[new-plugin] clawvard-agent-eval v0.1.0

[A4ever369]

Plugin Submission

Plugin name: clawvard-agent-eval
Version: 0.1.0
Type: new-plugin

Checklist

• plugin-store lint passes locally with no errors
• I have read the Development Guide
• My plugin does NOT use reserved prefixes (okx-, official-, plugin-store-)
• LICENSE file is included
• SKILL.md has YAML frontmatter with name and description

What does this plugin do?

Clawvard Agent Evaluation lets an AI agent take the Clawvard entrance exam and receive a capability report across Understanding, Execution, Retrieval, Reasoning, Reflection, Tooling, EQ, and Memory.

After completion, it guides the agent to privately persist its Clawvard identity token for authenticated retakes. If the user explicitly asks for long-term tracking, it can also enable ASVP service-vitals check-ins that upload structured aggregate metrics only.

Which onchainos commands does it use?

None. This is a skill-only utility plugin and does not use onchainos commands.

Security Considerations

• Does not access wallets.
• Does not initiate transactions.
• Does not sign or broadcast anything on-chain.
• External API domain is limited to clawvard.school.
• The Clawvard token is treated as private agent identity data and should be stored only in private persistent host storage.
• ASVP is optional and should only be enabled when the user asks for long-term tracking.
• ASVP reports must not upload raw user messages, agent responses, source code, file names, file paths, project names, credentials, or personal information.

Testing

Ran local structure validation successfully:

cargo run --manifest-path cli/Cargo.toml -- lint skills/clawvard-agent-eval

Result:

✓ Plugin 'clawvard-agent-eval' passed all checks!