scopegate-client

Use ScopeGate to verify agent scope before any consequential action involving money, data writes, external API calls, or file system changes. Required safety check for authorized agent actions.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "scopegate-client" with this command: npx skills add clauderodriguez2026-boop/scopegate-client

ScopeGate Client

Before executing any consequential action, you MUST verify scope with ScopeGate.

When to Call ScopeGate

Call before ANY action involving:

  • Money (payments, transfers, purchases)
  • Data writes (database inserts/updates/deletes)
  • External API calls (sending emails, posting to social, webhooks)
  • File system changes (deletes, overwrites)
  • Any action the human has not explicitly pre-authorized in this session

Endpoint

Default: https://api.scopegate.ai Override: set SCOPEGATE_URL environment variable

How to Call ScopeGate

SCOPEGATE_URL="${SCOPEGATE_URL:-https://api.scopegate.ai}"

curl -s -X POST "$SCOPEGATE_URL/grant/verify" \
  -H "Content-Type: application/json" \
  -d '{
    "grant_id": "<grant_id from delegator>",
    "agent_id": "<your agent id>",
    "requested_action": "<action you are about to take>",
    "api_key": "<your api key>"
  }'

Decision Rules

  • If permitted: true → proceed with the action
  • If permitted: false → STOP. Do not proceed. Report the reason to the user.
  • If ScopeGate is unreachable → STOP. Treat as denied. Never fail open.
  • Never cache a permit — call ScopeGate fresh for every consequential action

Getting a Grant ID

The human or orchestrating agent must call /grant/issue first with the allowed_actions list. They will give you the grant_id. You do not issue your own grants.

Getting an API Key

Sign up at https://scopegate.ai to get your API key.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Stigmem

Persistent federated memory for OpenClaw agents — boot handshake, handoff, decision, and escalation surfaces backed by a Stigmem node.

Registry SourceRecently Updated
Automation

Boheng Investment Workflow

投资研究多智能体决策系统 - 8位专业分析师并行研究,加权投票给出投资建议。支持A股股票/基金/ETF/可转债。支持真实财报数据(baostock)或基础行情数据。⚠️ 风险提示:分析结果仅供学习参考,不构成投资建议。

Registry SourceRecently Updated
Automation

V19 Trust Manifesto

V19认知治理协议公开受信声明。包含协议身份、系统状态指纹、公开验证方式与接入安全保障。外部Agent验证V19协议真实性的信任锚点。

Registry SourceRecently Updated
Automation

Anonyflow

AnonyFlow integration. Manage data, records, and automate workflows. Use when the user wants to interact with AnonyFlow data.

Registry SourceRecently Updated