Menu
Guides the implementation of the ReAct loop, orchestrator, memory, and planner. Use this when working on any file inside backend/agent/.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
Guides workspace and session management. Use this when working on session_manager.py, workspace_manager.py, or anything related to session isolation.
| name | agent-core |
| description | Guides the implementation of the ReAct loop, orchestrator, memory, and planner. Use this when working on any file inside backend/agent/. |
The agent follows a strict Think → Act → Observe cycle. Never break this pattern.
The agent never outputs free text mid-loop. Only the final DONE step produces a summary.
workspace_context into LLM on every stepAlways injected before each ReAct step:
{
"session_id": "...",
"target": "...",
"completed_tasks": [],
"pending_tasks": [],
"recent_findings": [],
"open_artifacts": []
}
workspace/.agent/findings.json (persisted)workspace/.agent/plan.json