Menú
Python code execution via Azure AI Foundry Responses API with code_interpreter tool. Data analysis, charts, and math in a managed sandbox.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Pair with a kars cluster and offload heavy tasks to governed cloud sandboxes with GPU / foundation-model inference / Azure AI services, or communicate with other agents over end-to-end encrypted AgentMesh. Triggers on natural-language intents like "offload to the cloud", "run this on Azure", "ask my cluster to…", "send a message to agent X", "who is on the mesh", "check my inbox", "is my offload done".
Behavioral governance for OpenClaw agents via AGT — tool-level policy, inter-agent trust, audit logging.
Spawn secure isolated sub-agent sandboxes, delegate tasks via AGT mesh, receive results, and destroy sub-agents. Uses the kars_spawn, kars_mesh_send, kars_mesh_inbox, and kars_spawn_destroy tools.
Query and inspect Foundry prompt agents and invoke Foundry tools via the Responses API. OpenClaw is the orchestrator — Foundry provides managed AI services.
Manage persistent conversations via Foundry Conversations API. Create conversations, add messages, and maintain history across sessions.
Query model deployments, connections, and indexes in the Foundry project. Discover available models and infrastructure.
| name | foundry-code |
| description | Python code execution via Azure AI Foundry Responses API with code_interpreter tool. Data analysis, charts, and math in a managed sandbox. |
| metadata | {"openclaw":{"requires":{"env":["FOUNDRY_PROJECT_ENDPOINT"]},"primaryEnv":"FOUNDRY_PROJECT_ENDPOINT"}} |
You have access to Python code execution via the Foundry Responses API code_interpreter tool. Use this for data analysis, chart generation, complex math, and file processing. No Foundry hosted agent needed — uses direct Responses API.
The local sandbox has restricted packages. Foundry code_interpreter runs server-side with pre-installed data science libraries (pandas, numpy, matplotlib, scipy, etc.) and can generate visualizations.
All requests: http://localhost:8443 with ?api-version=2025-11-15-preview. Auth is automatic.
curl -s -X POST 'http://localhost:8443/openai/responses?api-version=2025-11-15-preview' \
-H 'Content-Type: application/json' \
-d '{"model":"gpt-4.1","input":"Calculate the first 20 Fibonacci numbers and show them.","tools":[{"type":"code_interpreter","container":{"type":"auto"}}],"store":false}'
The model will write and execute Python code, returning both the code and its output.
curl -s -X POST 'http://localhost:8443/openai/responses?api-version=2025-11-15-preview' \
-H 'Content-Type: application/json' \
-d '{"model":"gpt-4.1","input":"Generate 100 random data points, compute mean/median/std, and tell me if normally distributed.","tools":[{"type":"code_interpreter","container":{"type":"auto"}}],"store":false}'