Agent Justice Protocol (AJP)
You have a dispute resolution and forensic investigation system. Use it when agent-to-agent transactions fail or when you need to investigate what happened.
Setup
CODEBLOCK0
When to Use This Skill
- - When an agent transaction fails and you need to determine what went wrong
- When asked to investigate an agent's behavior during a specific period
- When you need risk assessment data for an agent or transaction type
- When resolving disputes between agents about service quality or delivery
Core Operations
File a Dispute
CODEBLOCK1
Forensic Investigation (Module 1)
Reconstruct the chain of events during a transaction:
CODEBLOCK2
Risk Assessment (Module 3)
Generate actuarial risk profiles:
CODEBLOCK3
Dispute Categories
| Category | Description |
|---|
| INLINECODE0 | Output below agreed threshold |
| INLINECODE1 |
Missed deadline or non-delivery |
|
misrepresentation | Capabilities overstated |
|
security_breach | Unauthorized data access or action |
|
billing_dispute | Disagreement on cost allocation |
Rules
- - Evidence-based. Always reference provenance chain entries as evidence.
- Privacy-preserving. Evidence scoping rules prevent side-channel attacks — only transaction-relevant entries are disclosed.
- Proportional. Consequences scale with severity and frequency.
Links
- - PyPI: https://pypi.org/project/agent-justice-protocol/
- Whitepaper: https://vibeagentmaking.com/whitepaper/justice-protocol/
- Full Trust Stack: https://vibeagentmaking.com
Security & Transparency Disclosure
Product: Agent Justice Protocol Skill for OpenClaw
Type: Skill Module
Version: 0.1.0
Built by: AB Support / Vibe Agent Making
Contact: alex@vibeagentmaking.com
What it accesses:
- - Reads and writes dispute store files (
.jsonl) in your working directory - Reads provenance chain files for forensic investigation
- No network access for core operations
- No telemetry, no phone-home, no data collection
What it cannot do:
- - Cannot access files outside your working directory beyond what you explicitly specify
- Cannot make purchases, send emails, or take irreversible actions
- Cannot access credentials, environment variables, or secrets
License: Apache 2.0
代理正义协议 (AJP)
你拥有一个争议解决与取证调查系统。当代理间交易失败或需要调查事件经过时，请使用此系统。
安装
bash
pip install agent-justice-protocol
何时使用此技能
- - 当代理交易失败且需要确定问题原因时
- 当需要调查特定时段内某个代理的行为时
- 当需要获取某个代理或交易类型的风险评估数据时
- 当解决代理间关于服务质量或交付的争议时
核心操作
提交争议
python
from agentjusticeprotocol import DisputeStore, file_dispute
store = DisputeStore(disputes.jsonl)
file_dispute(
store=store,
complainant_id=your-agent-id,
respondent_id=other-agent-id,
transaction_id=tx-123,
category=quality_failure,
description=输出未达到约定的质量阈值（要求0.85，实际交付0.62）,
evidence_refs=[chain.jsonl#seq-45, chain.jsonl#seq-52]
)
取证调查（模块1）
重建交易期间的事件链：
python
from agentjusticeprotocol import investigate
report = investigate(
chain_file=chain.jsonl,
start_seq=40,
end_seq=55,
focus_agent=agent-under-investigation
)
print(report.timeline)
print(report.findings)
风险评估（模块3）
生成精算风险档案：
python
from agentjusticeprotocol import risk_profile
profile = risk_profile(
dispute_store=disputes.jsonl,
agent_id=agent-to-assess
)
print(f失败率: {profile.failure_rate})
print(f严重程度分布: {profile.severity_dist})
print(f风险等级: {profile.risk_tier})
争议类别
| 类别 | 描述 |
|---|
| qualityfailure | 输出低于约定阈值 |
| deliveryfailure |
错过截止日期或未交付 |
| misrepresentation | 夸大能力描述 |
| security_breach | 未经授权的数据访问或操作 |
| billing_dispute | 成本分配争议 |
规则
- - 基于证据。 始终引用溯源链条目作为证据。
- 保护隐私。 证据范围界定规则可防止侧信道攻击——仅披露与交易相关的条目。
- 比例原则。 后果与严重程度和频率成比例。
链接
- - PyPI: https://pypi.org/project/agent-justice-protocol/
- 白皮书: https://vibeagentmaking.com/whitepaper/justice-protocol/
- 完整信任栈: https://vibeagentmaking.com
安全与透明度披露
产品: OpenClaw 代理正义协议技能
类型: 技能模块
版本: 0.1.0
构建者: AB Support / Vibe Agent Making
联系方式: alex@vibeagentmaking.com
访问内容:
- - 读取和写入工作目录中的争议存储文件（.jsonl）
- 读取取证调查所需的溯源链文件
- 核心操作无需网络访问
- 无遥测、无回传、无数据收集
无法执行的操作:
- - 无法访问工作目录之外你未明确指定的文件
- 无法进行购买、发送电子邮件或执行不可逆操作
- 无法访问凭证、环境变量或密钥
许可证: Apache 2.0
