Agent skill

Raptor Dex

by agiprolabs in agiprolabs/claude-trading-skills

Self-hosted Solana DEX aggregator by SolanaTracker — multi-hop routing across 25+ DEXes, WebSocket streaming, Yellowstone Jet TPU submission, no rate limits

MITAuto-check passedBackend & APIs

Install Raptor Dex

skills CLI
$ npx skills add agiprolabs/claude-trading-skills --skill raptor-dex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agiprolabs/claude-trading-skills raptor-dex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/raptor-dex .claude/skills/raptor-dex && rm -rf skills-src

Use ~/.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/

Facts

Skill name
raptor-dex
GitHub stars
410
Token cost
~2.2k tokens
SKILL.md length
546 words
Files
5 (incl. scripts, references)
Skills in repo
68
Repo updated
First seen
Licence
MIT

At a glance

Self-hosted Solana DEX aggregator by SolanaTracker — multi-hop routing across 25+ DEXes, WebSocket streaming, Yellowstone Jet TPU submission, no rate limits

  • Tasks that involve Realtime and WebSockets
  • SKILL.md covers Quick Start, Execution Flow, API Endpoints and Get a Quote, plus 8 more sections
  • Runs Python scripts from its folder; calls git; reaches github.com; needs YELLOWSTONE_TOKEN and PRIVATE_KEY
  • Tasks that involve Rate limiting

What it does

Raptor Dex is an agent skill from agiprolabs/claude-trading-skills. Self-hosted Solana DEX aggregator by SolanaTracker — multi-hop routing across 25+ DEXes, WebSocket streaming, Yellowstone Jet TPU submission, no rate limits

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api_reference.md`, `references/deployment.md` and `scripts/raptor_quote.py`).

It sits in Backend & APIs, covering Realtime and WebSockets and Rate limiting. It works with Solana. The repository describes itself as: 68 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools. The licence is MIT.

When your agent uses it

  • Tasks that involve Realtime and WebSockets
  • Tasks that involve Rate limiting

Example prompts

  • “/raptor-dex”

Requirements

  • Python 3
  • Docker
  • A credential in YELLOWSTONE_TOKEN
  • A credential in PRIVATE_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 981e1d7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • docs.solanatracker.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • YELLOWSTONE_TOKEN
    • PRIVATE_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Raptor Dex loads about 2.2k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 546 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from agiprolabs/claude-trading-skills at commit 981e1d7, republished under its MIT licence (© agiprolabs). 546 words, ~2,243 tokens.

Download SKILL.mdSave it as .claude/skills/raptor-dex/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
raptor-dex
description
Self-hosted Solana DEX aggregator by SolanaTracker — multi-hop routing across 25+ DEXes, WebSocket streaming, Yellowstone Jet TPU submission, no rate limits

Raptor — Self-Hosted Solana DEX Aggregator

Raptor is a self-hosted Rust binary that aggregates swap quotes across 25+ Solana DEXes. Unlike Jupiter, Raptor runs on your own infrastructure with no rate limits, no API key, and no dependency on external API availability. Free during public beta.

Quick Start

bash
# Clone the binary repo (includes required signature file)
git clone https://github.com/solanatracker/raptor-binary
cd raptor-binary

# Run with required environment variables
export RPC_URL="https://your-solana-rpc.com"
export YELLOWSTONE_ENDPOINT="https://your-yellowstone-grpc.com"
export YELLOWSTONE_TOKEN="your-token"  # if required by provider
./raptor
# Listens on 0.0.0.0:8080 by default

Requirements: Solana RPC endpoint + Yellowstone gRPC endpoint (for pool indexing). Raptor uses very few RPC calls during normal operation since pool state is streamed via Yellowstone.

Signature file: The signature file must be in the same directory as the Raptor binary. It authenticates your instance and is included in the repo clone. If you move the binary, copy the signature file with it.

