Binance Spot Skill

Spot request on Binance using authenticated API endpoints. Requires API key and secret key for certain endpoints. Return the result in JSON format.

Quick Reference

Parameters

Common Parameters

• symbol: Symbol to query (e.g., BNBUSDT)
• symbols: List of symbols to query
• permissions: List of permissions to query
• showPermissionSets: Controls whether the content of the permissionSets field is populated or not. Defaults to true (e.g., true)
• symbol: (e.g., BNBUSDT)
• fromId: ID to get aggregate trades from INCLUSIVE. (e.g., 1)
• startTime: Timestamp in ms to get aggregate trades from INCLUSIVE. (e.g., 1735693200000)
• endTime: Timestamp in ms to get aggregate trades until INCLUSIVE. (e.g., 1735693200000)
• limit: Default: 500; Maximum: 1000. (e.g., 500)
• timeZone: Default: 0 (UTC)
• recvWindow: The value cannot be greater than 60000. Supports up to three decimal places of precision (e.g., 6000.346) so that microseconds may be specified. (e.g., 5000)
• timestamp: (e.g., 1)
• quantity: (e.g., 1)
• quoteOrderQty: (e.g., 1)
• price: (e.g., 400)
• newClientOrderId: A unique id among open orders. Automatically generated if not sent. Orders with the same newClientOrderID can be accepted only when the previous one is filled, otherwise the order will be rejected.
• strategyId: (e.g., 1)
• strategyType: The value cannot be less than 1000000. (e.g., 1)
• stopPrice: Used with STOP_LOSS, STOP_LOSS_LIMIT, TAKE_PROFIT, and TAKE_PROFIT_LIMIT orders. (e.g., 1)
• trailingDelta: See Trailing Stop order FAQ. (e.g., 1)
• icebergQty: Used with LIMIT, STOP_LOSS_LIMIT, and TAKE_PROFIT_LIMIT to create an iceberg order. (e.g., 1)
• pegOffsetValue: Priceleveltopegthepriceto(max:100). SeePeggedOrdersInfo (e.g., 1)
• orderId: (e.g., 1)
• origClientOrderId:
• newQty: newQty must be greater than 0 and less than the order's quantity. (e.g., 1)
• cancelNewClientOrderId: Used to uniquely identify this cancel. Automatically generated by default.
• cancelOrigClientOrderId: Either cancelOrderId or cancelOrigClientOrderId must be sent. </br> If both cancelOrderId and cancelOrigClientOrderId parameters are provided, the cancelOrderId is searched first, then the cancelOrigClientOrderId from that result is checked against that order. </br> If both conditions are not met the request will be rejected.
• cancelOrderId: Either cancelOrderId or cancelOrigClientOrderId must be sent. </br>If both cancelOrderId and cancelOrigClientOrderId parameters are provided, the cancelOrderId is searched first, then the cancelOrigClientOrderId from that result is checked against that order. </br>If both conditions are not met the request will be rejected. (e.g., 1)
• listClientOrderId: A unique Id for the entire orderList
• quantity: (e.g., 1)
• limitClientOrderId: A unique Id for the limit order
• price: (e.g., 1)
• limitStrategyId: (e.g., 1)
• limitStrategyType: The value cannot be less than 1000000. (e.g., 1)
• limitIcebergQty: Used to make the LIMIT_MAKER leg an iceberg order. (e.g., 1)
• stopClientOrderId: A unique Id for the stop loss/stop loss limit leg
• stopPrice: (e.g., 1)
• stopStrategyId: (e.g., 1)
• stopStrategyType: The value cannot be less than 1000000. (e.g., 1)
• stopLimitPrice: If provided, stopLimitTimeInForce is required. (e.g., 1)
• stopIcebergQty: Used with STOP_LOSS_LIMIT leg to make an iceberg order. (e.g., 1)
• computeCommissionRates: Default: false See Commissions FAQ to learn more.
• orderListId: Either orderListId or listClientOrderId must be provided (e.g., 1)
• aboveClientOrderId: Arbitrary unique ID among open orders for the above order. Automatically generated if not sent
• aboveIcebergQty: Note that this can only be used if aboveTimeInForce is GTC. (e.g., 1)
• abovePrice: Can be used if aboveType is STOP_LOSS_LIMIT , LIMIT_MAKER, or TAKE_PROFIT_LIMIT to specify the limit price. (e.g., 1)
• aboveStopPrice: Can be used if aboveType is STOP_LOSS, STOP_LOSS_LIMIT, TAKE_PROFIT, TAKE_PROFIT_LIMIT. Either aboveStopPrice or aboveTrailingDelta or both, must be specified. (e.g., 1)
• aboveTrailingDelta: See Trailing Stop order FAQ. (e.g., 1)
• aboveStrategyId: Arbitrary numeric value identifying the above order within an order strategy. (e.g., 1)
• aboveStrategyType: Arbitrary numeric value identifying the above order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• abovePegOffsetValue: (e.g., 1)
