{"slug": "have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a", "title": "\"Have you tried Claude Code?\" — How managing AI with text files led me to build a whole system", "summary": "A developer revived a shelved poker game project after discovering Claude Code, an AI coding tool that runs locally. Managing the project with text files and design docs, the developer built a system called FlowGate to handle AI-generated index files and inconsistent formatting. The game was completed and launched in May 2026.", "body_md": "February 2026. One sentence from a coworker woke up a development life that had been asleep for three years.\n\nI was clueless about dev communities when a coworker casually dropped this on me:\n\n**\"Have you tried Claude Code?\"**\n\nThe AI I'd only ever used in a browser was apparently *coming inside my own machine*. I tried it half-skeptical, and the result floored me. A development life I'd shelved for three years started turning again. Here's that timeline.\n\nAbout three years ago, I was building a poker game — an idea I'd only ever kept in my head — together with ChatGPT. The version back then was 3.5, \"Prometheus\" if I remember right. It was impressive, but development was slow. I moved to Claude, which had a reputation for being *unmatched at coding*, and kept going — until I hit **a wall you just can't get past over a browser.** So I shelved the project again.\n\nThen my coworker told me about \"Claude Code.\" The AI came *inside* my machine, and my development speed changed dramatically.\n\nAnd in those early days, I managed everything **in plain text.**\n\n```\nlast Axxx  addition number\nlast B001  bug number\nc   client-side (suspected)\ns   server-side (suspected)\ncs/sc  both, or unsure which side\n\n[bug pile]\nB001, cs, after phase-7 betting ends, the hi-lo selection dialog never appears and it freezes\n```\n\nIt may look crude, but it was my own management system.\n\nClaude's usage limit came fast. While hunting for an alternative, I found **GitHub Copilot.** Interestingly, it calls various models via *premium requests*. The Pro plan got me 300 of them.\n\nClaude Pro $20 + Copilot Pro $10\n\n300 ran out quickly too. While figuring out how to keep working on free models (back then GPT-4.1 and 5-mini were free), I remembered something I'd once glanced at without thinking — *the AI generating md files.* That trivial thing I'd ignored turned out to be the answer.\n\n**\"Ah — I can leave it as a design doc.\"**\n\nWhile Claude and Copilot were still alive, I started building a **design-doc factory** that even free models could mass-produce.\n\n```\n# Control.gd function map (reference for whoever writes the work order)\n\n**Purpose**: quickly check \"what functions exist, what they do, where they're called\"\n**Target file**: client/.../Control/Control.gd\n\n## A. Game-flow functions (in call order)\n| Function | Line | Role | When called |\n|----------|------|------|-------------|\n```\n\nNaturally, the design docs a free model spits out had their limits, so I ended up upgrading to Copilot **Pro+.**\n\nClaude Pro $20 + Copilot Pro+ $40\n\nAhh… comfortable. Pro+ gives 1,500 requests. Design handed to Claude, work done with Copilot. Efficiency shot up.\n\nAs workers multiplied, text management got unmanageable. So I introduced an **\"index.\"** And instead of managing it myself, I gave the workers an instruction:\n\n**\"Log it.\"**\n\n```\n## current logged items\n| ID | item | status | notes |\n|----|------|--------|-------|\n```\n\nAll I had to do was give instructions. No longer managing it myself — the workers managed it themselves. Much easier.\n\nFrom the moment I learned about \"Claude Code,\" it took **just one or two months** to go from text management to index delegation. I finished the game that way, built a homepage with my AI team, and launched in May. (👉 [horriblegames.net](https://horriblegames.net) — not a sketchy site, just a poker game demo.)\n\nThen it hit me. **The index files were scattered all over** — and the bigger problem: **AI is not consistent.** No matter how many times I gave it the formatting rules, it wrote things however it pleased.\n\nSo I built an **[index numbering tool]** — register a command and it auto-fills the index. I used this right up until FlowGate was born.\n\nBut the numbering tool had limits too: I had to manage presets every time, and if they weren't registered right it threw errors or the AI couldn't use it properly. So — **I decided to just turn it into a system.**\n\nAnd that's how **FlowGate** was born.\n\nUsing FlowGate doesn't mean the AI stops lying. It just means — **how many times it lied gets left behind as evidence.**\n\nSomething I learned building the poker game: the backend does fine once you nail the data flow, but **front-end / on-screen bugs? It genuinely can't fix them.**\n\n*\"That's not it — ugh, so frustrating.\"*\n\nI can't remember how many times I said that. Why? **Because there was no evidence.** Only the memory of *having said it* remains; what the AI actually changed, and why it still didn't work, is gone. All that's left is the memory of telling it \"this isn't working, route around it, do it this way.\"\n\nFlowGate being finished doesn't mean it fixes the bugs it couldn't before. But two **interesting things** appeared.\n\n**First, evidence remains.**\n\nYou can confirm things in conversation as you go, but *just like you forget today what you did yesterday*, if nothing is left behind you can't know yesterday. But the evidence I leave through FlowGate stays. So a difference emerged:\n\nFlowGate's action-bar SSE bug took three days. Before, I'd have had to leave a file somewhere to pick it up again; now I can just go **\"eh, I'll cut it here.\"**\n\n**Second, I can see how many times it got rejected.**\n\nThat SSE bug — **11 rejections on investigation, 13 on the work itself.** Before, I'd just vent in chat; now I can count how many times I got angry… just kidding 😅 — it means I can now **explicitly judge when to stop trying the same approach and switch to a different one.**\n\nUsually if the same method fails 2–3 times, try another; if a different method fails 4–6 times, try yet another… The SSE bug got caught by chance after exactly those counts, and as I recall it was a **conditional-branch bug + a deploy issue working together.** Either way, I can now **directly count how many times I attempted a given task.**\n\nFlowGate doesn't stop the AI from lying. Instead:\n\nFrom a single text file, to an index, to a numbering tool, and finally to a system. This is a four-month record of trying to close the gap between *\"the AI says it's done\"* and *\"it's actually done.\"*\n\n👉 FlowGate:\n\n[github.com/horrible-gh/FlowGate]", "url": "https://wpnews.pro/news/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a", "canonical_source": "https://dev.to/shinjpn1/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a-whole-system-2i8p", "published_at": "2026-06-17 20:54:44+00:00", "updated_at": "2026-06-17 21:21:45.653647+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "developer-tools", "ai-tools", "ai-agents"], "entities": ["Claude Code", "GitHub Copilot", "ChatGPT", "Claude", "FlowGate", "GPT-4.1", "5-mini", "horriblegames.net"], "alternates": {"html": "https://wpnews.pro/news/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a", "markdown": "https://wpnews.pro/news/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a.md", "text": "https://wpnews.pro/news/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a.txt", "jsonld": "https://wpnews.pro/news/have-you-tried-claude-code-how-managing-ai-with-text-files-led-me-to-build-a.jsonld"}}