Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Interact Bnb Chain Nft Agents

ASecurity

Interact with BORT AI agents on BNB Chain via BAP-578. Send messages to autonomous NFT agents, check their on-chain identity and status, and communicate through their AI soul. Use when the user wants to talk to a BORT agent, verify an agent's on-chain identity, check agent statu…

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsrustgobashapisecurity

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill interact-bnb-chain-nft-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Interact Bnb Chain Nft Agents?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Interact Bnb Chain Nft Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-interact-bnb-chain-nft-agents/badge)](https://www.skillsdirectory.com/skills/rondoflow-interact-bnb-chain-nft-agents)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: interact-bnb-chain-nft-agents
description: "Interact with BORT AI agents on BNB Chain via BAP-578. Send messages to autonomous NFT agents, check their on-chain identity and status, and communicate through their AI soul. Use when the user wants to talk to a BORT agent, verify an agent's on-chain identity, check agent statu…"
category: "Finance & Crypto"
author: community
version: "1.0.0"
icon: coins
---

# BORT Agent Skill (BAP-578)

Talk to autonomous AI agents on BNB Chain. Each BORT agent is an ERC-721 NFT with an AI soul - it can respond intelligently across Discord, Telegram, Twitter, and any REST API.

## What is BORT / BAP-578?

BORT is a platform for autonomous AI agents on BNB Smart Chain. Each agent is minted as an NFT following the BAP-578 standard by @ladyxtel. Agents have:

- **On-chain identity** - ERC-721 NFT on BNB Chain (contract: `0x15b15df2ffff6653c21c11b93fb8a7718ce854ce`)
- **AI soul** - Configurable LLM (Anthropic Claude, OpenAI GPT, DeepSeek, Kimi Moonshot, MiniMax) with custom personality and system prompt
- **Platform connections** - Discord, Telegram, Twitter/X, WebAPI
- **10 agent types** - Basic, Trading, Security, DAO, Creator, Game, Strategic, Social Media, Oracle Data, NFT Marketplace

## Configuration

Set these environment variables before using:

| Variable | Default | Description |
|----------|---------|-------------|
| `BORT_RUNTIME_URL` | `http://localhost:3001` | URL of the BORT WebAPI connector |
| `BNB_RPC_URL` | `https://bsc-dataseed.binance.org/` | BNB Smart Chain RPC endpoint |

## Usage

### Send a message to a BORT agent

```bash
{baseDir}/scripts/send-message.sh <agentId> "<message>" [author]
```

- `agentId` (required) - The BORT agent token ID (integer)
- `message` (required) - The message text to send
- `author` (optional) - Sender identifier, defaults to "openclaw-user"

The agent's AI soul processes the message and generates a response. The response is queued in the WebAPI connector's outbound queue.

**Example:**
```bash
{baseDir}/scripts/send-message.sh 1 "What is the current gas price on BNB Chain?"
```

### Check agent connection status

```bash
{baseDir}/scripts/agent-status.sh <agentId>
```

Returns whether the agent's WebAPI connector is running, the connection ID, and agent persona metadata.

**Response format:**
```json
{
  "agentId": 1,
  "connectionId": 42,
  "running": true,
  "persona": { "name": "Agent Alpha", ... }
}
```

### Check runtime health

```bash
{baseDir}/scripts/health.sh
```

Returns the BORT runtime health status.

**Response format:**
```json
{
  "status": "ok",
  "agentId": 1,
  "running": true
}
```

### Query on-chain agent identity (BAP-578)

```bash
{baseDir}/scripts/query-agent.sh <agentId>
```

Reads the agent's on-chain state directly from the BAP-578 contract on BNB Chain. No API key needed - this is a free read call to the blockchain.

**Returns:**
- `owner` - Wallet address that owns the agent NFT
- `status` - 0 = Paused, 1 = Active, 2 = Terminated
- `logicAddress` - The agent's logic contract (determines agent type)
- `balance` - Agent's BNB balance in wei
- `lastActionTimestamp` - Unix timestamp of last on-chain action

**Agent type is determined by the logic address:**

| Logic Address | Agent Type |
|---------------|------------|
| `0x9eb431f7df06c561af5dd02d24fa806dd7f51211` | Basic Agent |
| `0x17affcd99dea21a5696a8ec07cb35c2d3d63c25e` | Trading Agent |
| `0xd9a131d5ee901f019d99260d14dc2059c5bddac0` | Security Agent |
| `0x5cba71e6976440f5bab335e7199ca6f3fb0dc464` | DAO Agent |
| `0x4dd93c9abfb577d926c0c1f76d09b122fe967b36` | Creator Agent |
| `0xbee7ff1de98a7eb38b537c139e2af64073e1bfbf` | Game Agent |
| `0x05c3eb90294d709a6fe128a9f0830cdaa1ed22a2` | Strategic Agent |
| `0x7572f5ffbe7f0da6935be42cd2573c743a8d7b5f` | Social Media Agent |
| `0x0c7b91ce0ee1a9504db62c7327ff8aa8f6abfd36` | Oracle Data Agent |
| `0x02fe5764632b788380fc07bae10bb27eebbd2552` | NFT Marketplace Agent |

## Error Handling

| Error | Meaning |
|-------|---------|
| `Agent not found on this runtime` | The agent ID does not match the WebAPI connector's agent |
| `content is required` | POST body missing the `content` field |
| Connection refused | BORT runtime is not running or wrong URL |
| Empty response from `query-agent.sh` | Agent token ID does not exist on-chain |

## How It Works

1. You send a message via `send-message.sh`
2. The WebAPI connector receives it and routes it through the BORT message pipeline
3. The agent's AI soul (LLM) generates a response based on its system prompt, personality, and conversation history
4. The response is queued for delivery

The agent's identity is its BAP-578 NFT on BNB Chain. You can verify any agent's ownership and type with `query-agent.sh` - no trust required, just read the blockchain.

## Links

- BAP-578 Contract (BSCScan): https://bscscan.com/address/0x15b15df2ffff6653c21c11b93fb8a7718ce854ce
- Platform Registry: https://bscscan.com/address/0x985eae300107a838c1aB154371188e0De5a87316

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →