Numbers·Claude Code, Cursor, Other·Software companies
Mental models framework built with agents
A solo founder gave Claude, ChatGPT, Windsurf, and Cursor defined roles to build and deploy a 120-model mental models framework.
The author shipped 120 models, an MCP server for Claude Desktop, and 140 chaos tests with a 100% pass rate over 22 months.
Overview
How it was set up
Four AI tools given defined roles with a SITREP coordination protocol, running four tasks in parallel. Stack: React, Cloudflare Workers, D1, TypeScript.
Worth knowing
The 9.2/10 quality score is self-reported. The project took 22 months, and the agents' share of the work is not broken out.
A prompt to start from
The source does not show the prompt.
Sources 1
History
- Source published
- 2025-11-26
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/mental-models-framework-built-with-agents-claude-code.md
More in software companies
15 featsResultSmall scoped fixes took about five minutes to test and merge versus roughly an hour by hand; the full-stack task failed and was rewritten.
ResultDevin found nearly every old term in a docs-wide rename, but the edits still needed 20+ manual commits.
ResultCognition merged 659 Devin PRs into its own codebase in one week, up from 154 in its best week of 2025.