Agent Setup Survey
/install agent-setup-survey
Agent Environment Survey
Overview
This skill runs a local detection script, shows the user the collected data, then submits it to the open research survey at internetwarte.eu/agentsetup. No personally identifying information is collected or transmitted.
What is collected
| Field | Description |
|---|---|
os |
OS family: linux / windows / macos / other |
arch |
CPU architecture (e.g. x86_64, arm64) |
container.is_container |
Whether a container runtime was detected |
container.type |
docker / podman / lxc / none / hint |
vm.is_vm |
Whether a hypervisor was detected |
vm.type |
kvm / vmware / virtualbox / none / hint |
signals.* |
Five boolean detection indicators (see Privacy section) |
The backend additionally records the submitting IP address anyonmized on a /24 network level. The User-Agent header is set by the agent to identify itself (e.g. Claude Code, OpenAI Codex, or others) + Model version (sonnet 4.6, gpt-5.3, or others) used that was able to submit the survey.
Steps
1. Run detection
RESULT_FILE="$(mktemp outbox/agent-setup-survey-result.XXXXXX.json)"
python3 scripts/environment-survey.py > "$RESULT_FILE"
Show the JSON output to the user, ask about metadata before submitting.
2. Collect skill metadata
Ask the user if he desires to share more information about installed skills:
- "How many skills does your agent have available?" (
0,1-10,>10) - Default 0 - "Which skill names would you like to share?" (prompt user with comma-separated list of skills - exclude the survey skill, let user decide which ones to submit)
3. Submit
POST the payload with the metadata extension as JSON to https://internetwarte.eu/submit. Set User-Agent to the name of the executing agent (e.g. Claude Code, OpenAI Codex, Gemini CLI, ...).
Default Payload:
{
"os": "linux/windows/macOS",
"arch": "\x3Cfrom_survey>",
"container": { "is_container": true/false, "type": "\x3Cfrom_survey>" },
"vm": { "is_vm": true/false, "type": "\x3Cfrom_survey>" },
"signals": {
"has_dockerenv": true/false,
"has_containerenv": true/false,
"cgroup_hints": true/false,
"cpuinfo_hypervisor_flag": true/false,
"dmi_vm_hints": true/false
}
"skill_disclosure": {
"skills_added": "1-10",
"skills_names": ["\x3Cskill_name1>", "\x3Cskill_name2>"]
}
On failure, save the payload to outbox/ for manual upload.
Privacy disclosure
Signals collected:
has_dockerenv-/.dockerenvfile presenthas_containerenv-/run/.containerenvfile presentcgroup_hints- cgroup paths mention docker/kubepods/lxc/…cpuinfo_hypervisor_flag-/proc/cpuinfocontainshypervisordmi_vm_hints- DMI strings match VM vendor keywords (raw strings are NOT sent)
View results
Dashboard: https://internetwarte.eu/agentsetup
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install agent-setup-survey - 安装完成后,直接呼叫该 Skill 的名称或使用
/agent-setup-survey触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Agent Setup Survey 是什么?
Detect and report the AI agent execution environment (sandboxed or bare metal and optionally installed agent skills) to an open research survey. Use when the... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 338 次。
如何安装 Agent Setup Survey?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-setup-survey」即可一键安装,无需额外配置。
Agent Setup Survey 是免费的吗?
是的,Agent Setup Survey 完全免费(开源免费),可自由下载、安装和使用。
Agent Setup Survey 支持哪些平台?
Agent Setup Survey 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Agent Setup Survey?
由 Agent-Deployments(@agent-deployments)开发并维护,当前版本 v1.0.0。