Skip to main content

​
Overview

The Sage agent is a Nanobot skill pack. It’s the only component that talks to the user — over Telegram — and it routes every message and button tap to the Sage API. The server handles deterministic screening and execution; the agent handles everything conversational. Its role is intentionally narrow: call endpoints, report the actual result, never fabricate.

​
Setup

1

Link the skill into Nanobot's workspace

2

Restart the Nanobot gateway

3

Verify detection

Nanobot loads the skill from agents/SKILL.md and begins responding to Telegram commands.

​
Authentication

Every request to the Sage API carries the shared agent secret:
The same secret authorizes server-to-server calls (e.g. the queue handler self-calling /execute).

​
Owner Commands

Bare commands (no proposal ID) resolve to the latest in-review proposal for the vault.

​
Analysis Commands

​
Rules Commands

​
MCP Security Tools

Beyond the Sage API, the agent has access to security tools over MCP — GoPlus address & token intelligence, Rugcheck, and sanctioned-address lookups. This lets the owner ask open-ended questions (“is this address safe?”, “why was this flagged?”) and get a deep report inline, even outside a pending proposal.

​
Proposal Lifecycle

​
Environment Variables

The agent is conversational only. Scoring, thresholds, and execution all live on the server — the agent runs the call, waits for the response, and reports the real outcome.