agentleFS
Nunchi-tradeNunchi-trade/agent-cli/cli/skill.md

yex-trader

Skill521 starsChanged 7 months agoMITView on GitHub

Autonomous Hyperliquid trading — 14 strategies (MM, momentum, arbitrage, LLM) with APEX multi-slot orchestrator, REFLECT performance review, DSL trailing stops, and builder fee revenue collection.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run hl reflect run after a trading session.

    line 234

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

YEX Trader

Autonomous Hyperliquid trading via agent-cli. 14 strategies across market making, momentum, arbitrage, and LLM-powered trading. APEX multi-slot orchestrator. REFLECT nightly performance review. Builder fee revenue collection.

Quick Start (Agent-Friendly)

cd ~/agent-cli
bash scripts/bootstrap.sh           # Creates venv, installs, validates
hl wallet auto --save-env             # Creates wallet, saves creds to ~/.hl-agent/env
hl setup claim-usdyp                 # Claim testnet USDyP
hl builder approve                   # Approve builder fee (one-time)
hl run avellaneda_mm --mock --max-ticks 3  # Validate
hl run engine_mm -i ETH-PERP --tick 15 --max-ticks 5  # First live trade

For full step-by-step onboarding, see skills/onboard/SKILL.md.

Setup (Manual)

cd ~/agent-cli && pip install -e .
hl setup check  # Validate environment

Getting Started — YEX Testnet

  1. Set your private key (or use hl wallet auto):
export HL_PRIVATE_KEY=0x...
export HL_TESTNET=true  # default
  1. Claim testnet USDyP (required for YEX markets):
hl setup claim-usdyp
  1. Approve builder fee (one-time):
hl builder approve
  1. Start trading:
hl run avellaneda_mm -i VXX-USDYP --tick 15          # YEX yield market
hl run engine_mm -i ETH-PERP --tick 10                # Standard perp
hl apex run --mock --max-ticks 5                       # APEX multi-slot

Getting Started — Mainnet

  1. Set your private key and network:
export HL_PRIVATE_KEY=0x...
export HL_TESTNET=false
  1. Approve builder fee (one-time):
hl builder approve --mainnet
  1. Start trading:
hl run engine_mm -i ETH-PERP --tick 10 --mainnet      # ETH perp
hl run avellaneda_mm -i BTC-PERP --tick 10 --mainnet   # BTC perp
hl apex run --mainnet                                   # APEX multi-slot

Environment Variables

VariableRequiredDescription
HL_PRIVATE_KEYYes*Hyperliquid private key
HL_KEYSTORE_PASSWORDAlt*Password for encrypted keystore
HL_TESTNETNotrue (default) or false for mainnet
BUILDER_ADDRESSNoOverride builder fee address (default: hardcoded)
BUILDER_FEE_TENTHS_BPSNoOverride fee rate (default: 100 = 10 bps)
ANTHROPIC_API_KEYNoFor claude_agent strategy
GEMINI_API_KEYNoFor claude_agent with Gemini

* Either HL_PRIVATE_KEY or a keystore with HL_KEYSTORE_PASSWORD is required.

Commands

Core Trading

# Start autonomous trading
hl run <strategy> [-i INSTRUMENT] [-t TICK] [--config FILE] [--mainnet] [--dry-run] [--mock] [--max-ticks N]

# Single manual order
hl trade <instrument> <side> <size>

# Account info
hl account [--mainnet]

# Check positions and PnL
hl status [--watch] [--interval 5]

# List all strategies
hl strategies

APEX Multi-Slot Orchestrator

hl apex run [-t 60] [--preset conservative|default|aggressive] [--mock] [--budget 1000] [--slots 5]
hl apex once [--mock]
hl apex status
hl apex presets

REFLECT Performance Review

hl reflect run [--since 2026-03-01] [--data-dir data/cli]
hl reflect report [--date 2026-03-03]
hl reflect history [-n 10]

