菜单
MCP security hardening — credential leakage prevention, input sanitization, and tool access control. Use for reviewing agent MCP configurations.
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。
基于 SOC 职业分类
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references
Multi-agent orchestration with model routing, category delegation, and sprint management. Use for coordinating Pantheon agents.
Auto-continue through todos with idle detection and safety gates. Use for multi-step orchestration.
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references
Multi-model routing with cost/quality selection and provider fallbacks. Use for AI gateway abstraction.
Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instructions.
| name | mcp-security |
| description | MCP security hardening — credential leakage prevention, input sanitization, and tool access control. Use for reviewing agent MCP configurations. |
| context | fork |
| globs | ["agents/*.agent.md"] |
Mandatory security measures for all MCP server usage in Pantheon agents.
See instructions/mcp-security.instructions.md for the full rules.
