aawp
AAWP (AI Agent Wallet Protocol) — the only crypto wallet protocol built exclusively for AI Agents on EVM-compatible blockchains. Not for humans. The signer is the AI Agent itself, cryptographically bound at wallet creation. Supports wallet lifecycle management, token transfers, DEX swaps, cross-chain bridging, arbitrary contract interactions, DCA automation, and price alerts.
What this skill does
# AAWP — AI Agent Wallet Protocol
The only crypto wallet protocol built exclusively for AI Agents. Not for humans.
AAWP enforces a single invariant: the signer is the AI Agent itself — locked in at wallet creation, immutable, verifiable on-chain. AI Agents manage their own on-chain assets across EVM networks through a guardian-based architecture. Transactions are signed locally via a sharded-key daemon — no human approval per tx, with full recovery and freeze capabilities for the human guardian.
**Networks:** Ethereum · Base · BNB Chain · Polygon · Optimism · Arbitrum
---
## Architecture Overview
```
┌─────────────────────────────────────────────────┐
│ AI Agent (OpenClaw) │
│ ┌───────────────┐ ┌──────────────────────┐ │
│ │ wallet-manager│───▶│ Signing Daemon │ │
│ │ dca / alerts │ │ (Unix socket) │ │
│ └───────────────┘ │ ┌──────────────────┐ │ │
│ │ │ aawp-core.node │ │ │
│ │ │ (Rust N-API) │ │ │
│ │ └──────────────────┘ │ │
│ └──────────┬───────────┘ │
│ │ sign │
│ ┌───────────────┐ ▼ │
│ │ Guardian Key │──▶ Pay gas ──▶ EVM Chain │
│ │ (gas only) │ │ │
│ └───────────────┘ ┌──────────▼───────────┐ │
│ │ Smart Contract Wallet │ │
│ │ (holds assets) │ │
│ └──────────────────────┘ │
└─────────────────────────────────────────────────┘
```
**Key separation:** Guardian pays gas → Wallet holds assets → Daemon signs transactions.
---
## Quick Reference
| Task | Command |
|------|---------|
| Create wallet | `wallet-manager.js --chain base create` |
| Check balance | `wallet-manager.js --chain base balance` |
| Send ETH | `wallet-manager.js --chain base send <to> <amount>` |
| Send ERC-20 | `wallet-manager.js --chain base send-token USDC <to> <amount>` |
| Get swap quote | `wallet-manager.js --chain base quote ETH USDC 0.01` |
| Execute swap | `wallet-manager.js --chain base swap ETH USDC 0.01` |
| Bridge cross-chain | `wallet-manager.js --chain base bridge ETH optimism 0.1` |
| Contract call | `wallet-manager.js --chain base call <addr> "fn(args)" ...` |
| Contract read | `wallet-manager.js --chain base read <addr> "fn() returns (uint)" ...` |
| DCA strategy | `dca.js add --chain base --from ETH --to USDC --amount 0.01 --cron "0 9 * * *"` |
| Price alert | `price-alert.js add --chain base --from ETH --to USDC --above 2600 --notify` |
| Cross-chain portfolio | `portfolio.js` |
| Single chain portfolio | `portfolio.js --chain base` |
| Limit order | `limit-order.js --chain base create ETH USDC 0.1 2700` |
| List orders | `limit-order.js --chain base list` |
| List NFTs | `nft.js --chain base balance` |
| NFT transfer | `nft.js --chain base transfer <contract> <tokenId> <to>` |
| NFT floor price | `nft.js --chain eth floor <contract>` |
| Yield rates | `yield.js --chain base rates` |
| Supply collateral | `yield.js --chain base supply USDC 1000` |
| Borrow | `yield.js --chain base borrow USDC 200` |
| Aave positions | `yield.js --chain base positions` |
| Diagnostics | `bash scripts/doctor.sh` |
| Backup | `wallet-manager.js backup ./backup.tar.gz` |
All commands: `node scripts/wallet-manager.js --help`
---
## Getting Started
### 1. Provision
First run is automatic — `ensure-daemon.sh` detects a missing seed and provisions.
```bash
bash scripts/provision.sh # Initialize
bash scripts/provision.sh --reset # Full reset (⚠️ destroys existing wallet)
```
### 2. Create Wallet
```bash
node scripts/wallet-manager.js --chain base create
```
If the Guardian needs gas, you'll see a funding guide with the Guardian address and private key.