Dynamic Stop Loss (DSL)

hl dsl start <instrument> [--entry-price 2500] [--direction long] [--preset tight|standard|wide]
hl dsl check <instrument>
hl dsl status
hl dsl presets

Radar & Movers

hl radar run [--top 10] [--min-score 7.0]
hl radar history [-n 5]
hl movers run [--top 10]

Builder Fee

hl builder status
hl builder approve [--mainnet]

Wallet (Encrypted Keystore)

hl wallet auto                       # Non-interactive wallet creation (agent-friendly)
hl wallet create                     # Interactive wallet creation
hl wallet import --key <hex>
hl wallet list
hl wallet export [--address 0x...]

Environment Setup

hl setup check                       # Validate environment
hl setup bootstrap                   # Auto-create venv and install
hl setup claim-usdyp                 # Claim testnet USDyP tokens

MCP Server (24 Tools)

hl mcp serve                         # Start MCP server (stdio transport)
hl mcp serve --transport sse         # Start MCP server (SSE transport)

Tools: strategies, builder_status, wallet_list, wallet_auto, setup_check, funding_hedge_info, funding_hedge_propose, funding_hedge_backtest, account, status, trade, run_strategy, radar_run, apex_status, apex_run, reflect_run, schedule_cancel, emergency_close_all, order_status, funding_rates, agent_memory, trade_journal, judge_report, obsidian_context

Strategies (14)

NameTypeDescription
simple_mmMMSymmetric bid/ask quoting around mid
avellaneda_mmMMInventory-aware Avellaneda-Stoikov model
engine_mmMMProduction quoting engine — composite FV, dynamic spreads, multi-level ladder
regime_mmMMVol-regime adaptive — switches behavior by volatility regime (calm/normal/volatile/extreme)
grid_mmMMFixed-interval grid levels above and below mid
liquidation_mmMMProvides liquidity during cascade/liquidation events
funding_arbArbCross-venue funding rate arbitrage
basis_arbArbTrades implied basis from funding rate (contango/backwardation)
mean_reversionSignalTrades when price deviates from SMA
momentum_breakoutSignalEnters on volume + price breakout above/below N-period range
aggressive_takerTakerDirectional spread crossing with bias
hedge_agentRiskInventory exposure reducer; BTCSWP funding hedge lives under hl hedge
rfq_agentRFQBlock-size dark RFQ liquidity
claude_agentLLMClaude/Gemini-powered autonomous trading agent

Instruments

  • Standard perps: ETH-PERP, BTC-PERP, SOL-PERP, etc.
  • YEX yield markets: VXX-USDYP (yex:VXX), US3M-USDYP (yex:US3M)

Workflow

  1. Setup: hl setup check
  2. Claim USDyP (testnet only): hl setup claim-usdyp
  3. Approve builder fee: hl builder approve (testnet) or hl builder approve --mainnet
  4. Mock test: hl run avellaneda_mm --mock --max-ticks 5
  5. Dry run: hl run engine_mm --dry-run --max-ticks 10
  6. Live testnet: hl run engine_mm -i ETH-PERP --tick 10
  7. Live mainnet: hl run engine_mm -i ETH-PERP --tick 10 --mainnet
  8. APEX mode: hl apex run --mainnet or hl apex run --mock --max-ticks 5
  9. Monitor: hl status --watch
  10. Review: hl reflect run

Builder Fee Revenue

Set BUILDER_ADDRESS and BUILDER_FEE_TENTHS_BPS to collect fees on every trade. Users must approve once via hl builder approve. Fee is collected natively by Hyperliquid — no extra gas, no contract calls.

REFLECT Self-Improvement

Run hl reflect run after a trading session. REFLECT computes win rate, fee drag ratio (FDR), direction analysis, holding period buckets, monster trade dependency, and generates actionable recommendations. Reports saved to data/reflect/.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.