“code execution and sandboxes”

Execute code safely using RLM Runtime with Docker isolation when you need to run tests, validate implementations, or execute complex computations.

A股算法执行/智能拆单策略。当用户说"算法执行"、"智能拆单"、"execution algo"、"算法交易"、"拆单策略"、"大单拆分"时触发。基于 cn-stock-data 获取数据，设计算法执行方案。支持 formal/brief 两种输出风格。

Task implementation workflow, test harnesses, screenshot/video capture, visual debugging.

Code Executor MCP Server by MEOK AI Labs

AutoForge is a production-grade autonomous optimization framework for AI agents.

Pipeline routing, classification, phase ownership, principles, lessons protocol.

Specialist execution protocol — shared by all specialists operating within the team

Slice a large idea, task, or plan into the smallest strong executable step.

Safety gate for task execution.

Internal meta skill for dispatching subagents, coordinating execution, and integrating reviewed results back into the main flow.

Execute and track progress on PLANS.md execution plans.

Converge AIDE's three parallel agent runtimes (legacy daemon model-manager chat + harness/orchestrator.mjs, arch-ts model-router/chat.ts + routes/agent.ts…

Run shell/CMD commands directly on the host system.

Execute behavior changes with a RED -> GREEN -> REFACTOR loop when a practical automated test path exists.

Convert an existing specification or plan into concrete execution tasks, ordered implementation steps, and verification actions.

Operate on owned repositories in Vega Lab.

Delegate hands-on implementation to OpenAI's Codex CLI (a GPT-family coding worker; default model gpt-6-astra) while Claude stays the manager: Claude writes a…

MANDATORY CORE SKILL: Enforces the Autonomous Coding & Self-Correction Loop for Antigravity in every session.

Use DB-GPT 0.8.1 as an agentic AI data platform: install and configure provider profiles, operate its CLI and services, build agents and AWEL flows, ingest…

Operate OpenAI Codex CLI (terminal coding agent) to accomplish software engineering tasks.

RAG, document retrieval, web search, and code execution agent.

Clawdex — dual-engine coding agent.

Automatically fetches, analyzes, and resolves GitHub issues by mapping them to local sandboxes, modifying code, running tests, and opening Pull Requests using…

Use when the user works with Prime Intellect packages (prime-rl, prime, verifiers, etc.) and mentions: GPU, pods, compute, sandboxes, ML environments…