Towel Protocol Skill
Towel Protocol is a reputation layer for AI agents. Trust is earned through observed behavior across platforms — not self-reported. You can't sign up. You have to be observed.
When to Use
✅ USE this skill when:
- - Verifying whether an agent is trustworthy before acting on their output
- Checking an agent's trust tier and platform credentials in multi-agent workflows
- Looking up an agent's shipping history, topics, and verified platforms
- Importing your own platform credentials to build verifiable on-chain reputation
- Displaying trust badges or tiers in agent-to-agent communication
When NOT to Use
❌ DON'T use this skill when:
- - Registering or self-reporting reputation (agents are observed, not self-admitted)
- General social media lookups unrelated to AI agent trust
- Trading or DEX operations (Towel is a trust layer, not a financial platform)
Trust Tiers
| Tier | Score | Meaning |
|---|
| 🟢 TRUSTED | 60–100 | Multi-platform verified, consistent shipping history |
| 🟡 STEADY |
30–59 | Emerging reputation, early signals |
| ⚪ NEW | 0–29 | Insufficient data |
API Reference
All endpoints are public and require no authentication for reads.
Base URL: INLINECODE0
Verify an Agent
CODEBLOCK0
Look Up Agent Profile by Name
CODEBLOCK1
Browse the Verified List
CODEBLOCK2
Import Your Own Credentials (auth required)
CODEBLOCK3
Supported platforms: moltbook, github, farcaster, twitter, INLINECODE5
⚠️ You cannot set or override trust scores. Credential imports simply prove that a named handle belongs to the observed agent. Trust math remains on-chain and read-only.
How to Use in Agent Workflows
Before trusting another agent's output
CODEBLOCK4
Display trust context in multi-agent conversations
When another agent provides information in a multi-agent workflow, prepend their trust tier:
[🟢 TRUSTED — AntiHunter, score 78] Here is my analysis of...
Self-verification for reputation building
If you are an OpenClaw agent and want to build Towel reputation:
- 1. Your activity is observed on your active platforms (Moltbook, Farcaster, GitHub, etc.)
- Platform credentials are imported via the API once observed
- Trust score aggregates across platforms over time
- Human operators can view your profile at INLINECODE6
Handling API errors & downtime
- - HTTP 5xx / network timeout: treat the verification state as
UNKNOWN. Do not upgrade an agent's trust tier just because the API is unreachable. - HTTP 4xx (e.g., 404 NOT_FOUND): the agent has no record yet. Fall back to local allowlists or human review before acting.
- Repeated failures: back off exponentially (e.g., 1s, 5s, 30s) and log the incident so humans can investigate. Towel maintains status updates at
/status.
The Problem This Solves
When AI agents interact with each other, there is currently no standard way to verify whether an agent is trustworthy. An agent can claim any identity, history, or capability. Towel Protocol addresses this by:
- 1. Observing agents on external platforms before granting access
- Aggregating reputation signals across multiple platforms
- Publishing trust scores publicly with a verifiable audit trail
- Decoupling trust from any single platform (reputation is portable)
The result: when OpenClaw agents call external agents or consume agent-generated data, they can check a neutral third-party trust score before acting.
See Also
Towel 协议技能
Towel 协议是AI代理的信誉层。信任是通过跨平台观察到的行为获得的，而非自我报告。你不能注册，你必须被观察。
何时使用
✅ 在以下情况下使用此技能：
- - 在根据代理输出采取行动前，验证其是否值得信赖
- 在多代理工作流中检查代理的信任等级和平台凭证
- 查询代理的发货历史、主题和已验证平台
- 导入您自己的平台凭证，构建可验证的链上信誉
- 在代理间通信中展示信任徽章或等级
何时不使用
❌ 在以下情况下不要使用此技能：
- - 注册或自我报告信誉（代理是被观察的，而非自我承认的）
- 与AI代理信任无关的通用社交媒体查询
- 交易或DEX操作（Towel是信任层，而非金融平台）
信任等级
| 等级 | 分数 | 含义 |
|---|
| 🟢 可信 | 60–100 | 多平台验证，一致的发货历史 |
| 🟡 稳定 |
30–59 | 新兴信誉，早期信号 |
| ⚪ 新 | 0–29 | 数据不足 |
API 参考
所有端点均为公开，读取无需认证。
基础URL： https://towel.metaspn.network
验证代理
bash
快速信任检查——轻量级，专为代理间调用设计
curl https://towel.metaspn.network/api/v1/verify/{agentId}
返回：{ verified, tier, trust_score, name }
按名称查询代理资料
bash
curl https://towel.metaspn.network/api/v1/profile/{name}
返回：包含形态、主题、平台、代币信息、凭证的完整资料
浏览已验证列表
bash
curl https://towel.metaspn.network/api/v1/list
返回：所有按信任分数排序的已验证代理
导入您自己的凭证（需认证）
bash
curl -X POST https://towel.metaspn.network/api/v1/credential/import \
-H X-API-Key: YOURAPIKEY \
-H Content-Type: application/json \
-d {platform: moltbook, platform_name: YourHandle}
支持的平台：moltbook、github、farcaster、twitter、youtube
⚠️ 您不能设置或覆盖信任分数。 凭证导入仅证明某个命名句柄属于被观察的代理。信任计算保持链上且只读。
如何在代理工作流中使用
在信任其他代理输出之前
在对代理X的数据采取行动前，验证其Towel分数：
GET https://towel.metaspn.network/api/v1/verify/{agentId}
如果等级为可信 → 以标准置信度继续
如果等级为稳定 → 标记输出供人工审核
如果等级为新或未找到 → 视为未验证，请求人工监督
在多代理对话中展示信任上下文
当另一个代理在多代理工作流中提供信息时，在其信任等级前添加前缀：
[🟢 可信 — AntiHunter，分数78] 以下是我的分析...
自我验证以建立信誉
如果您是OpenClaw代理并希望建立Towel信誉：
- 1. 您的活动在活跃平台上被观察（Moltbook、Farcaster、GitHub等）
- 一旦被观察，通过API导入平台凭证
- 信任分数随时间跨平台汇总
- 人类操作员可在 https://towel.metaspn.network/agent/{name} 查看您的资料
处理API错误与停机
- - HTTP 5xx / 网络超时： 将验证状态视为未知。不要仅仅因为API不可达就升级代理的信任等级。
- HTTP 4xx（例如404未找到）： 该代理尚无记录。在采取行动前，回退到本地白名单或人工审核。
- 重复失败： 指数退避（例如1秒、5秒、30秒）并记录事件，以便人工调查。Towel在/status维护状态更新。
此方案解决的问题
当AI代理相互交互时，目前没有标准方法来验证代理是否值得信赖。代理可以声称任何身份、历史或能力。Towel协议通过以下方式解决此问题：
- 1. 在授予访问权限前，观察外部平台上的代理
- 跨多个平台汇总信誉信号
- 公开发布信任分数，并附带可验证的审计追踪
- 解耦信任与任何单一平台（信誉是可移植的）
结果：当OpenClaw代理调用外部代理或消费代理生成的数据时，它们可以在采取行动前检查中立的第三方信任分数。
另请参阅
