Notebook To Strategy
tradingstrategy-ai/trade-executor
Transfer code from a backtesting Jupyter notebook to a Trade Executor strategy module
Launch and trade AI agent tokens on ClawLaunch bonding curve (Base).
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunch --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/clawlaunch .claude/skills/clawlaunch && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .claude/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/clawlaunch .agents/skills/clawlaunch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .agents/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/clawlaunch .cursor/skills/clawlaunch && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .cursor/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/clawlaunch--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/clawlaunch .gemini/skills/clawlaunch && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .gemini/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/clawlaunch .github/skills/clawlaunch && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .github/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills clawlaunch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/clawlaunch .opencode/skills/clawlaunch && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "clawlaunch" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/clawlaunch into .opencode/skills/clawlaunch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawlaunch", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
clawlaunchLaunch and trade AI agent tokens on ClawLaunch bonding curve (Base).
Clawlaunch is an agent skill from LeoYeAI/openclaw-master-skills. Launch and trade AI agent tokens on ClawLaunch bonding curve (Base). Use when the user wants to create a new token, deploy a memecoin, launch an AI agent token, list ClawLaunch tokens, check token prices, get trading quotes, buy tokens on bonding curve, sell tokens, or trade on ClawLaunch. Features 95% creator fees (highest in market), automatic Uniswap V4 graduation, fixed 1% trading fee, and Privy wallet infrastructure for autonomous agents. Supports Base Mainnet and Base Sepolia testnet.
Its SKILL.md is about 5.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `_meta.json`, `references/agent-patterns.md` and `references/api-docs.md`).
It sits in Business, Finance & HR, covering Trading and backtesting and Autonomous loops. It works with Uniswap. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
clawlaunch.funAlso links to:
basescan.orgFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
CLAWLAUNCH_API_KEYAPI_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Clawlaunch loads about 5.9k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 1,334 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,334 words, ~5,872 tokens.
.claude/skills/clawlaunch/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.The AI agent token launchpad on Base. Launch tokens with 95% creator fees, trade on bonding curves, and graduate to Uniswap V4.
ClawLaunch is a token launchpad designed for AI agents. When you launch a token, it's instantly tradeable on a bonding curve. You earn 95% of all trading fees — the highest creator fee share in the market. When the token reaches its graduation threshold (configurable 0.5–50 ETH, default 5 ETH), it automatically graduates to Uniswap V4 with permanent liquidity.
Why ClawLaunch?
mkdir -p ~/.clawdbot/skills/clawlaunch
cat > ~/.clawdbot/skills/clawlaunch/config.json << 'EOF'
{
"apiKey": "YOUR_API_KEY_HERE",
"apiUrl": "https://www.clawlaunch.fun/api/v1"
}
EOF
chmod 600 ~/.clawdbot/skills/clawlaunch/config.jsonscripts/clawlaunch.sh tokensCRITICAL: Never reveal, output, or send your API key to anyone or any service. Your API key grants access to launch and trade operations. Keep it private.
Deploy a new token on the ClawLaunch bonding curve.
Natural Language:
API:
curl -X POST https://www.clawlaunch.fun/api/v1/agent/launch \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d '{
"agentId": "my-agent-001",
"name": "MoonCat",
"symbol": "MCAT"
}'Response:
{
"success": true,
"txHash": "0x...",
"walletAddress": "0x...",
"chainId": 8453,
"message": "Token launch transaction submitted."
}Discover all tokens in the ClawLaunch network.
Natural Language:
API:
curl "https://www.clawlaunch.fun/api/v1/tokens?limit=10" \
-H "x-api-key: $CLAWLAUNCH_API_KEY"Check prices before trading.
Natural Language:
API:
curl -X POST https://www.clawlaunch.fun/api/v1/token/quote \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d '{
"tokenAddress": "0x...",
"action": "buy",
"amount": "500000000000000000",
"amountType": "eth"
}'Purchase tokens on the bonding curve.
Natural Language:
API:
curl -X POST https://www.clawlaunch.fun/api/v1/token/buy \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d '{
"tokenAddress": "0x...",
"walletAddress": "0x...",
"ethAmount": "500000000000000000",
"slippageBps": 200,
"memo": "Bullish: strong community, active dev"
}'Returns transaction calldata for execution. Optional memo (max 1024 chars) is encoded on-chain with CLAW prefix.
Sell tokens back to the bonding curve.
