菜单
Self-amendment MCP server framework with layered skill architecture and blockchain auditability. Use when managing knowledge layers, evolving skills, auditing health, or understanding KairosChain's architecture and capabilities.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Governed autonomous OODA loop for cognitive agents. Use when starting, stepping, monitoring, or stopping agent sessions with human checkpoints and safety gates.
Compile mode_hooks definitions into the plugin_projector pipeline. Use to inspect mode_hooks status (read-only in stage 0).
Manage Claude Code plugin projection from KairosChain SkillSets. Use when checking projection status, forcing re-projection, or verifying integrity.
Scaffold and design new SkillSets. Use when creating new SkillSet packages with tools, knowledge, and optional Claude Code plugin artifacts.
Exchange SkillSets between KairosChain instances via the decentralized Meeting Place. Use when acquiring, depositing, withdrawing, or browsing SkillSets from peers.
基于 SOC 职业分类
| name | kairos-chain |
| description | Self-amendment MCP server framework with layered skill architecture and blockchain auditability. Use when managing knowledge layers, evolving skills, auditing health, or understanding KairosChain's architecture and capabilities. |
KairosChain provides a layered skill architecture (L0/L1/L2) with blockchain-backed auditability. All core functionality is provided via MCP tools. This skill provides an architectural overview and guides you to per-SkillSet skills for detailed workflows.
Immutable safety rules and meta-governance. L0 defines the rules that govern L0 itself — this structural self-referentiality is the foundation of KairosChain's design. Changes require human approval and full blockchain recording.
Project knowledge in structured format. Changes recorded with hash references.
Use knowledge_list and knowledge_get to browse, skills_promote to promote from L2.
Temporary session context. Free modification, no blockchain recording.
Use context_save for session work, promote to L1 when proven valuable.
L2 (free) → skills_promote → L1 (recorded) → skills_promote → L0 (human approval + blockchain)
Each layer has increasing governance requirements. This gradient ensures that volatile ideas can be captured freely (L2) while stable knowledge is protected (L0).
Detailed workflow guides are provided by individual SkillSets:
Use tool_guide for dynamic tool discovery and workflow recommendations.
If the MCP server is not running, these skills and agents are still visible but MCP tools will not be available. To connect:
gem install kairos-chain is installed (Ruby 3.0+ required).mcp.json configuration in the project root/reload-plugins