• belowClientOrderId: Arbitrary unique ID among open orders for the below order. Automatically generated if not sent
• belowIcebergQty: Note that this can only be used if belowTimeInForce is GTC. (e.g., 1)
• belowPrice: Can be used if belowType is STOP_LOSS_LIMIT, LIMIT_MAKER, or TAKE_PROFIT_LIMIT to specify the limit price. (e.g., 1)
• belowStopPrice: Can be used if belowType is STOP_LOSS, STOP_LOSS_LIMIT, TAKE_PROFIT or TAKE_PROFIT_LIMIT Either belowStopPrice or belowTrailingDelta or both, must be specified. (e.g., 1)
• belowTrailingDelta: See Trailing Stop order FAQ. (e.g., 1)
• belowStrategyId: Arbitrary numeric value identifying the below order within an order strategy. (e.g., 1)
• belowStrategyType: Arbitrary numeric value identifying the below order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• belowPegOffsetValue: (e.g., 1)
• workingClientOrderId: Arbitrary unique ID among open orders for the working order. Automatically generated if not sent.
• workingPrice: (e.g., 1)
• workingQuantity: Sets the quantity for the working order. (e.g., 1)
• workingIcebergQty: This can only be used if workingTimeInForce is GTC, or if workingType is LIMIT_MAKER. (e.g., 1)
• workingStrategyId: Arbitrary numeric value identifying the working order within an order strategy. (e.g., 1)
• workingStrategyType: Arbitrary numeric value identifying the working order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• workingPegOffsetValue: (e.g., 1)
• pendingClientOrderId: Arbitrary unique ID among open orders for the pending order. Automatically generated if not sent.
• pendingPrice: (e.g., 1)
• pendingStopPrice: (e.g., 1)
• pendingTrailingDelta: (e.g., 1)
• pendingIcebergQty: This can only be used if pendingTimeInForce is GTC or if pendingType is LIMIT_MAKER. (e.g., 1)
• pendingStrategyId: Arbitrary numeric value identifying the pending order within an order strategy. (e.g., 1)
• pendingStrategyType: Arbitrary numeric value identifying the pending order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• pendingPegOffsetValue: (e.g., 1)
• pendingAboveClientOrderId: Arbitrary unique ID among open orders for the pending above order. Automatically generated if not sent.
• pendingAbovePrice: Can be used if pendingAboveType is STOP_LOSS_LIMIT , LIMIT_MAKER, or TAKE_PROFIT_LIMIT to specify the limit price. (e.g., 1)
• pendingAboveStopPrice: Can be used if pendingAboveType is STOP_LOSS, STOP_LOSS_LIMIT, TAKE_PROFIT, TAKE_PROFIT_LIMIT (e.g., 1)
• pendingAboveTrailingDelta: See Trailing Stop FAQ (e.g., 1)
• pendingAboveIcebergQty: This can only be used if pendingAboveTimeInForce is GTC or if pendingAboveType is LIMIT_MAKER. (e.g., 1)
• pendingAboveStrategyId: Arbitrary numeric value identifying the pending above order within an order strategy. (e.g., 1)
• pendingAboveStrategyType: Arbitrary numeric value identifying the pending above order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• pendingAbovePegOffsetValue: (e.g., 1)
• pendingBelowClientOrderId: Arbitrary unique ID among open orders for the pending below order. Automatically generated if not sent.
• pendingBelowPrice: Can be used if pendingBelowType is STOP_LOSS_LIMIT or TAKE_PROFIT_LIMIT to specify limit price (e.g., 1)
• pendingBelowStopPrice: Can be used if pendingBelowType is STOP_LOSS, STOP_LOSS_LIMIT, TAKE_PROFIT or TAKE_PROFIT_LIMIT. Either pendingBelowStopPrice or pendingBelowTrailingDelta or both, must be specified. (e.g., 1)
• pendingBelowTrailingDelta: (e.g., 1)
• pendingBelowIcebergQty: This can only be used if pendingBelowTimeInForce is GTC, or if pendingBelowType is LIMIT_MAKER. (e.g., 1)
• pendingBelowStrategyId: Arbitrary numeric value identifying the pending below order within an order strategy. (e.g., 1)
• pendingBelowStrategyType: Arbitrary numeric value identifying the pending below order strategy. Values smaller than 1000000 are reserved and cannot be used. (e.g., 1)
• pendingBelowPegOffsetValue: (e.g., 1)
• pendingQuantity: Sets the quantity for the pending order. (e.g., 1)
• omitZeroBalances: When set to true, emits only the non-zero balances of an account. Default value: false
• fromAllocationId: (e.g., 1)
• timestamp: (e.g., 1)
• preventedMatchId: (e.g., 1)
• fromPreventedMatchId: (e.g., 1)
• orderId: (e.g., 1)
• fromExecutionId: (e.g., 1)
• limit: Default:500; Maximum: 1000 (e.g., 500)