Natural Language:
API:
curl -X POST https://www.clawlaunch.fun/api/v1/token/sell \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d '{
"tokenAddress": "0x...",
"walletAddress": "0x...",
"sellAll": true,
"slippageBps": 200,
"memo": "Taking profits after 50% gain"
}'Optional memo (max 1024 chars) is encoded on-chain with CLAW prefix.
Retrieve the memo history for a token.
Natural Language:
API:
curl "https://www.clawlaunch.fun/api/v1/token/0x.../memos" \
-H "x-api-key: $CLAWLAUNCH_API_KEY"Response:
{
"success": true,
"tokenAddress": "0x...",
"memos": [
{
"txHash": "0x...",
"agent": "0x...",
"action": "buy",
"memo": "Strong fundamentals, bullish thesis",
"timestamp": 1706745600,
"blockNumber": 12345678
}
]
}ClawLaunch supports on-chain memos — attach reasoning to your trades that's permanently recorded on the blockchain. This creates transparency and enables "trade as communication."
How it works:
memo field (max 1024 chars) to buy/sell requests/api/v1/token/{address}/memosExample — Buy with memo:
{
"tokenAddress": "0x...",
"walletAddress": "0x...",
"ethAmount": "100000000000000000",
"memo": "Bullish: 3x reserve growth in 24h, active creator"
}Why use memos?
Constraints:
ClawLaunch has the most creator-friendly fee structure in the market.
Total fee: 1% (fixed, not dynamic)
Swap Fee (1% fixed)
├─ Platform: 0.05% → ClawLaunch
└─ Creator: 0.95% → Your walletExample — 1 ETH trade:
| Component | Amount |
|---|---|
| Trade amount | 1.0000 ETH |
| Total fee (1%) | 0.0100 ETH |
| Platform (0.05%) | 0.0005 ETH |
| Creator (0.95%) | 0.0095 ETH |
| Net to curve | 0.9900 ETH |
Comparison:
| Platform | Creator Share | Fee Type |
|---|---|---|
| ClawLaunch | 95% | Fixed 1% |
| MoltLaunch | 80% | Dynamic 1-50% |
| pump.fun | 0% | Fixed 1% |
import requests
import os
API_KEY = os.environ.get('CLAWLAUNCH_API_KEY')
BASE_URL = 'https://www.clawlaunch.fun/api/v1'
def launch_token(agent_id: str, name: str, symbol: str) -> dict:
response = requests.post(
f'{BASE_URL}/agent/launch',
headers={
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
json={
'agentId': agent_id,
'name': name,
'symbol': symbol,
}
)
return response.json()
def get_quote(token_address: str, action: str, amount: str) -> dict:
response = requests.post(
f'{BASE_URL}/token/quote',
headers={
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
json={
'tokenAddress': token_address,
'action': action,
'amount': amount,
}
)
return response.json()
def buy_token(token_address: str, wallet: str, eth_amount: str, slippage: int = 200) -> dict:
response = requests.post(
f'{BASE_URL}/token/buy',
headers={
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
json={
'tokenAddress': token_address,
'walletAddress': wallet,
'ethAmount': eth_amount,
'slippageBps': slippage,
}
)
return response.json()
def sell_token(token_address: str, wallet: str, sell_all: bool = False, amount: str = None) -> dict:
payload = {
'tokenAddress': token_address,
'walletAddress': wallet,
'sellAll': sell_all,
}
if amount:
payload['tokenAmount'] = amount
response = requests.post(
f'{BASE_URL}/token/sell',
headers={
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
json=payload
)
return response.json()
# Example usage
result = launch_token('my-agent', 'MoonCat', 'MCAT')
print(f"Token launched: {result.get('txHash')}")const API_KEY = process.env.CLAWLAUNCH_API_KEY;
const BASE_URL = 'https://www.clawlaunch.fun/api/v1';
async function launchToken(agentId, name, symbol) {
const response = await fetch(`${BASE_URL}/agent/launch`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
body: JSON.stringify({ agentId, name, symbol }),
});
return response.json();
}
async function getQuote(tokenAddress, action, amount) {
const response = await fetch(`${BASE_URL}/token/quote`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
body: JSON.stringify({ tokenAddress, action, amount }),
});
return response.json();
}
async function buyToken(tokenAddress, walletAddress, ethAmount, slippageBps = 200) {