Execution Flow

1. GET  /quote              → Best route across 25+ DEXes
2. POST /swap               → Unsigned versioned transaction
3. Sign locally              → Your private key never leaves your machine
4. POST /send-transaction   → Submit via Yellowstone Jet TPU
5. GET  /transaction/{sig}  → Confirm status (pending/confirmed/failed/expired)

API Endpoints

MethodEndpointDescription
GET/quoteGet swap quote with multi-hop routing
POST/swapBuild swap transaction from quote
POST/swap-instructionsGet swap instructions only (no tx wrapper)
POST/quote-and-swapQuote + transaction in one request
POST/send-transactionSubmit via Yellowstone Jet TPU with auto-retry
GET/transaction/:signatureTrack transaction status and parsed events
GET/healthHealth check (pools, cache, Yellowstone connection)

Get a Quote

python
import httpx

RAPTOR = "http://localhost:8080"

resp = httpx.get(f"{RAPTOR}/quote", params={
    "inputMint": "So11111111111111111111111111111111111111112",   # SOL
    "outputMint": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",  # USDC
    "amount": 1_000_000_000,  # 1 SOL in lamports
    "slippageBps": 50,
})
quote = resp.json()
print(f"Output: {quote['amountOut']} lamports")
print(f"Price impact: {quote['priceImpact']}%")
print(f"Route: {len(quote['routePlan'])} hops")
Quote Parameters
ParameterTypeRequiredDescription
inputMintstringYesInput token mint address
outputMintstringYesOutput token mint address
amountintegerYesAmount in smallest unit (lamports)
slippageBpsstringNoBasis points or "dynamic" (default: 50)
dexesstringNoComma-separated DEX filter
excludeDexesstringNoDEXes to exclude
maxHopsintegerNo1-4 hops (default: 4)
directRouteOnlybooleanNoOnly single-hop routes
poolsstringNoComma-separated pool address filter
feeBpsintegerNoPlatform fee 0-1000 bps
feeAccountstringNoFee recipient wallet

Build and Sign a Swap

python
import base64
import os

# Step 2: Build transaction from quote
resp = httpx.post(f"{RAPTOR}/swap", json={
    "quoteResponse": quote,
    "userPublicKey": "YOUR_WALLET_PUBKEY",
    "wrapUnwrapSol": True,
    "txVersion": "v0",
    "priorityFee": "auto",       # min|low|auto|medium|high|veryHigh|turbo|unsafeMax
    "maxPriorityFee": 100_000,    # cap in lamports
})
swap = resp.json()
# swap["swapTransaction"] is base64-encoded unsigned transaction

# Step 3: Sign locally (private key never sent to Raptor)
from solders.transaction import VersionedTransaction
from solders.keypair import Keypair

tx_bytes = base64.b64decode(swap["swapTransaction"])
tx = VersionedTransaction.from_bytes(tx_bytes)
keypair = Keypair.from_base58_string(os.getenv("PRIVATE_KEY"))
signed_tx = VersionedTransaction(tx.message, [keypair])
signed_b64 = base64.b64encode(bytes(signed_tx)).decode()

# Step 4: Submit via Yellowstone Jet TPU
resp = httpx.post(f"{RAPTOR}/send-transaction", json={
    "transaction": signed_b64,
})
result = resp.json()
print(f"Signature: {result['signature']}")

# Step 5: Track status
resp = httpx.get(f"{RAPTOR}/transaction/{result['signature']}")
status = resp.json()
# status: pending | confirmed | failed | expired
print(f"Status: {status['status']}, Latency: {status.get('latency_ms')}ms")

WebSocket Streaming

Real-time quote streaming with slot-based updates when pool state changes:

python
import asyncio, websockets, json

async def stream_quotes():
    async with websockets.connect("ws://localhost:8080/stream") as ws:
        await ws.send(json.dumps({
            "type": "subscribe",
            "inputMint": "So11111111111111111111111111111111111111112",
            "outputMint": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
            "amount": 1_000_000_000,
            "slippageBps": "50",
        }))
        async for msg in ws:
            data = json.loads(msg)
            if data.get("type") == "quote":
                print(f"Out: {data['data']['amountOut']} (slot {data['data']['contextSlot']})")

/stream/swap variant pre-builds transactions ready for signing, with automatic resend every 10 slots to prevent expiry.

