I’m John Ruf, the builder behind Glitch Forgeworks. I make software, games, stories, and tools for people who love turning ideas into something real. My skills bring structure to working with AI coding agents—from sharpening requirements and planning parallel builds to checking what actually shipped. They’re built around a simple standard: clear instructions, useful outputs, and evidence that the work is done. Engineer by trade, artist by instinct. Always tinkering.
by John Ruf
Your agent reads your whole manuscript cold, prose only, then tells you in five blunt paragraphs where it hooked, where it drifted, what's broken, and whether it would keep reading.
by John Ruf
Turns a raw app idea into an approved idea brief and a requirements spec with stable FR IDs, testable acceptance criteria and an explicit out-of-scope list.
by John Ruf
Seven specialist agents take your novel from rough idea to copy-edited DOCX/EPUB through 15 approval-gated phases: pitch, outline, draft, cold read, dev edit, revision, copy edit, publish.
by John Ruf
Derives the real dependency graph from imports, flags every architecture-doc claim the code disproves, proposes coherent rewrites and scouts dead code without deleting anything.
by John Ruf
Audits your code against the spec one requirement at a time: exists, real or stub, wired to a real entry point, and proven by a test it actually ran.
by John Ruf
Runs a session plan with parallel subagents: whole waves launched at once, lease-checked commits, gates re-run before "done", and a requirement-by-requirement final verification.