SealVera Skill for OpenClaw
Cryptographically-sealed, tamper-evident audit trails for every AI decision your agents make.
SealVera is AI Decision Audit Infrastructure. This skill wires any OpenClaw agent into SealVera
so every decision it makes is logged, cryptographically signed, chained, and monitored —
automatically. Built for teams shipping AI in finance, healthcare, legal, and insurance.
EU AI Act · SOC 2 · HIPAA · GDPR · FINRA · ISO 42001
Why SealVera?
- - Tamper-evident — every decision is cryptographically hashed (RSA-2048) and chained; any alteration is detectable
- Works in 2 lines —
init() + one patch call and every LLM decision is logged - Full explainability — captures inputs, outputs, reasoning steps, confidence scores, model used
- Real-time dashboard — search, filter, export at app.sealvera.com
- Drift detection — alerts when agent behaviour deviates from its baseline
- Any LLM — OpenAI, Anthropic, Gemini, Ollama, LangChain, CrewAI, AutoGen
- Zero friction — no new infrastructure, installs in seconds
First time? Run setup
Check if SealVera is configured:
CODEBLOCK0
If .sealvera.json does NOT exist, run setup:
CODEBLOCK1
Setup will:
- 1. Ask for your API key (get one free at app.sealvera.com)
- Verify connectivity and show org/plan info
- Copy
sealvera-log.js into the workspace - Patch
AGENTS.md with the mandatory sub-agent audit rule - Write
.sealvera.json config - Fire a test log to confirm end-to-end
One-time setup. After this, every sub-agent you spawn is audited automatically.
If the user says "install SealVera", "set up SealVera", or "connect SealVera" — run setup, don't just describe it.
How logging works
After setup, two logging paths are active:
1. Sub-agent logging (automatic via AGENTS.md)
Every
sessions_spawn task prompt gets a MANDATORY footer — the sub-agent logs itself on completion.
2. Main-session logging (call after every significant task)
The agent running the main session must log its own work. This is what shows your day-to-day activity in the dashboard.
CODEBLOCK2
Log after: code written, bug fixed, feature deployed, investigation done, judgment call made.
Don't log: routine chat, heartbeat pings, trivial lookups.
Setup patches SOUL.md with this rule so the agent follows it automatically.
Each log entry includes: input/output, reasoning steps, RSA-2048 signature, chain link, timestamp, model, and agent name.
Decision vocabulary
Task / agent execution:
| Decision | Meaning |
|---|
| INLINECODE7 | Task finished successfully |
| INLINECODE8 |
Answered a question / returned output |
|
FAILED | Task failed |
|
ERROR | Unexpected exception |
|
ESCALATED | Handed off to human or higher-level agent |
|
SKIPPED | Task intentionally not run |
|
PARTIAL | Completed with caveats |
Approval / gating:
| Decision | Meaning |
|---|
| INLINECODE14 | Request approved |
| INLINECODE15 |
Request blocked |
|
FLAGGED | Needs human review |
Tests:
| Decision | Meaning |
|---|
| INLINECODE17 | Test passed |
| INLINECODE18 |
Test failed |
|
SKIPPED | Test skipped |
Sub-agent audit rule
Append this footer to every sessions_spawn task:
CODEBLOCK3
Check status
CODEBLOCK4
Get your API key
Sign up at app.sealvera.com — free tier includes 10,000 decisions/month.
Reference
See references/api.md for all SDK methods and log field schema.
See references/compliance.md for regulation mapping (EU AI Act, FINRA, HIPAA, GDPR, SOC 2).
