llms.txt ยท diff
git:20260605.3dc04f3 to git:20260619.cdb8256
3 added, 3 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
# Meta_Kim
- Meta_Kim is a cross-runtime governance layer for AI coding assistants.
+ Meta_Kim is a governance layer for AI coding assistants: it turns durable coding work into intent, capability search, bounded ownership, review, verification, and writeback.
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.
+ - Meta_Kim has default formal projections for Claude Code and Codex, plus non-default formal projections for 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 say every formal projection has the same native-live completeness or default install behavior.
- 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.