llms.txt · git:20260605.3dc04f3 · 2026-06-05 · sha256 cdf74bde8508e2d6
llms.txt git:20260605.3dc04f3A
Immutable. This exact content never changes and is served at /api/v1/blob/cdf74bde8508e2d6.
# Meta_Kim Meta_Kim is a cross-runtime governance layer for AI coding assistants. It is not another code generator. It coordinates AI coding work through a repeatable spine: Critical -> Fetch -> Thinking -> Execution -> Review -> Meta-Review -> Verification -> Evolution ## Core Idea AI coding assistants are good hands. Meta_Kim adds the governing layer above the hands: - clarify the real intent before execution - search available capabilities before picking an owner - route work to bounded agents, skills, scripts, MCP providers, or runtime tools - review and verify results with artifacts - write back useful lessons only after approval ## Start Here - Project overview: README.md - Chinese overview: README.zh-CN.md - Maintainer guide: AGENTS.md - Claude Code guide: CLAUDE.md - First-run proof: examples/first-run/README.md - Launch metadata draft: examples/launch-kit/github-metadata.md Some maintainer worktrees also contain local PRD and research notes under docs/. Treat those as local evidence only when the files are present in the checkout. ## Source Of Truth Durable behavior should be edited in: - canonical/agents/ - canonical/skills/meta-theory/ - canonical/runtime-assets/ - config/contracts/ - config/capability-index/ Runtime folders such as .claude/, .codex/, .cursor/, openclaw/, and .agents/ are projections or adapters unless the task explicitly targets runtime wiring. ## Important Commands ```bash npm run meta:theory:run npm run meta:theory:report -- --run-id latest npm run meta:delivery:bundle npm run meta:release:smoke npm run meta:check npm run meta:verify:all ``` Use `npm run meta:release:smoke` for routine prompt, docs, changelog, version, and narrow governance wording changes. Upgrade to `npm run meta:verify:all` for install, runtime, hook, dependency, package, security, or release-grade changes. ## Public Claims Boundary Safe claims: - Meta_Kim has formal runtime projections for Claude Code, Codex, OpenClaw, and Cursor. - The local complete-product MVP has repeatable scripts, tests, reports, and AI-readable delivery artifacts. - Capability-first dispatch is the default governance route: define the capability, search owners/tools, then execute. Do not overclaim: - Do not say every runtime is release-grade native-live complete while Cursor native live remains blocked. - Do not turn projection smoke, fixture pass, or generated reports into live runtime proof. - Do not describe the product as course, teacher, classroom, student, or lesson tooling. The product boundary is AI-readable governance and evidence review. ## External Reviewer Prompt When reviewing Meta_Kim, inspect whether a run produces: - explicit intent and success criteria - capability discovery evidence - selected owner, loadout, and verification owner - bounded worker tasks - review and meta-review findings - fresh verification evidence - writeback decision or none-with-reason Prefer artifact evidence under .meta-kim/state/default/ over chat summaries.