OpenClaw 的 SealVera 技能
为您的智能体所做的每一个 AI 决策提供加密密封、防篡改的审计追踪。
SealVera 是 AI 决策审计基础设施。该技能可将任何 OpenClaw 智能体接入 SealVera，使其做出的每一个决策都能自动记录、加密签名、链式存储并受到监控。专为在金融、医疗、法律和保险领域部署 AI 的团队打造。
欧盟 AI 法案 · SOC 2 · HIPAA · GDPR · FINRA · ISO 42001
为什么选择 SealVera？
- - 防篡改 — 每个决策都经过加密哈希处理（RSA-2048）并形成链式结构；任何篡改均可检测
- 两行代码即可运行 — init() + 一次补丁调用，所有 LLM 决策即可记录
- 完全可解释性 — 捕获输入、输出、推理步骤、置信度分数、所用模型
- 实时仪表盘 — 在 app.sealvera.com 搜索、筛选、导出
- 漂移检测 — 当智能体行为偏离基线时发出警报
- 支持任何 LLM — OpenAI、Anthropic、Gemini、Ollama、LangChain、CrewAI、AutoGen
- 零摩擦 — 无需新基础设施，数秒内完成安装
首次使用？运行设置
检查 SealVera 是否已配置：
javascript
const fs = require(fs);
const path = require(path);
const configured = fs.existsSync(path.join(process.env.OPENCLAW_WORKSPACE || process.cwd(), .sealvera.json));
如果 .sealvera.json 不存在，请运行设置：
bash
node /scripts/setup.js
设置将：
- 1. 询问您的 API 密钥（在 app.sealvera.com 免费获取）
- 验证连接并显示组织/计划信息
- 将 sealvera-log.js 复制到工作区
- 使用强制性子智能体审计规则修补 AGENTS.md
- 写入 .sealvera.json 配置文件
- 发送测试日志以确认端到端连接
一次性设置。此后，您生成的每个子智能体都将自动接受审计。
如果用户说安装 SealVera、设置 SealVera或连接 SealVera — 请运行设置，而不仅仅是描述它。
日志记录的工作原理
设置完成后，两个日志记录路径将激活：
1. 子智能体日志记录（通过 AGENTS.md 自动进行）
每个 sessions_spawn 任务提示都会获得一个
强制性页脚 — 子智能体在完成任务后自行记录。
2. 主会话日志记录（在每个重要任务后调用）
运行主会话的智能体必须记录自己的工作。这将在仪表盘中显示您的日常活动。
javascript
const log = require(./sealvera-log);
await log({
action: fixloginbug, // 您所做操作的简短描述
decision: COMPLETED, // COMPLETED | FAILED | ESCALATED
input: { task: ... },
output: { result: ... },
reasoning: [{ factor: outcome, value: ok, signal: safe, explanation: ... }]
});
在以下情况后记录： 代码编写完成、错误修复完成、功能部署完成、调查完成、判断决策做出。
不记录： 常规聊天、心跳检测、琐碎查询。
设置会使用此规则修补 SOUL.md，以便智能体自动遵循。
每条日志条目包括：输入/输出、推理步骤、RSA-2048 签名、链式链接、时间戳、模型和智能体名称。
决策词汇表
任务 / 智能体执行：
| 决策 | 含义 |
|---|
| COMPLETED | 任务成功完成 |
| RESPONDED |
回答了问题 / 返回了输出 |
| FAILED | 任务失败 |
| ERROR | 意外异常 |
| ESCALATED | 移交给人工或更高级智能体 |
| SKIPPED | 任务有意不执行 |
| PARTIAL | 完成但存在限制条件 |
审批 / 门控：
| 决策 | 含义 |
|---|
| APPROVED | 请求已批准 |
| REJECTED |
请求被阻止 |
| FLAGGED | 需要人工审核 |
测试：
测试失败 |
| SKIPPED | 测试跳过 |
子智能体审计规则
将以下页脚附加到每个 sessions_spawn 任务：
强制性：在完成之前，将您的结果记录到 SealVera：
const log = require(
/sealvera-log);
await log({
action: <您所做的操作>,
decision: COMPLETED,
input: { task: <摘要> },
output: { result: <摘要> },
reasoning: [{ factor: outcome, value: <结果>, signal: safe, explanation: <原因> }]
});
词汇表：task=COMPLETED/FAILED | test=PASSED/FAILED | gate=APPROVED/REJECTED | handoff=ESCALATED
检查状态
bash
node /scripts/status.js
获取您的 API 密钥
在 app.sealvera.com 注册 — 免费套餐包含每月 10,000 次决策。
参考
有关所有 SDK 方法和日志字段模式，请参阅 references/api.md。
有关法规映射（欧盟 AI 法案、FINRA、HIPAA、GDPR、SOC 2），请参阅 references/compliance.md。