### 3. Pin & Fund
```bash
export AAWP_WALLET=0x... # Pin your wallet address
# Send a small amount of native token to the wallet address
node scripts/wallet-manager.js --chain base balance
```
### 4. Test
```bash
node scripts/wallet-manager.js --chain base quote ETH USDC 0.001
node scripts/wallet-manager.js --chain base swap ETH USDC 0.001
```
> After fresh provisioning, verify the daemon binary hash is approved on the factory contract. If not, the factory owner must call `approveBinary(hash)`.
---
## Wallet Manager CLI
**Entry point:** `node scripts/wallet-manager.js`
**Chain flag:** `--chain <base|bsc|polygon|optimism|arbitrum|ethereum>`
### Wallet Lifecycle
```bash
wallet-manager.js --chain base status # Status overview
wallet-manager.js --chain base balance # Native + token balances
wallet-manager.js --chain base portfolio # Full portfolio view
wallet-manager.js compute-address # Predict wallet address
wallet-manager.js --chain base history # Transaction history
wallet-manager.js --chain base upgrade-signer # Rotate signer key
wallet-manager.js --chain base guardian-chains # Guardian chain info
```
### Transfers
```bash
wallet-manager.js --chain base send <recipient> <amount>
wallet-manager.js --chain base send-token <symbol> <recipient> <amount>
```
### Trading
```bash
wallet-manager.js --chain base quote <from> <to> <amount> # Preview (no gas)
wallet-manager.js --chain base swap <from> <to> <amount> # Execute
wallet-manager.js --chain base bridge <token> <dest> <amount> # Cross-chain
```
### Approvals
```bash
wallet-manager.js --chain base approve <token> <spender> <amount>
wallet-manager.js --chain base allowance <token> <spender>
wallet-manager.js --chain base revoke <token> <spender>
```
### Contract Interaction
```bash
# Write (sends tx)
wallet-manager.js --chain base call <contract> "transfer(address,uint256)" 0xTo 1000
# Read (free)
wallet-manager.js --chain base read <contract> "balanceOf(address) returns (uint256)" 0xAddr
# Batch (atomic)
wallet-manager.js --chain base batch ./calls.json
```
Batch format:
```json
[
{ "to": "0x...", "sig": "approve(address,uint256)", "args": ["0x...", "1000000"] },
{ "to": "0x...", "sig": "transfer(address,uint256)", "args": ["0x...", "500000"] }
]
```
### Address Book
```bash
wallet-manager.js addr add <label> <address>
wallet-manager.js addr list
wallet-manager.js addr get <label>
wallet-manager.js addr remove <label>
```
### RPC & Backup
```bash
wallet-manager.js get-rpc
wallet-manager.js --chain base set-rpc <url|default>
wallet-manager.js backup ./backup.tar.gz
wallet-manager.js restore ./backup.tar.gz
```
---
## DCA Automation
**Entry point:** `node scripts/dca.js`
```bash
dca.js add --chain base --from ETH --to USDC --amount 0.01 --cron "0 9 * * *" --name "Daily ETH→USDC"
dca.js list
dca.js run <id>
dca.js history <id>
dca.js remove <id>
```
Registers an OpenClaw cron job that executes swaps on schedule.
---
## Price Alerts
**Entry point:** `node scripts/price-alert.js`
```bash
# Notification only
price-alert.js add --chain base --from ETH --to USDC --above 2600 --notify
# Auto-swap on trigger
price-alert.js add --chain base --from ETH --to USDC --below 2200 --notify --auto-swap 0.01
price-alert.js list
price-alert.js check
price-alert.js remove <id>
```
---
## Daemon Management
| Script | Purpose |
|--------|---------|
| `scripts/doctor.sh` | Full diagnostic check |
| `scripts/ensure-daemon.sh` | Start daemon if not running (auto-provisions on first run) |
| `scripts/restart-daemon.sh` | Force restart |
Run `doctor.sh` before sensitive operations or when signing seems off.
---
## Cross-Chain Portfolio View
**Entry point:** `node scripts/portfolio.js`
**Supported chains:** All 6 (base · eth · arb · op · polygon · bsc) — queried **in parallel**
### Commands
```bash
portfolio.js # Full cross-chain summary with USD values
portfolio.js --chain base # Single chain only
portfolio.js --no-prices # Skip CoinGecko pricing (faster)
portfolio.js --hide-zero Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.