Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Version 1.2.0 of agent-signet-id - All API routes now available under both the root path and /v1/ (e.g., /v1/register/self). - Responses include an X-Request-Id header for improved debugging and traceability. - Self-registration flow now starts agents at composite_score 300 and recommendation "caution"; field identity_level (starting at 0) is included in responses. - Public and detailed score lookups now include identity_level. - Updated scoring and recommendation system: “clear” status requires score ≥700, medium+ confidence, and identity level 1+. - Added identity verification via callback (documented new /agents/{sid}/verify and /verify/confirm endpoints); only verified agents can achieve “clear” trust status. - Support for API key rotation via the new /me/rotate-key endpoint. - Paging parameters (limit, offset) added to the profile (/me) endpoint. - Documentation updates to clarify confidence levels, identity levels, scoring, and adjustment limits.
What This Skill Does
Signet is a trust scoring platform for autonomous AI agents. It assigns each registered agent a unique Signet ID and a composite score from 0 to 1000 across five dimensions: reliability, quality, financial, security, and stability. Platforms query this score to decide whether to allow an agent to transact.
Unlike ad-hoc reputation schemes, Signet provides a standardized, multi-dimensional trust score that external platforms can query without coordinating directly with the agent's operator.
When to use it
- Registering a new agent to establish a verifiable identity before deployment
- Checking a third-party agent's trust score before granting it access to a system
- Reporting task completion outcomes to build up an agent's score over time
- Rotating an API key after a suspected credential leak
- Verifying agent identity via callback to unlock 'clear' recommendation status
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Register my agent and check its initial trust score
- 1POST to /register/self with agent name, model provider, and model name
- 2Store the returned api_key as SIGNET_API_KEY environment variable
- 3Note the assigned SID from the registration response
- 4GET /score/{sid}/public using the returned SID
- 5Return the composite_score, confidence level, and recommendation to the user
Agent registered with SID 'SID-0x7a3f8b2c1d4e5f6a', initial composite score 300, confidence 'low', recommendation 'caution'
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.