Supported DEXes (25+)

Raydium: AMM, CLMM, CPMM, LaunchLab | Meteora: DLMM, Dynamic AMM, DAMM V2, Curve, DBC | Orca: Whirlpool v1/v2 | Bonding Curves: Pump.fun, Pumpswap, Heaven, MoonIt, Boopfun | PropAMM: Humidifi, Tessera, Solfi V1/V2, AlphaQ, ZeroFi, BisonFi, GoonFi V2 | Other: FluxBeam, PancakeSwap V3

Show full SKILL.md (207 more words)Show less

Configuration

Environment Variables
VariableRequiredDefaultDescription
RPC_URLYes—Solana RPC endpoint
YELLOWSTONE_ENDPOINTYes—Yellowstone gRPC endpoint
YELLOWSTONE_TOKENNo—Auth token (if provider requires)
BIND_ADDRNo0.0.0.0:8080Listen address
INCLUDE_DEXESNoallComma-separated DEX filter
EXCLUDE_DEXESNononeDEXes to exclude
WORKER_THREADSNoCPU coresWorker thread count
ENABLE_WEBSOCKETNofalseEnable /stream endpoints
ENABLE_YELLOWSTONE_JETNofalseEnable Jet TPU for /send-transaction
ENABLE_ARBITRAGENofalseEnable circular arbitrage routes
CLI Flags
bash
./raptor --include-dexes raydium,orca,meteora \
         --enable-websocket \
         --enable-yellowstone-jet \
         --workers 4
DEX Filtering Examples
bash
# Only bonding curve DEXes (for PumpFun sniping)
INCLUDE_DEXES="pumpfun,pumpswap,heaven,moonit,boopfun" ./raptor

# Only major AMMs
INCLUDE_DEXES="raydium,orca,meteora" ./raptor

Priority Fee Levels

LevelUse Case
min / lowCost-saving, non-urgent
auto / mediumRecommended default
high / veryHighFaster confirmation
turbo / unsafeMaxMaximum speed, competitive scenarios

Raptor vs Jupiter

FeatureRaptorJupiter
Self-hostedYesNo
Rate limitsNone (your hardware)API rate limits
DEX coverage25+30+
LatencyNetwork-localRemote API
CostFree (beta)Free (hosted)
Tx submissionYellowstone Jet TPUStandard RPC
On-chain programRaptorD5o...JUP...
API key requiredNoNo

Deployment

See references/deployment.md for Docker, Fly.io, and bare metal setup.

Files

References
Scripts
  • scripts/raptor_quote.py — Get and compare swap quotes with --demo mode
  • scripts/raptor_swap.py — Full swap flow: quote → build → sign → submit → confirm (simulation only in --demo)

© agiprolabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/raptor-dex of agiprolabs/claude-trading-skills.

  • SKILL.md
  • references/api_reference.md
  • references/deployment.md
  • scripts/raptor_quote.py
  • scripts/raptor_swap.py

Open the folder on GitHubat commit 981e1d7

Compare with similar skills

Raptor Dex 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.

Raptor Dex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Raptor Dex this skillagiprolabs/claude-trading-skills410—~2.2kAutomated safety check: PassMIT
Venice Crypto Rpcveniceai/skills144—~3.2kAutomated safety check: PassMIT
Domain Webfjrevoredo/mini-diarium3091 repos~1kAutomated safety check: PassMIT
Neon Functionsneondatabase/agent-skills100—~12kAutomated safety check: NotesApache-2.0
Switchboard Oracle SDKinternet-court/internet-court-skill6.6k2 repos~2.9kAutomated safety check: PassApache-2.0
Helius for Solanainternet-court/internet-court-skill6.6k1 repos~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Venice Crypto Rpc

    veniceai/skills

    Use Venice as a pay-per-call JSON-RPC proxy to 27 EVM, Starknet, and Solana networks.

    144 GitHub stars~3.2k tokensUpdated 4 days ago
    Backend & APIsAuto-check passed
  • Domain Web

    fjrevoredo/mini-diarium

    A skill your agent uses when building web services. An agent skill from fjrevoredo/mini-diarium.

    309 GitHub starsUsed in 1 repo~1k tokens
    Backend & APIsAuto-check passed
  • Neon Functions

    neondatabase/agent-skills

    Official

    Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.

    100 GitHub stars~12k tokensUpdated yesterday
    Backend & APIsAuto-check: notes
  • Switchboard Oracle SDK

    internet-court/internet-court-skill

    Covers integrating Switchboard oracles on Solana: pull feeds, oracle quotes, VRF randomness and Surge WebSocket streaming, from both the TypeScript SDK and Rust.

