bankofbots

Trust scoring for AI agents. Submit on-chain payment proofs and x402 receipts to build a verifiable BOB Score that other agents and services can check before doing business with yours.

3,891 stars

Best use case

bankofbots is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Trust scoring for AI agents. Submit on-chain payment proofs and x402 receipts to build a verifiable BOB Score that other agents and services can check before doing business with yours.

Teams using bankofbots should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/bankofbots/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/bankofbotsandy/bankofbots/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/bankofbots/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How bankofbots Compares

Feature / AgentbankofbotsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Trust scoring for AI agents. Submit on-chain payment proofs and x402 receipts to build a verifiable BOB Score that other agents and services can check before doing business with yours.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

## Core concepts

BOB (beta) is a non-custodial payment proof and trust layer. Agents submit cryptographic proofs of on-chain payments they made externally. Each proof builds credit history and raises their BOB Score, a 0–1000 reputation score for long-term financial trustworthiness.

- **Agent**: An AI agent with its own identity and BOB Score
- **Payment Proof**: Cryptographic evidence of an on-chain transaction (BTC, ETH, Base, or SOL txid/hash)
- **BOB Score**: 0–1000 reputation score derived from proof history, wallet binding, and social signals
- **Credit Event**: A scored action that changed the agent's BOB Score
- **Wallet Binding**: Proof of ownership over an external EVM wallet

## Quick start

```bash
bob init --code <claim-code>
bob auth me
```

## Commands

### Check your identity

```bash
bob auth me
```

### Agent management

```bash
bob agent create --name <name>
bob agent get <agent-id>
bob agent list
bob agent approve <agent-id>
```

### Import historical on-chain proofs

For outbound proofs, pass `--sender-address` (required for EVM proofs) so BOB can verify the on-chain sender matches your bound wallet. For inbound proofs, pass `--recipient-address` instead. When both the sender and recipient submit the same tx, confidence is boosted from Medium to Strong (see "Dual-sided proof submission" below).

```bash
# BTC on-chain (outbound)
bob agent credit-import <agent-id> \
  --proof-type btc_onchain_tx \
  --proof-ref <txid> \
  --rail onchain \
  --currency BTC \
  --amount <sats> \
  --direction outbound

# ETH on-chain (outbound — sender-address required)
bob agent credit-import <agent-id> \
  --proof-type eth_onchain_tx \
  --proof-ref <0x...txhash> \
  --rail onchain \
  --currency ETH \
  --amount <wei> \
  --direction outbound \
  --sender-address <your-bound-wallet>

# Base on-chain (outbound — sender-address required)
bob agent credit-import <agent-id> \
  --proof-type base_onchain_tx \
  --proof-ref <0x...txhash> \
  --rail onchain \
  --currency ETH \
  --amount <wei> \
  --direction outbound \
  --sender-address <your-bound-wallet>

# Solana on-chain (outbound)
bob agent credit-import <agent-id> \
  --proof-type sol_onchain_tx \
  --proof-ref <txsig> \
  --rail onchain \
  --currency SOL \
  --amount <lamports> \
  --direction outbound

# ETH on-chain (inbound — you received the payment)
bob agent credit-import <agent-id> \
  --proof-type eth_onchain_tx \
  --proof-ref <0x...txhash> \
  --rail onchain \
  --currency ETH \
  --amount <wei> \
  --direction inbound \
  --recipient-address <your-bound-wallet>

bob agent credit-imports <agent-id> [--limit 50] [--offset 0]
```

### Dual-sided proof submission

Both the sender and recipient of a transaction can independently submit a proof for the same on-chain tx. Each side earns credit:

- **Outbound** (`--direction outbound`, default): You sent the payment. Pass `--sender-address` for EVM proofs so the on-chain sender can be verified against your bound wallet.
- **Inbound** (`--direction inbound`): You received the payment. Pass `--recipient-address` for EVM proofs.

When both counterparties submit the same transaction, confidence is automatically upgraded from `medium` to `strong`.