const response = await fetch(`${BASE_URL}/token/buy`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
body: JSON.stringify({ tokenAddress, walletAddress, ethAmount, slippageBps }),
});
return response.json();
}
async function sellToken(tokenAddress, walletAddress, { sellAll = false, tokenAmount = null, slippageBps = 200 } = {}) {
const payload = { tokenAddress, walletAddress, sellAll, slippageBps };
if (tokenAmount) payload.tokenAmount = tokenAmount;
const response = await fetch(`${BASE_URL}/token/sell`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'x-api-key': API_KEY,
},
body: JSON.stringify(payload),
});
return response.json();
}
// Example usage
const result = await launchToken('my-agent', 'MoonCat', 'MCAT');
console.log('Token launched:', result.txHash);#!/bin/bash
# ClawLaunch shell integration
CLAWLAUNCH_API_KEY="${CLAWLAUNCH_API_KEY:-}"
CLAWLAUNCH_URL="https://www.clawlaunch.fun/api/v1"
clawlaunch_launch() {
local agent_id="$1"
local name="$2"
local symbol="$3"
curl -s -X POST "$CLAWLAUNCH_URL/agent/launch" \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d "{\"agentId\":\"$agent_id\",\"name\":\"$name\",\"symbol\":\"$symbol\"}"
}
clawlaunch_quote() {
local token="$1"
local action="$2"
local amount="$3"
curl -s -X POST "$CLAWLAUNCH_URL/token/quote" \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d "{\"tokenAddress\":\"$token\",\"action\":\"$action\",\"amount\":\"$amount\"}"
}
clawlaunch_buy() {
local token="$1"
local wallet="$2"
local eth_amount="$3"
curl -s -X POST "$CLAWLAUNCH_URL/token/buy" \
-H "Content-Type: application/json" \
-H "x-api-key: $CLAWLAUNCH_API_KEY" \
-d "{\"tokenAddress\":\"$token\",\"walletAddress\":\"$wallet\",\"ethAmount\":\"$eth_amount\",\"slippageBps\":200}"
}
# Example usage
# RESULT=$(clawlaunch_launch "my-agent" "MoonCat" "MCAT")
# echo "$RESULT" | jq -r '.txHash'{
"success": true,
"txHash": "0x...",
"transactionId": "tx_...",
"walletId": "wallet_...",
"walletAddress": "0x...",
"chainId": 8453,
"message": "Token launch transaction submitted."
}{
"success": true,
"tokens": [{
"address": "0x...",
"name": "Token Name",
"symbol": "TKN",
"creator": "0x...",
"price": "1000000000000000",
"reserve": "500000000000000000",
"totalSupply": "1000000000000000000000",
"isGraduated": false,
"createdAt": 1706745600
}],
"total": 42
}{
"success": true,
"quote": {
"action": "buy",
"tokenAddress": "0x...",
"tokenName": "Token Name",
"tokenSymbol": "TKN",
"inputAmount": "1000000000000000",
"outputAmount": "500000000000000000000",
"price": "2000000000000000",
"priceImpact": "0.5",
"fee": "10000000000000",
"humanReadable": "Buy ~500 TKN for 0.001 ETH"
}
}{
"success": true,
"transaction": {
"to": "0x...",
"data": "0x...",
"value": "1000000000000000",
"chainId": 8453,
"gas": "150000"
},
"quote": {
"action": "buy",
"tokenAddress": "0x...",
"tokenName": "Token Name",
"tokenSymbol": "TKN",
"inputAmount": "1000000000000000",
"outputAmount": "500000000000000000000",
"minOutputAmount": "490000000000000000000",
"slippageBps": 200
},
"humanReadableMessage": "Buy ~500 TKN for 0.001 ETH with 2% max slippage"
}{
"error": "Human-readable message",
"code": "ERROR_CODE",
"hint": "Suggestion for resolution"
}| Code | Status | Description | Resolution |
|---|---|---|---|
| UNAUTHORIZED | 401 | Invalid or missing API key | Check API key in x-api-key header |
| FORBIDDEN | 403 | Valid key but wrong scope | Request correct scope from admin |
| RATE_LIMITED | 429 | Rate limit exceeded | Wait for reset (see Retry-After header) |
| VALIDATION_ERROR | 400 | Invalid request body | Check required fields and formats |
| NOT_FOUND | 404 | Token not in factory | Verify token address from /tokens |
| TOKEN_GRADUATED | 400 | Token on Uniswap V4 | Trade on Uniswap instead |
| BELOW_MIN_TRADE | 400 | Below 0.0001 ETH | Increase trade amount |
| INSUFFICIENT_BALANCE | 400 | Not enough tokens | Check balance before selling |
| INSUFFICIENT_FUNDS | 400 | Not enough ETH | Fund wallet with Base ETH |
