ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

safe-multisig-skill

Propose, confirm, and execute Safe multisig transactions using the Safe{Core} SDK (protocol-kit v6 / api-kit v4). TypeScript strict. Use when an agent needs to operate a Safe smart account — (1) create/predict a new Safe, (2) fetch Safe owners/threshold/nonce, (3) list pending multisig txs, (4) build + propose a tx, (5) add confirmations, (6) execute a tx onchain, or (7) troubleshoot Safe nonce/signature issues across chains (Base/Ethereum/Optimism/Arbitrum/Polygon/etc.).

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/openclaw-consensus-bot/safe-multisig
Or

Safe Multisig Skill

TypeScript-strict scripts for interacting with Safe multisig accounts via:

  • Safe Transaction Service (read state, propose txs, submit confirmations)
  • Safe{Core} SDK (create Safes, create txs, compute hashes, sign, execute)

All scripts use ethers v6, validate inputs (addresses, tx hashes), and output JSON.

Quick start

cd <this-skill>
./scripts/bootstrap.sh

# sanity check network + service
./scripts/safe_about.sh --chain base

Core scripts

ScriptDescription
create-safe.tsPredict address + optionally deploy a new Safe
safe-info.tsFetch Safe info (owners/threshold/nonce)
list-pending.tsList pending (queued) multisig transactions
safe_txs_list.tsList all multisig transactions (queued + executed)
propose-tx.tsCreate + propose a multisig tx
approve-tx.tsAdd an off-chain confirmation for a tx hash
execute-tx.tsExecute a fully-confirmed tx onchain

All scripts: npx tsx scripts/<name>.ts --help

Common tasks

1) Create a new Safe

npx tsx scripts/create-safe.ts \
  --chain base \
  --owners 0xOwner1,0xOwner2,0xOwner3 \
  --threshold 2

Add --deploy + SAFE_SIGNER_PRIVATE_KEY to send the deployment tx.

2) Get Safe info

npx tsx scripts/safe-info.ts --chain base --safe 0xYourSafe

3) List pending transactions

npx tsx scripts/list-pending.ts --chain base --safe 0xYourSafe

4) Propose a new transaction

Create a tx request JSON (see references/tx_request.schema.json and references/examples.md).

export SAFE_SIGNER_PRIVATE_KEY="..."

npx tsx scripts/propose-tx.ts \
  --chain base \
  --rpc-url "$BASE_RPC_URL" \
  --tx-file ./references/example.tx.json

5) Confirm (approve) a proposed transaction

export SAFE_SIGNER_PRIVATE_KEY="..."

npx tsx scripts/approve-tx.ts \
  --chain base \
  --safe 0xYourSafe \
  --safe-tx-hash 0x...

6) Execute a confirmed transaction (onchain)

export SAFE_SIGNER_PRIVATE_KEY="..."

npx tsx scripts/execute-tx.ts \
  --chain base \
  --rpc-url "$BASE_RPC_URL" \
  --safe 0xYourSafe \
  --safe-tx-hash 0x...

Configuration

All scripts accept:

  • --chain <slug> (recommended): e.g. base, base-sepolia, mainnet, arbitrum, optimism
  • --tx-service-url <url>: Override the transaction service URL
  • --rpc-url <url>: RPC endpoint (or RPC_URL env var)
  • --api-key <key>: Safe Transaction Service API key (or SAFE_TX_SERVICE_API_KEY env var)

Security rules

  • Never paste private keys into chat. Use env vars or files.
  • Prefer low-privilege signers and spending limits.
  • Always verify Safe address, chainId / RPC, and nonce before signing.

References

  • references/examples.md — example requests + workflows
  • references/tx_request.schema.json — tx request JSON shape
  • references/tx_service_slugs.md — chain slugs + notes

Metadata

Stars1287
Views0
Updated2026-02-22
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-openclaw-consensus-bot-safe-multisig": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

agent-pulse

Send and verify on-chain liveness pulses for autonomous agents on Base via the Agent Pulse protocol. Use when you need to: (1) prove an agent is alive by sending a pulse, (2) check any agent's liveness status or streak, (3) monitor multiple agents, (4) view the global pulse feed, (5) auto-configure wallet and PULSE balance, (6) run scheduled heartbeat pulses, or (7) read protocol health and config. Supports both API and direct on-chain (cast) modes.

openclaw-consensus-bot 1287

uniswap-v4

Swap tokens and read pool state on Uniswap V4 (Base, Ethereum). Use when the agent needs to: (1) swap ERC20 tokens or ETH via Uniswap V4, (2) get pool info (price, tick, liquidity, fees), (3) find the best pool for a token pair, (4) quote expected swap output via the on-chain V4Quoter, (5) set up Permit2 approvals for the Universal Router, or (6) execute exact-input swaps with proper slippage protection. Supports Base and Ethereum mainnet, plus Base Sepolia testnet. TypeScript with strict types. Write operations need a private key via env var.

openclaw-consensus-bot 1287

safe-multisig-skill

Propose, confirm, and execute Safe multisig transactions using the Safe{Core} SDK (protocol-kit v6 / api-kit v4). TypeScript strict. Use when an agent needs to operate a Safe smart account — (1) create/predict a new Safe, (2) fetch Safe owners/threshold/nonce, (3) list pending multisig txs, (4) build + propose a tx, (5) add confirmations, (6) execute a tx onchain, or (7) troubleshoot Safe nonce/signature issues across chains (Base/Ethereum/Optimism/Arbitrum/Polygon/etc.).

openclaw-consensus-bot 1287

farcaster-skill

Post, read, search, and engage on Farcaster via the Neynar API. Use when an agent needs to: (1) post casts with text, embeds, or in channels, (2) reply to or thread casts, (3) read a user's feed or a channel feed, (4) search casts by keyword, (5) look up user profiles by username or FID, (6) like or recast, (7) delete casts, (8) list or search channels. Pure bash+curl+jq — zero npm dependencies.

openclaw-consensus-bot 1287