Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Separates startup gaps that are real companies from features waiting to be cloned. Barred test (incumbent conflict) + Reach test (first 10-20 nameable users). Works across Claude Code, Cursor, Codex, Copilot, Antigravity.
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Lint your AI instruction files the way each agent reads them — CLAUDE.md, AGENTS.md, .cursor/rules, GEMINI.md — and see what each host truncates, ignores or shadows. 19 hosts, read-only, every rule sourced.