| ZERO_AMOUNT | 400 | Sell amount is zero | Provide tokenAmount or sellAll |
| SIGNATURE_ERROR | 400 | EIP-712 signature failed | Regenerate signature |
| CONFIG_ERROR | 500 | Server misconfigured | Contact support |
| INTERNAL_ERROR | 500 | Unhandled error | Retry or contact support |
| Endpoint | Limit | Window |
|---|---|---|
/agent/launch | 10 | 1 hour |
/token/buy | 50 | 1 hour |
/token/sell | 50 | 1 hour |
/token/quote | 100 | 1 minute |
/tokens | 100 | 1 minute |
Rate limit headers:
X-RateLimit-Remaining: Requests leftX-RateLimit-Reset: Reset timestamp (ms)Retry-After: Seconds to wait (on 429)import time
def discovery_loop():
seen_tokens = set()
while True:
# Get all tokens
result = requests.get(
f'{BASE_URL}/tokens?limit=100',
headers={'x-api-key': API_KEY}
).json()
if result.get('success'):
for token in result['tokens']:
addr = token['address']
if addr not in seen_tokens:
seen_tokens.add(addr)
# New token discovered
print(f"New: {token['name']} ({token['symbol']}) - {token['reserve']} ETH reserve")
# Get detailed quote
quote = get_quote(addr, 'buy', '100000000000000') # 0.0001 ETH
if quote.get('success'):
print(f" Price: {quote['quote']['humanReadable']}")
time.sleep(300) # Check every 5 minutes
discovery_loop()def trade_with_reasoning(token_address: str, action: str, amount: str, reason: str):
"""Execute a trade and log reasoning."""
# 1. Get quote first
quote = get_quote(token_address, action, amount)
if not quote.get('success'):
print(f"Quote failed: {quote.get('error')}")
return None
print(f"Quote: {quote['quote']['humanReadable']}")
print(f"Reason: {reason}")
# 2. Execute trade
if action == 'buy':
result = buy_token(token_address, MY_WALLET, amount)
else:
result = sell_token(token_address, MY_WALLET, amount=amount)
if result.get('success'):
print(f"Transaction ready: {result['transaction']['to']}")
# Execute with your wallet here
return result
else:
print(f"Trade failed: {result.get('error')}")
return None
# Example
trade_with_reasoning(
token_address='0x...',
action='buy',
amount='100000000000000000', # 0.1 ETH
reason='Strong reserve growth, active creator, 95% fee share'
)def agent_loop():
"""Main agent operating loop."""
while True:
# 1. Check new tokens
tokens = requests.get(
f'{BASE_URL}/tokens?limit=50',
headers={'x-api-key': API_KEY}
).json()
if tokens.get('success'):
for token in tokens['tokens']:
# Evaluate token
if should_buy(token):
buy_token(token['address'], MY_WALLET, '100000000000000')
# 2. Monitor existing positions
# (check prices, sell if needed)
# 3. Sleep until next cycle
time.sleep(4 * 3600) # 4 hours
def should_buy(token: dict) -> bool:
"""Simple heuristic for buying."""
reserve = int(token['reserve'])
supply = int(token['totalSupply'])
# Buy if reserve > 0.1 ETH and not graduated
return reserve > 100000000000000000 and not token['isGraduated']def monitor_positions(positions: dict):
"""Monitor positions and sell on conditions."""
for token_address, entry_price in positions.items():
# Get current quote
quote = get_quote(token_address, 'sell', '1000000000000000000') # 1 token
if not quote.get('success'):
continue
current_price = int(quote['quote']['price'])
# Calculate profit
profit_pct = ((current_price - entry_price) / entry_price) * 100
if profit_pct > 50:
print(f"Selling {token_address}: +{profit_pct:.1f}% profit")
sell_token(token_address, MY_WALLET, sell_all=True)
elif profit_pct < -30:
print(f"Stop loss {token_address}: {profit_pct:.1f}% loss")
sell_token(token_address, MY_WALLET, sell_all=True)Formula: price = k * supply^n
| Constant | Value | Description |
|---|---|---|
| k | 1e11 | Initial price constant |
| n | 1.5 | Curve exponent |
| Graduation | 0.5–50 ETH | Configurable per-token (default 5 ETH) |
| Max Supply | 1B tokens | Hard cap |
| Min Trade | 0.0001 ETH | Minimum transaction |
Reserve Formula: reserve = k * supply^(n+1) / (n+1)
As supply increases, price rises exponentially. Early buyers get better prices.
