[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7956GCQTQ0KXSXD43DM9AF3":3,"skill-same:01M7956GCQTQ0KXSXD43DM9AF3":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7956GCQTQ0KXSXD43DM9AF3","execution-and-safety",null,"Configure smolagents CodeAgent execution safely: local imports, executor_type choices, remote sandboxes, PythonInterpreterTool, and sandbox troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: execution-and-safety\ndescription: \"Configure smolagents CodeAgent execution safely: local imports,\n  executor_type choices, remote sandboxes, PythonInterpreterTool, and sandbox\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Execution and Safety\n\nUse this sub-skill when a task involves how `CodeAgent` executes Python, how to limit or authorize imports, how to choose `executor_type`, or how to troubleshoot local and remote execution failures.\n\nRoute elsewhere when the request is mainly about:\n- Model\u002FAPI\u002Fprovider configuration: use `model-providers`.\n- CLI flags or web UI behavior: use `cli-and-ui`.\n- Agent control flow, planning, multi-step runs, or managed agents: use `agent-workflows`.\n- Tool schemas, `Tool` subclasses, MCP, or tool serialization: use `tools-and-integrations`.\n\n## Safety-first defaults\n\nPrefer this decision order:\n1. Use `CodeAgent(..., executor_type=\"local\")` only for trusted tasks and low-risk code, because `LocalPythonExecutor` is a restricted AST interpreter but not a complete security sandbox.\n2. Add `additional_authorized_imports` narrowly, one package or submodule at a time; avoid `\"*\"` unless the user explicitly accepts local execution risk.\n3. Use `executor_type=\"docker\"`, `\"e2b\"`, `\"modal\"`, or `\"blaxel\"` for untrusted prompts, web-browsing contexts, public-facing agents, or higher-risk code.\n4. Use a context manager or call `agent.cleanup()` for remote executors so sandboxes\u002Fcontainers terminate promptly.\n5. Do not pass destructive, credential-printing, filesystem-mutating, or network-scanning snippets as examples.\n\n## Quick local configuration\n\n```python\nfrom smolagents import CodeAgent\n\nagent = CodeAgent(\n    tools=[],\n    model=model,\n    executor_type=\"local\",\n    additional_authorized_imports=[\"math\", \"statistics\"],\n    max_print_outputs_length=10_000,\n    executor_kwargs={\"timeout_seconds\": 10},\n)\n```\n\nKey points:\n- `additional_authorized_imports` extends smolagents' built-in safe module list for local code execution.\n- Submodules are explicit: authorizing `\"numpy\"` allows `import numpy`; use `\"numpy.random\"` for that submodule or `\"numpy.*\"` for the package tree.\n- `LocalPythonExecutor` checks that authorized modules are importable during initialization, except wildcard `\"*\"`.\n- `max_print_outputs_length` truncates captured stdout, not the returned Python value.\n- `executor_kwargs={\"timeout_seconds\": N}` sets the local execution timeout; `None` disables it and should be avoided for untrusted code.\n\nFor exact constructor behavior, see [executor-reference.md](references\u002Fexecutor-reference.md). For risk patterns and sandbox selection, see [security-workflows.md](references\u002Fsecurity-workflows.md). For errors, see [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Remote executor choices\n\n`CodeAgent` accepts exactly these executor names:\n\n| `executor_type` | Best fit | Extra |\n| --- | --- | --- |\n| `\"local\"` | Trusted local workflows, fastest setup | base package |\n| `\"docker\"` | Self-hosted isolation, local container control | `smolagents[docker]` |\n| `\"e2b\"` | Managed cloud sandbox with E2B account\u002FAPI setup | `smolagents[e2b]` |\n| `\"modal\"` | Managed Modal sandbox with Modal account\u002FAPI setup | `smolagents[modal]` |\n| `\"blaxel\"` | Managed Blaxel sandbox, fast hibernating VMs | `smolagents[blaxel]` |\n\nRemote executor pattern:\n\n```python\nfrom smolagents import CodeAgent\n\nwith CodeAgent(\n    tools=[],\n    model=model,\n    executor_type=\"docker\",\n    additional_authorized_imports=[\"numpy\"],\n    executor_kwargs={\"build_new_image\": False},\n) as agent:\n    result = agent.run(\"Compute a small numeric result without writing files.