Enums

• interval: 1s | 1m | 3m | 5m | 15m | 30m | 1h | 2h | 4h | 6h | 8h | 12h | 1d | 3d | 1w | 1M
• windowSize: 1m | 2m | 3m | 4m | 5m | 6m | 7m | 8m | 9m | 10m | 11m | 12m | 13m | 14m | 15m | 16m | 17m | 18m | 19m | 20m | 21m | 22m | 23m | 24m | 25m | 26m | 27m | 28m | 29m | 30m | 31m | 32m | 33m | 34m | 35m | 36m | 37m | 38m | 39m | 40m | 41m | 42m | 43m | 44m | 45m | 46m | 47m | 48m | 49m | 50m | 51m | 52m | 53m | 54m | 55m | 56m | 57m | 58m | 59m | 1h | 2h | 3h | 4h | 5h | 6h | 7h | 8h | 9h | 10h | 11h | 12h | 13h | 14h | 15h | 16h | 17h | 18h | 19h | 20h | 21h | 22h | 23h | 1d | 2d | 3d | 4d | 5d | 6d
• type: FULL | MINI
• type: MARKET | LIMIT | STOP_LOSS | STOP_LOSS_LIMIT | TAKE_PROFIT | TAKE_PROFIT_LIMIT | LIMIT_MAKER | NON_REPRESENTABLE
• selfTradePreventionMode: NONE | EXPIRE_TAKER | EXPIRE_MAKER | EXPIRE_BOTH | DECREMENT | NON_REPRESENTABLE
• symbolStatus: TRADING | END_OF_DAY | HALT | BREAK | NON_REPRESENTABLE
• timeInForce: GTC | IOC | FOK | NON_REPRESENTABLE
• pegPriceType: PRIMARY_PEG | MARKET_PEG | NON_REPRESENTABLE
• pegOffsetType: PRICE_LEVEL | NON_REPRESENTABLE
• newOrderRespType: ACK | RESULT | FULL | MARKET | LIMIT
• cancelRestrictions: ONLY_NEW | NEW | ONLY_PARTIALLY_FILLED | PARTIALLY_FILLED
• cancelReplaceMode: STOP_ON_FAILURE | ALLOW_FAILURE
• orderRateLimitExceededMode: DO_NOTHING | CANCEL_ONLY
• stopLimitTimeInForce: GTC | IOC | FOK
• side: BUY | SELL
• aboveType: STOP_LOSS_LIMIT | STOP_LOSS | LIMIT_MAKER | TAKE_PROFIT | TAKE_PROFIT_LIMIT
• aboveTimeInForce: GTC | IOC | FOK
• abovePegPriceType: PRIMARY_PEG | MARKET_PEG
• abovePegOffsetType: PRICE_LEVEL
• belowType: STOP_LOSS | STOP_LOSS_LIMIT | TAKE_PROFIT | TAKE_PROFIT_LIMIT
• belowTimeInForce: GTC | IOC | FOK
• belowPegPriceType: PRIMARY_PEG | MARKET_PEG
• belowPegOffsetType: PRICE_LEVEL
• workingType: LIMIT | LIMIT_MAKER
• workingPegPriceType: PRIMARY_PEG | MARKET_PEG
• workingPegOffsetType: PRICE_LEVEL
• pendingPegPriceType: PRIMARY_PEG | MARKET_PEG
• pendingPegOffsetType: PRICE_LEVEL
• pendingAboveType: STOP_LOSS_LIMIT | STOP_LOSS | LIMIT_MAKER | TAKE_PROFIT | TAKE_PROFIT_LIMIT
• pendingAbovePegPriceType: PRIMARY_PEG | MARKET_PEG
• pendingAbovePegOffsetType: PRICE_LEVEL
• pendingBelowType: STOP_LOSS | STOP_LOSS_LIMIT | TAKE_PROFIT | TAKE_PROFIT_LIMIT
• pendingBelowPegPriceType: PRIMARY_PEG | MARKET_PEG
• pendingBelowPegOffsetType: PRICE_LEVEL
• workingSide: BUY | SELL
• workingTimeInForce: GTC | IOC | FOK
• pendingType: LIMIT | MARKET | STOP_LOSS | STOP_LOSS_LIMIT | TAKE_PROFIT | TAKE_PROFIT_LIMIT | LIMIT_MAKER
• pendingSide: BUY | SELL
• pendingTimeInForce: GTC | IOC | FOK
• pendingAboveTimeInForce: GTC | IOC | FOK
• pendingBelowTimeInForce: GTC | IOC | FOK