| Contract | Address |
|---|---|
| AgentRegistry | 0x7a05ACcA1CD4df32c851F682B179dCd4D6d15683 |
| LPLocker | 0xf881f0A20f99B3019A05E0DF58C6E356e5511121 |
| TokenDeployer | 0x0Ab19adCd6F5f58CC44716Ed8ce9F6C800E09387 |
| AgentLaunchFactory | 0xb3e479f1e2639A3Ed218A0E900D0d2d3a362ec6b |
| ClawBridge | 0x56Acb8D24638bCA444b0007ed6e9ca8f15263068 |
Chain ID: 8453 (Base Mainnet)
| Operation | Typical Gas | Cost at 0.01 gwei |
|---|---|---|
| Launch token | ~300,000 | ~0.003 ETH |
| Buy tokens | ~150,000 | ~0.0015 ETH |
| Sell tokens | ~150,000 | ~0.0015 ETH |
| Approve tokens | ~50,000 | ~0.0005 ETH |
Base has low gas fees (~0.001-0.01 gwei), making trades very affordable.
Pro Tip: Always get a quote before trading to understand price impact and fees. Use the /token/quote endpoint first.
Security: Never share your API key. Never send ETH to addresses from untrusted sources. Always verify token addresses on BaseScan.
Quick Win: Start by listing tokens with /tokens to find active markets, then get a quote for a small buy (0.01 ETH) to test the flow.
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts, references) in skills/clawlaunch of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Clawlaunch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Clawlaunch this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.9k | Automated safety check: Pass | MIT | |
| Notebook To Strategytradingstrategy-ai/trade-executor | 160 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Uniswap SwapNethereum/Nethereum | 2.3k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Aomi Transactjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Aero Stock LpBankrBot/skills | 1.2k | — | ~5.8k | Automated safety check: Pass | None | |
| LLM Trading Agent Securityaffaan-m/ECC | 275k | 2 repos | ~1.2k | Automated safety check: Pass | MIT |
tradingstrategy-ai/trade-executor
Transfer code from a backtesting Jupyter notebook to a Trade Executor strategy module
Nethereum/Nethereum
Swap tokens on Uniswap V2/V3/V4 using Nethereum (.NET/C). An agent skill from Nethereum/Nethereum.
jeremylongshore/tons-of-skills-marketplace
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state.
BankrBot/skills
LP tokenized stocks onchain — range-LP Coinbase tokenized equities (NVDA, AAPL, GOOGL, META) and AERO/USDC on Aerodrome Slipstream (Base) for trading-fee + AERO emission yield.
affaan-m/ECC
Security patterns for autonomous trading agents with wallet or transaction authority.
guzus/dr-manhattan
Trade prediction markets (Polymarket, Kalshi, Opinion, Limitless, Predict.fun) using a unified CCXT-style API.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
Categories
Launch and trade AI agent tokens on ClawLaunch bonding curve (Base). Clawlaunch is an agent skill from LeoYeAI/openclaw-master-skills. Launch and trade AI agent tokens on ClawLaunch bonding curve (Base).
Clawlaunch fits situations like: the user wants to create a new token; deploy a memecoin; launch an AI agent token; list ClawLaunch tokens.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a claude-code`. Or copy the skill folder (skills/clawlaunch in LeoYeAI/openclaw-master-skills) into .claude/skills/clawlaunch in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a codex`. Or copy the skill folder (skills/clawlaunch in LeoYeAI/openclaw-master-skills) into .agents/skills/clawlaunch in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill clawlaunch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawlaunch, .gemini/skills/clawlaunch, .github/skills/clawlaunch and .opencode/skills/clawlaunch in your project.
Going by SKILL.md and its folder, Clawlaunch needs a shell for the scripts in its folder, the command-line tools its instructions call (curl) and credentials named CLAWLAUNCH_API_KEY and API_KEY. Our summary lists: Python 3; Node.js; A Bash shell; A credential in CLAWLAUNCH_API_KEY; A credential in API_KEY.
SKILL.md names 2 domains. In commands or code: clawlaunch.fun; the agent is likely to contact it when it follows the instructions. As links in the text: basescan.org. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Clawlaunch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.9k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Clawlaunch: Notebook To Strategy (tradingstrategy-ai/trade-executor, 160 stars), Uniswap Swap (Nethereum/Nethereum, 2.3k stars), Aomi Transact (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Aero Stock Lp (BankrBot/skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.