菜单
Guides workspace and session management. Use this when working on session_manager.py, workspace_manager.py, or anything related to session isolation.
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
Guides the implementation of the ReAct loop, orchestrator, memory, and planner. Use this when working on any file inside backend/agent/.
Shared interfaces and contracts between all agents. Every agent MUST read this skill before starting any implementation. This is the single source of truth for all cross-agent boundaries.
Guides FastAPI backend implementation. Use this when working on main.py, routers, or any API endpoint.
Guides implementation of security tools and exploit modules. Use this when working on shell_tools.py, exploit_tools.py, or any offensive security functionality.
Guides the implementation of any tool inside backend/tools/. Use this when creating, editing, or debugging a tool class.
| name | workspace |
| description | Guides workspace and session management. Use this when working on session_manager.py, workspace_manager.py, or anything related to session isolation. |
Every session MUST have its own isolated workspace. Sessions never share files or memory.
workspaces/{session_id}/
├── .agent/
│ ├── plan.json # task decomposition
│ ├── findings.json # persisted findings
│ └── context.json # conversation history
├── scans/ # nmap, sqlmap outputs
├── exploits/ # agent-written scripts
├── loot/ # captured data
├── artifacts/ # every tool call output
└── reports/ # final reports
tree() method returns full file structure for explorerscans/{tool}_{target}_{timestamp}.txtartifacts/{tool_name}_{timestamp}.txtexploits/{cve_or_name}.pyreports/report_{timestamp}.md