\")\n```\n\nRemote execution details:\n- `additional_authorized_imports` becomes the list of packages installed in the remote environment.\n- Tool requirements are also installed remotely when tools are sent to the executor.\n- Variables are serialized with safe JSON-compatible serialization by default.\n- `allow_pickle=True` enables pickle fallback for complex objects but can execute arbitrary code during deserialization; use it only in fully trusted environments.\n- Managed agents are not supported with snippet-level remote execution; run the whole agentic system in a sandbox for multi-agent isolation.\n\n## PythonInterpreterTool\n\nUse `PythonInterpreterTool` when a tool-calling agent needs a calculator-like Python tool rather than CodeAgent code actions:\n\n```python\nfrom smolagents import PythonInterpreterTool\n\npython_tool = PythonInterpreterTool(\n    authorized_imports=[\"math\"],\n    timeout_seconds=10,\n)\n```\n\nThe tool returns a string containing captured stdout and the final output. Its `authorized_imports` follows the same allow-list idea as `LocalPythonExecutor` and includes base built-in modules automatically.\n\n## Bundled helper\n\nUse the bundled helper for safe local validation before constructing a real agent:\n\n```bash\npython sub-skills\u002Fexecution-and-safety\u002Fscripts\u002Fcheck_executor_config.py --executor-type local --imports math statistics --tiny-local-check\npython sub-skills\u002Fexecution-and-safety\u002Fscripts\u002Fcheck_executor_config.py --executor-type docker --imports numpy --explain-only\n```\n\nThe helper performs parser-only checks by default. It never starts Docker, Modal, E2B, or Blaxel, never reads credentials, and never runs network calls. `--tiny-local-check` executes only a tiny in-process local interpreter smoke test.\n","# Execution and Safety\n\nUse this sub-skill when a task involves how `CodeAgent` executes Python, how to limit or authorize imports, how to choose `executor_type`, or how to troubleshoot local and remote execution failures.\n\nRoute elsewhere when the request is mainly about:\n- Model\u002FAPI\u002Fprovider configuration: use `model-providers`.\n- CLI flags or web UI behavior: use `cli-and-ui`.\n- Agent control flow, planning, multi-step runs, or managed agents: use `agent-workflows`.\n- Tool schemas, `Tool` subclasses, MCP, or tool serialization: use `tools-and-integrations`.\n\n## Safety-first defaults\n\nPrefer this decision order:\n1. Use `CodeAgent(..., executor_type=\"local\")` only for trusted tasks and low-risk code, because `LocalPythonExecutor` is a restricted AST interpreter but not a complete security sandbox.\n2. Add `additional_authorized_imports` narrowly, one package or submodule at a time; avoid `\"*\"` unless the user explicitly accepts local execution risk.\n3. Use `executor_type=\"docker\"`, `\"e2b\"`, `\"modal\"`, or `\"blaxel\"` for untrusted prompts, web-browsing contexts, public-facing agents, or higher-risk code.\n4. Use a context manager or call `agent.cleanup()` for remote executors so sandboxes\u002Fcontainers terminate promptly.\n5. Do not pass destructive, credential-printing, filesystem-mutating, or network-scanning snippets as examples.\n\n## Quick local configuration\n\n```python\nfrom smolagents import CodeAgent\n\nagent = CodeAgent(\n    tools=[],\n    model=model,\n    executor_type=\"local\",\n    additional_authorized_imports=[\"math\", \"statistics\"],\n    max_print_outputs_length=10_000,\n    executor_kwargs={\"timeout_seconds\": 10},\n)\n```\n\nKey points:\n- `additional_authorized_imports` extends smolagents' built-in safe module list for local code execution.\n- Submodules are explicit: authorizing `\"numpy\"` allows `import numpy`; use `\"numpy.random\"` for that submodule or `\"numpy.*\"` for the package tree.\n- `LocalPythonExecutor` checks that authorized modules are importable during initialization, except wildcard `\"*\"`.\n- `max_print_outputs_length` truncates captured stdout, not the returned Python value.