Skip to content
Development
Command

/meta-theory-verify

Run the appropriate Meta_Kim verification path

From plugin
meta-kim
2633 skills9 agents3 commands
Install
$ npx -y skills add KimYx0207/Meta_Kim --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/meta-theory-verify

Context preview

What this command does when you run it.

Run the appropriate Meta_Kim verification path

Command definition

meta-theory-verify.md
description: Run the appropriate Meta_Kim verification path
argument-hint: [smoke|release|global]

Run Meta_Kim verification from the rendered Meta_Kim package root. Choose the lightest route that matches the change risk:

  • `smoke`: prompt, docs, changelog, or narrow governance wording.
  • `global`: global hooks, runtime homes, command sync, or install/update wiring.
  • `release`: install/update, hooks, runtime matrix, provider registry,

dependency compatibility, or explicitly release-grade work.

Default to `smoke` when no argument is provided.

npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:release:smoke
git -C "__META_KIM_PACKAGE_ROOT__" diff --check

For `global`, also run:

npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:check:global:release -- --targets claude,codex,cursor

For `release`, run:

npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:verify:all

Return the exact command results and keep proof layers separate: smoke pass, global-hook pass, graph freshness, and release-grade pass are not the same claim.

Ships withmeta-kim

Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.

Get the whole plugin