Nihil

Root-authority, write-capable transformation of a repository you own — the Touch of God as one line. Full rewrite, public-API break, subsystem replacement, and deletion are pre-authorized; compatibility ceremony is skipped because the consumers are CI bots and your own framework. Keeps exactly two brakes: never leak a secret, never run a catastrophic unrecoverable command. Use when you want to transform your own framework end-to-end without permission friction. Invoked as /nihil:raze.

Last-resort first-principles repository transformation run as a pantheon of dynamic workflows, where no artifact has intrinsic preservation value and every no-op, patch, deletion, public-API break, or rebuild must be justified by evidence. Use for Nihil, first-principles transformation, aggressive architectural simplification, destructive code cleanup, public API redesign, dead-code evaporation, codebase rescue, or last-resort remediation. Routes to the /nihil, /nihil-maat, /nihil-odin, /nihil-shiva, and /nihil-athena workflows.

Strict evidence-based maintainability review of a repository or diff. Read, search, compare, and trace only — never modify. Use when you want findings gated by >85% confidence and repository evidence, with strict scope control and no speculative architecture. Invoked as /nihil:review.

Release-gate workflow with strict CI and publishing discipline. Inspects the repository's release workflow, verifies versioning and CI state, and refuses to publish when checks are red or unknown. Blocks force-push/hard-reset/rm -rf. For NuGet, applies trusted-publishing rules. Invoked as /nihil:release.

Implement evidence-backed Nihil findings within a fixed scope, preserving behavior unless authorized. Modifies only scoped files and runs checks before claiming done. Blocks push/tag/publish/version-bump (those belong to release). Use after /nihil:review to apply findings. Invoked as /nihil:implement.

Review code for extreme implementation ambition without tolerating accidental complexity. Reward code that is hard, powerful, and sophisticated only when it stays readable, cohesive, loosely coupled, expressive, and semantically named. Penalize redundant code extractable into meaningful private helpers, missed refactoring, giant or fragmented files outside the 500-1000 line range, vague abstractions, noisy comments, fake simplicity, meaningless over-extraction, under-extracted logic, duplicated intent, unstable APIs, and any structure that fails to justify its complexity. Use for absence-of-value-and-meaning reviews where the target is astonishingly simple code, not simplistic code.