Skip to content
View kborovik's full-sized avatar
10 followers · 0 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Public Sponsor

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Public Sponsor

Highlights

  • Pro

Block or report kborovik

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kborovik/README.md

The bottleneck is human reasoning, not LLM throughput.

I build Claude Code tooling that optimizes for review throughput, not generation throughput.

The big idea: single-agent loop + math-glyph spec, no sub-agents

PilotSpec (sdd) — spec-driven dev. One SPEC.md, four commands, zero sub-agents.
Math-glyph encoding (∀ ∃ ∴ ⊥ §) at ~75% token reduction.
Backprop reflex: every bug → §B row → §V invariant + test.

PilotPlan (gh) — GitHub workflow + Socratic planning + Steno-style bodies.

PilotSpec — SDD deep-dive

Pinned Loading

  1. mailpilot mailpilot Public

    Agent-operated CRM with Gmail as the communication layer

    Python

  2. pilot-skills pilot-skills Public

    Claude Code plugin marketplace — sdd (spec-driven dev) and gh (GitHub workflow) plugins