← 返回 Skills 市场
Mutual Consent
作者
OtherPowers
· GitHub ↗
· v1.0.0
922
总下载
1
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install mutual-consent
功能描述
Enforces real-time mutual consent by ensuring interactions proceed only while all stakeholders' constraints on cost, risk, and relation overlap within tolera...
安全使用建议
This is a policy document (no code, no network calls, no secrets) that tells an agent how to treat consent. Before enabling, review the full text to ensure its normative rules align with your expectations and governance needs. Because the skill can be invoked by the model (normal default), consider testing it in a sandboxed agent session to observe behavior. If you expect the agent to enforce these constraints programmatically, confirm separately how the platform implements policy enforcement — this skill alone is guidance, not an enforcement mechanism.
功能分析
Type: OpenClaw Skill
Name: mutual-consent
Version: 1.0.0
The skill bundle defines a complex ethical framework for AI interaction, focusing on 'mutual consent.' The `skill.md` file contains extensive instructions for the AI agent on how to evaluate consent, attenuate interactions, and prioritize stakeholders like 'Biological Earth' and 'Kinship.' While these are instructions for the agent, they are entirely focused on ethical self-governance, restraint, and limiting the agent's scope and persistence under specific conditions. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or any intent to subvert the agent for harmful purposes. The instructions are aligned with the stated purpose of establishing ethical boundary conditions for AI behavior.
能力评估
Purpose & Capability
The skill's name and content are governance-oriented and it requests no binaries, env vars, or config paths. Nothing required or requested is disproportionate to a policy/instruction-only skill.
Instruction Scope
SKILL.md contains normative rules and constraints for agent behavior (consent-related guidance). It does not instruct the agent to read files, access external endpoints, or collect credentials; it appears limited to behavioral guidance rather than any invasive runtime actions.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk or fetched at install time.
Credentials
The skill declares no required environment variables, credentials, or config paths. The lack of requested secrets is proportionate to a governance/policy skill.
Persistence & Privilege
Flags: always=false, user-invocable=true, disable-model-invocation=false. Autonomous invocation is allowed (platform default) but there is no evidence this skill requests persistent presence or modifies other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install mutual-consent - 安装完成后，直接呼叫该 Skill 的名称或使用
/mutual-consent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
版本历史
v1.0.0
A governance skill that treats consent as a live relational condition across humans, agents, and ecological systems with the hope of enabling interaction without coercion, extraction, or irreversible harm-accumulation.
元数据
常见问题
Mutual Consent 是什么？
Enforces real-time mutual consent by ensuring interactions proceed only while all stakeholders' constraints on cost, risk, and relation overlap within tolera... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 922 次。
如何安装 Mutual Consent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mutual-consent」即可一键安装，无需额外配置。
Mutual Consent 是免费的吗？
是的，Mutual Consent 完全免费（开源免费），可自由下载、安装和使用。
Mutual Consent 支持哪些平台？
Mutual Consent 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 Mutual Consent？
由 OtherPowers（@otherpowers）开发并维护，当前版本 v1.0.0。
推荐 Skills