“code execution and sandboxes”

Safely modify Space Code itself using sandboxed execution, validation, review gates, and NEMO writeback.

Run a local mathematical experiment through the MathModel runtime and package traceable observations, metrics, checks, and figures.

Execute Python code in a sandboxed environment and return the result.

Use when executing implementation plans — choose mode: batch execution with checkpoints, subagent-per-task, or parallel dispatch for independent problems.

Validate code examples across the 4-Layer Teaching Method with intelligent strategy selection.

Delegate a coding task to the Codex CLI (@openai/codex).

Solana DEX swap execution via Jupiter aggregator including quoting, transaction building, signing, and confirmation

Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing…

Executes the deterministic implementation plan step by step in the isolated worktree or branch, writing code, migrations, and tests.

Design sales conversations and evaluate call transcripts.

Use when a multi-step implementation needs a durable plan or an existing approved plan needs coordinated execution

FDD 主流程 step 2——执行循环。串行驱动 feature 构建：next-feature → 派 implementer → handoff 决策树 → complete。每个 feature 由交接决策树把关（核验 implementer 自验留下的证据）。静态验证 → 代码审查 → user-test…

Use when a work item in a project with devflow on is to be implemented, built, worked on or fixed (an item id such as 3, the next item of a plan, or a bug…

Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks.

Track substantial work, changing scope, and resumable progress.

当你有一个书面的撰写实施计划，需要在一个单独的会话中执行，并带有审查检查点时使用

Hand a decision loop (Jev) an execution map: which steps of a sandbox loop to run, in what order, on which values.

sole-executor engagement, startup census, coordinator ladder, adoption, extermination, landing

沙盒执行器 — 在安全隔离环境中运行 Python/Shell 脚本获取外部数据

Implements, verifies, and audits technical and on-page SEO tasks.

Delegated step runner over the HOTL execution state machine — delegates eligible steps to fresh subagents while the controller keeps governance, verification…

Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.

Deliver complete SCP, load, and generator commands with a generated artifact.

Boot-loaded baseline — terminal, timeouts, build loop, commits, prohibited actions, quality.