Reivo

Track AI agent costs in real-time, set budget limits, and auto-detect runaway loops. Smart routing reduces costs 40-60%. Works with OpenAI, Anthropic, and Go...

This skill appears to do what it says: manage budgets and route requests through Reivo's proxy using a single REIVO_API_KEY. Before installing, consider the privacy/trust tradeoff: routing LLM API calls through proxy.reivo.dev means your agent's requests (and potentially prompt content) will transit a third party — verify Reivo's privacy policy and the open-source guardrail repo if you need guarantees. Use limited-scope or project-scoped provider keys as recommended, test with non-sensitive prompts first, and confirm the REIVO_API_KEY you receive matches the documented format (rv_...). Note: the registry describes the skill as instruction-only but the package includes Node scripts—if you plan to run any included scripts locally, review them (they call only app.reivo.dev and proxy.reivo.dev). If you need zero third‑party transit, consider self‑hosting the open-source reivo-guard instead.

Type: OpenClaw Skill Name: reivo Version: 0.4.4 The Reivo skill is a legitimate tool designed for AI agent cost optimization, budget enforcement, and loop detection. It functions by routing LLM API calls through a transparent proxy (proxy.reivo.dev) and providing a dashboard (app.reivo.dev) for monitoring. The JavaScript commands (e.g., budget.js, status.js, defense.js) and the SKILL.md instructions are consistent with the stated purpose and do not contain any evidence of malicious intent, data exfiltration of local secrets, or prompt injection attacks. While the service requires high trust due to its proxy architecture, the implementation is transparent and includes security-conscious instructions such as masking API keys in output.