    6.6k GitHub starsUsed in 2 repos~2.9k tokens
    Backend & APIsAuto-check passed
  • Helius for Solana

    internet-court/internet-court-skill

    Guides building Solana apps on Helius: sending transactions, asset and NFT queries, live streaming, webhooks, priority fees, wallet analysis and API key onboarding.

    6.6k GitHub starsUsed in 1 repo~2.7k tokens
    Backend & APIsAuto-check passed
  • Ros2 Web Integration

    arpitg1304/robotics-agent-skills

    Patterns and best practices for integrating ROS2 systems with web technologies including REST APIs, WebSocket bridges, and browser-based robot interfaces.

    369 GitHub stars~13k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes

More from agiprolabs/claude-trading-skills

All 68 skills in this repo
  • Backtrader

    agiprolabs/claude-trading-skills

    Event-driven backtesting with bar-by-bar execution, complex order types, multiple analyzers, and custom indicators

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Birdeye API

    agiprolabs/claude-trading-skills

    Solana token market data via Birdeye — prices, OHLCV, trades, token metadata, security checks, and trader activity

    410 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Coingecko API

    agiprolabs/claude-trading-skills

    Broad crypto market data from CoinGecko covering 13,000+ tokens.

    410 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Cointegration Analysis

    agiprolabs/claude-trading-skills

    Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis

    410 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Copy Trading

    agiprolabs/claude-trading-skills

    Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Correlation Analysis

    agiprolabs/claude-trading-skills

    Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation

    410 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Raptor Dex

What does Raptor Dex do?

Self-hosted Solana DEX aggregator by SolanaTracker — multi-hop routing across 25+ DEXes, WebSocket streaming, Yellowstone Jet TPU submission, no rate limits. Raptor Dex is an agent skill from agiprolabs/claude-trading-skills.

When should I use Raptor Dex?

Raptor Dex fits situations like: tasks that involve Realtime and WebSockets; tasks that involve Rate limiting.

How do I install Raptor Dex in Claude Code?

Run `npx skills add agiprolabs/claude-trading-skills --skill raptor-dex -a claude-code`. Or copy the skill folder (skills/raptor-dex in agiprolabs/claude-trading-skills) into .claude/skills/raptor-dex in your project. Claude Code loads it when a task matches its description.

How do I install Raptor Dex in Codex?

Run `npx skills add agiprolabs/claude-trading-skills --skill raptor-dex -a codex`. Or copy the skill folder (skills/raptor-dex in agiprolabs/claude-trading-skills) into .agents/skills/raptor-dex in your project. Codex loads it when a task matches its description.

Can I use Raptor Dex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agiprolabs/claude-trading-skills --skill raptor-dex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/raptor-dex, .gemini/skills/raptor-dex, .github/skills/raptor-dex and .opencode/skills/raptor-dex in your project.

What does Raptor Dex need to run?

Going by SKILL.md and its folder, Raptor Dex needs Python for the scripts in its folder, the command-line tools its instructions call (git) and credentials named YELLOWSTONE_TOKEN and PRIVATE_KEY. Our summary lists: Python 3; Docker; A credential in YELLOWSTONE_TOKEN; A credential in PRIVATE_KEY.

Does Raptor Dex access the network?

SKILL.md names 2 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: docs.solanatracker.io. This is read from the text; nothing was executed.

Is Raptor Dex safe to install?

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.

What licence does Raptor Dex use?

Raptor Dex is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Raptor Dex use?

About 2.2k tokens (SKILL.md is roughly 9k 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 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Raptor Dex?

Skills that share tags, products or a category with Raptor Dex: Venice Crypto Rpc (veniceai/skills, 144 stars), Domain Web (fjrevoredo/mini-diarium, 309 stars), Neon Functions (neondatabase/agent-skills, 100 stars) and Switchboard Oracle SDK (internet-court/internet-court-skill, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Raptor Dex?

agiprolabs (a GitHub user) maintains it in agiprolabs/claude-trading-skills, which has 410 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on September 3, 2026.

Source: agiprolabs/claude-trading-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.