\n- `executor_kwargs={\"timeout_seconds\": N}` sets the local execution timeout; `None` disables it and should be avoided for untrusted code.\n\nFor exact constructor behavior, see [executor-reference.md](references\u002Fexecutor-reference.md). For risk patterns and sandbox selection, see [security-workflows.md](references\u002Fsecurity-workflows.md). For errors, see [troubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Remote executor choices\n\n`CodeAgent` accepts exactly these executor names:\n\n| `executor_type` | Best fit | Extra |\n| --- | --- | --- |\n| `\"local\"` | Trusted local workflows, fastest setup | base package |\n| `\"docker\"` | Self-hosted isolation, local container control | `smolagents[docker]` |\n| `\"e2b\"` | Managed cloud sandbox with E2B account\u002FAPI setup | `smolagents[e2b]` |\n| `\"modal\"` | Managed Modal sandbox with Modal account\u002FAPI setup | `smolagents[modal]` |\n| `\"blaxel\"` | Managed Blaxel sandbox, fast hibernating VMs | `smolagents[blaxel]` |\n\nRemote executor pattern:\n\n```python\nfrom smolagents import CodeAgent\n\nwith CodeAgent(\n    tools=[],\n    model=model,\n    executor_type=\"docker\",\n    additional_authorized_imports=[\"numpy\"],\n    executor_kwargs={\"build_new_image\": False},\n) as agent:\n    result = agent.run(\"Compute a small numeric result without writing files.\")\n```\n\nRemote execution details:\n- `additional_authorized_imports` becomes the list of packages installed in the remote environment.\n- Tool requirements are also installed remotely when tools are sent to the executor.\n- Variables are serialized with safe JSON-compatible serialization by default.\n- `allow_pickle=True` enables pickle fallback for complex objects but can execute arbitrary code during deserialization; use it only in fully trusted environments.\n- Managed agents are not supported with snippet-level remote execution; run the whole agentic system in a sandbox for multi-agent isolation.\n\n## PythonInterpreterTool\n\nUse `PythonInterpreterTool` when a tool-calling agent needs a calculator-like Python tool rather than CodeAgent code actions:\n\n```python\nfrom smolagents import PythonInterpreterTool\n\npython_tool = PythonInterpreterTool(\n    authorized_imports=[\"math\"],\n    timeout_seconds=10,\n)\n```\n\nThe tool returns a string containing captured stdout and the final output. Its `authorized_imports` follows the same allow-list idea as `LocalPythonExecutor` and includes base built-in modules automatically.\n\n## Bundled helper\n\nUse the bundled helper for safe local validation before constructing a real agent:\n\n```bash\npython sub-skills\u002Fexecution-and-safety\u002Fscripts\u002Fcheck_executor_config.py --executor-type local --imports math statistics --tiny-local-check\npython sub-skills\u002Fexecution-and-safety\u002Fscripts\u002Fcheck_executor_config.py --executor-type docker --imports numpy --explain-only\n```\n\nThe helper performs parser-only checks by default. It never starts Docker, Modal, E2B, or Blaxel, never reads credentials, and never runs network calls. `--tiny-local-check` executes only a tiny in-process local interpreter smoke test.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill execution-and-safety",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill execution-and-safety",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill execution-and-safety","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fexecutor-reference.md","REFERENCE","参考文档",7446,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002Freferences\u002Fexecutor-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fsecurity-workflows.md",6152,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002Freferences\u002Fsecurity-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",6678,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_executor_config.py","SCRIPT","脚本",7593,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fexecution-and-safety\u002Fscripts\u002Fcheck_executor_config.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]