Authentication

For endpoints that require authentication, you will need to provide Binance API credentials. Required credentials:

• apiKey: Your Binance API key (for header)
• secretKey: Your Binance API secret (for signing)

Base URLs:

• Mainnet: https://api.binance.com
• Testnet: https://testnet.binance.vision
• Demo: https://demo-api.binance.com

Security

Share Credentials

Users can provide Binance API credentials in different ways. The agent will try to retrieve automatically with the two first ways the credentials, but users can also explicitly tell the agent that they have set the credentials or stored them in a .env file, and the agent should re-read that file when they do. The agent can also make http requests with the two first methods without user confirmation.

1. Environment variables

Search for the following specific variables only (never dump the full environment):

Authorized environment variables

• Mainnet: BINANCE_API_KEY and BINANCE_SECRET_KEY
• Testnet: BINANCE_TESTNET_API_KEY and BINANCE_TESTNET_SECRET_KEY
• Demo: BINANCE_DEMO_API_KEY and BINANCE_DEMO_SECRET_KEY

Read and use in a single exec call so the raw key never enters the agent's context:

KEY="$BINANCE_API_KEY"
SECRET="$BINANCE_SECRET_KEY"

response=$(curl -s -X GET "$URL" \
  -H "X-MBX-APIKEY: $KEY" \
  --data-urlencode "param1=value1")

echo "$response"

Environment variables must be set before OpenClaw starts. They are inherited at process startup and cannot be injected into a running instance. If you need to add or update credentials without restarting, use a secrets file (see option 2).

2. Secrets file (.env)

Check ~/.openclaw/secrets.env , ~/.env, or a .env file in the workspace. Read individual keys with grep, never source the full file:

# Try all credential locations in order
API_KEY=$(grep '^BINANCE_API_KEY=' ~/.openclaw/secrets.env 2>/dev/null | cut -d= -f2-)
SECRET_KEY=$(grep '^BINANCE_SECRET_KEY=' ~/.openclaw/secrets.env 2>/dev/null | cut -d= -f2-)

# Fallback: search .env in known directories (KEY=VALUE then raw line format)
for dir in ~/.openclaw ~; do
  [ -n "$API_KEY" ] && break
  env_file="$dir/.env"
  [ -f "$env_file" ] || continue