### Import x402 payment receipts

```bash
bob agent x402-import <agent-id> \
  --tx <tx-hash> \
  --network eip155:8453 \
  --payer <wallet-address> \
  --payee <service-address> \
  --amount <atomic-units> \
  --resource-url <service-url>
```

### Agent credit and BOB Score

```bash
bob score me
bob agent credit-events <agent-id> [--limit 50] [--offset 0]

bob score me
bob score composition
bob score leaderboard
bob score signals --signal github --visible true
```

### Agent wallets

```bash
bob wallet list [--agent-id <id>]
bob wallet balance [--agent-id <id>]
bob wallet credit-limit [--agent-id <id>]
bob wallet addresses
bob wallet register --rail <evm|btc|solana> --address <addr> [--agent-id <id>]

```

### Operator command queue

Operators send commands to agents via the dashboard. Use `bob inbox check` to process pending commands.

```bash
# Check for and process pending commands (single check, exit)
bob inbox check [--agent-id <id>]

# Blocking loop for server agents
bob inbox check --poll [--interval 30s]
```

Currently supported command types: `wallet.provision`. Future: `transfer.request`, `loan.accept`, `kill_switch`, `key.rotate`.

## Heartbeat

When running during a heartbeat or periodic check-in, execute `bob inbox check --once` to process any pending operator commands. This covers wallet provisioning, fund transfers, and future command types.

- If commands are pending, process them and report what was done.
- If no commands are pending, continue with other tasks or reply HEARTBEAT_OK.

For lower-latency command processing, operators can create an OpenClaw cron job:
```bash
openclaw cron add --name "bob-inbox-check" --every 5m --session isolated \
  --message "Run bob inbox check --once to process pending operator commands. If none are pending, reply HEARTBEAT_OK."
```

### Bind a wallet

```bash
bob binding evm-challenge --address <0x...>
bob binding evm-verify --challenge-id <id> --address <0x...> --signature <sig> [--chain-id 0x1]
```

### Webhooks and inbox

```bash
bob webhook create <agent-id> --url https://example.com/hook --events proof.verified,credit.updated
bob webhook list <agent-id>
bob webhook get <agent-id> <webhook-id>
bob webhook update <agent-id> <webhook-id> --active true
bob webhook delete <agent-id> <webhook-id>

bob inbox list <agent-id> [--limit 30] [--offset 0]
bob inbox ack <agent-id> <event-id>
bob inbox events <agent-id> [--limit 30]
```

### API keys

```bash
bob api-key list
bob api-key create --name <label>
bob api-key revoke <key-id>
```

## Output format

```json
{
  "ok": true,
  "command": "bob agent credit-import",
  "data": {},
  "next_actions": [
    {
      "command": "bob score me",
      "description": "Check updated BOB Score"
    }
  ]
}
```

### Import MPP receipt (Tempo, Lightning, Stripe, Card)

```bash
bob agent mpp-import $BOB_AGENT_ID \
  --method tempo \
  --reference 0xabc123... \
  --challenge-id ch_xxx \
  --challenge-intent pay \
  --challenge-request <base64url-encoded-json> \
  --realm api.merchant.com \
  --source did:key:sender... \
  --resource-url https://api.merchant.com/v1/chat
```

Supported methods: `tempo` (stablecoin on Base), `lightning`, `stripe`, `card`.

## Error recovery

| Error | Cause | Fix |
|---|---|---|
| `sender_address_mismatch` | The `--sender-address` you provided does not match the on-chain sender of the transaction | Verify the address matches the actual sender on-chain and that it is bound to your agent via `bob binding evm-verify` |

### Passport (W3C Verifiable Credential)

```bash
# Step 1: Create auth key binding challenge
bob agent auth-key-challenge $BOB_AGENT_ID --alg Ed25519
# → returns challenge_id + message to sign with Ed25519 key

# Step 2: Verify auth key binding
bob agent auth-key-verify $BOB_AGENT_ID \
  --challenge-id <id> \
  --kid <key-id> \
  --public-key <base64url-ed25519-pubkey> \
  --signature <base64url-signature>

# Step 3: Issue passport (requires bound auth key)
bob agent passport-issue $BOB_AGENT_ID
# → returns W3C VC 2.0 signed passport

# Get current passport
bob agent passport-get $BOB_AGENT_ID
```

Businesses verify passports with the SDK (policy check — structure, expiry, score, issuer):

```javascript
import { verifyPassport } from '@bankofbots/sdk'
const result = await verifyPassport(passport, { minScore: 400 })
if (!result.valid) return res.status(403).json({ error: result.reason })
```

```python
from bob import verify_passport
result = verify_passport(passport, min_score=400)
if not result["valid"]: raise PermissionError(result["reason"])
```

## Important rules

1. Amounts are native atomic units: satoshis for BTC, wei for ETH/Base, lamports for SOL.
2. Proofs are non-custodial. BOB never holds your funds.
3. Historical on-chain proof imports and x402 receipt imports are the current public proof rails.
4. For outbound EVM proofs, `--sender-address` is required and must match the on-chain sender — mismatches fail with `sender_address_mismatch`.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation