
Limitations
Prerequisites include access to Claude Code, a Baselight account with MCP support, and a private Git repository for version control. Sensitive data must be encrypted via Git hooks before pushing, as noted by the author's privacy concerns. Integration uncertainty exists regarding the stability of MCP connections and the potential for LLM hallucinations in financial analysis. Human approval is strictly required before executing any real-world financial transactions based on agent outputs.
Try it
Act as a financial assistant builder using Claude Code. I want to create a personal finance agent named 'Mr. Malone' that uses Baselight for macro data and Markdown for memory. Inputs: - My current portfolio holdings: [replaceable inputs: list of assets and values] - Recent expense categories: [replaceable inputs: monthly spend breakdown] - Baselight API/MCP access details: [replaceable inputs: connection string or auth token] Steps: 1. Create a CLAUDE.md file defining the agent's role as a financial analyst who prioritizes data accuracy and risk assessment. 2. Set up a directory structure with Markdown files for 'portfolio.md', 'expenses.md', and 'decisions.md'. 3. Write a script or prompt sequence to query Baselight for current interest rate trends and store the summary in 'macro_context.md'. 4. Generate a sample investment analysis combining my portfolio data with the macro context. Deliverables: - A complete file tree of the agent's memory structure. - A sample analysis report in Markdown format. Quality Check: - Ensure all financial data is sourced from the provided inputs or Baselight queries. - Verify that no sensitive data is exposed in plain text if the repo is public (use encryption hooks if needed). Safeguards: - Do not execute any real trades. - Perform a dry run with dummy data first. - Ask me to confirm the CLAUDE.md instructions before generating the final analysis. - If Baselight connection fails, stop and ask for credentials rather than hallucinating data.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.