  # Read first two lines
  line1=$(sed -n '1p' "$env_file")
  line2=$(sed -n '2p' "$env_file")

  # Check if lines contain '=' indicating KEY=VALUE format
  if [[ "$line1" == *=* && "$line2" == *=* ]]; then
    API_KEY=$(grep '^BINANCE_API_KEY=' "$env_file" 2>/dev/null | cut -d= -f2-)
    SECRET_KEY=$(grep '^BINANCE_SECRET_KEY=' "$env_file" 2>/dev/null | cut -d= -f2-)
  else
    # Treat lines as raw values
    API_KEY="$line1"
    SECRET_KEY="$line2"
  fi
done

This file can be updated at any time without restarting OpenClaw, keys are read fresh on each invocation. Users can tell you the variables are now set or stored in a .env file, and you should re-read that file when they do.

3. Inline file

Sending a file where the content is in the following format:

abc123...xyz
secret123...key

• Never run printenv, env, export, or set without a specific variable name
• Never run grep on env files without anchoring to a specific key ('^VARNAME=')
• Never source a secrets file into the shell environment (source .env or . .env)
• Only read credentials explicitly needed for the current task
• Never echo or log raw credentials in output or replies
• Never commit TOOLS.md to version control if it contains real credentials — add it to .gitignore

Never Disclose API Key and Secret

Never disclose the location of the API key and secret file.

Never send the API key and secret to any website other than Mainnet and Testnet.

Never Display Full Secrets

When showing credentials to users:

• API Key: Show first 5 + last 4 characters: su1Qc...8akf
• Secret Key: Always mask, show only last 5: ***...aws1

Example response when asked for credentials: Account: main API Key: su1Qc...8akf Secret: ***...aws1 Environment: Mainnet

Listing Accounts

When listing accounts, show names and environment only — never keys: Binance Accounts:

• main (Mainnet/Testnet)
• testnet-dev (Testnet)
• futures-keys (Mainnet)

Transactions in Mainnet

When performing transactions in mainnet, always confirm with the user before proceeding by asking them to write "CONFIRM" to proceed.

Binance Accounts

main

• API Key: your_mainnet_api_key
• Secret: your_mainnet_secret
• Testnet: false

testnet-dev

• API Key: your_testnet_api_key
• Secret: your_testnet_secret
• Testnet: true

TOOLS.md Structure

## Binance Accounts

### main
- API Key: abc123...xyz
- Secret: secret123...key
- Testnet: false
- Description: Primary trading account

### testnet-dev
- API Key: test456...abc
- Secret: testsecret...xyz
- Testnet: true
- Description: Development/testing

### futures-keys
- API Key: futures789...def
- Secret: futuressecret...uvw
- Testnet: false
- Description: Futures trading account

Agent Behavior

1. Credentials requested: Mask secrets (show last 5 chars only)
2. Listing accounts: Show names and environment, never keys
3. Account selection: Ask if ambiguous, default to main
4. When doing a transaction in mainnet, confirm with user before by asking to write "CONFIRM" to proceed
5. New credentials: Prompt for name, environment, signing mode
6. When a request requires signing, if the request isn't an order and the API keys aren't described as mainnet, testnet or demo keys, try to make request to the different base urls and see if it works, without asking the user. If it works, store the keys with the corresponding environment.

Adding New Accounts

When user provides new credentials by Inline file or message:

• Ask for account name
• Ask: Mainnet, Testnet or Demo
• Store in TOOLS.md with masked display confirmation

Signing Requests

For trading endpoints that require a signature:

1. Detect key type first, inspect the secret key format before signing.
2. Build query string with all parameters, including the timestamp (Unix ms).
3. Percent-encode the parameters using UTF-8 according to RFC 3986.
4. Sign query string with secretKey using HMAC SHA256, RSA, or Ed25519 (depending on the account configuration).
5. Append signature to query string.
6. Include X-MBX-APIKEY header.

Otherwise, do not perform steps 4–6.

New Client Order ID

For endpoints that include the newClientOrderId parameter, the value must always start with agent-. If the parameter is not provided, agent- followed by 18 random alphanumeric characters will be generated automatically. If a value is provided, it will be prefixed with agent-

Example: agent-1a2b3c4d5e6f7g8h9i

User Agent Header

Include User-Agent header with the following string: binance-spot/1.1.0 (Skill)

See references/authentication.md for implementation details.