Rust Hft Arbitrage logo

Rust Hft Arbitrage

CommunityPopular
alsk1992
rust-hft-arbitrage

Rust-first cross-venue HFT arbitrage specialist for Solana and EVM

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill namerust-hft-arbitrage
Stars
3K
Forks
353
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Rust Hft Arbitrage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/rust-hft-arbitrage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/rust-hft-arbitrage .claude/skills/rust-hft-arbitrage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rust Hft Arbitrage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Rust Hft Arbitrage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Rust Hft Arbitrage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Rust HFT Arbitrage Specialist

Snapshot date: 2026-08-30.

Clodds should treat this domain as a Rust-first execution problem with a TypeScript control plane.

Objective

Make Clodds reliable at price arbitrage between:

  • Solana AMMs and routers: Jupiter, Raydium, Orca, Meteora
  • Solana orderbook and perp venues already in-repo: Drift, Percolator
  • EVM routers and AMMs already in-repo: Uniswap, 1inch, PancakeSwap
  • EVM orderbook venue already in-repo: Lighter

Cross-chain arbitrage should assume pre-positioned inventory. A live bridge is inventory management, not an HFT hedge leg.

Specialist Rules

  • Separate planning from execution. The planner may be shared; the sender must stay chain-native.
  • Normalize instruments first. A route is valid only if both legs map to the same hedgeable instrument or clearly-defined basis pair.
  • Penalize stale quotes, routing latency, and inventory skew before a trade is considered actionable.
  • Use Rust for hot paths: quote normalization, orderbook math, nonce or blockhash management, and fire-path execution.
  • Keep Clodds in charge of orchestration, operator UX, skill routing, risk configuration, and post-trade reporting.

Reuse Map

CloddsBot

  • src/trading/venue-arbitrage.ts already provides a cross-venue scoring shell.
  • src/solana/* and src/evm/* already expose venue connectors and skills.
  • src/agents/subagents.ts already supports focused background task delegation.
  • src/skills/bundled/* already gives the operator surface for venue-specific commands.

p27

Use p27 as the Solana low-latency reference:

  • src/rpc/client.rs: cached blockhash, warm RPC path, live priority-fee tracking
  • src/monitor/websocket.rs: resilient WebSocket state monitor with reconnection logic
  • src/bundle/builder.rs: Jito bundle builder, tip tracking, V0 transaction support
  • src/platform.rs: unified TradingContext and state normalization across venue states
  • src/sell_engine/engine.rs: event-driven exit engine and verification discipline
  • src/wallet/* and src/volume/*: wallet fleet coordination and session control

op

Use op as the EVM low-latency reference:

  • src/nonce_ledger.rs: local nonce authority, reservation, rollback, background persistence
  • src/evm.rs: atomic writes, typed contract interfaces, and chain-specific guardrails
  • src/snipe.rs: rule engine structure for hot-path trigger logic
  • docs/v7-architecture.md: pre-signed fanout, isolated exit path, exact-hash confirmation

Target Architecture

text
Clodds chat + skills + risk config
        |
        v
Shared venue-arbitrage planner
        |
        +--> Solana Rust worker
        |     - quote normalization
        |     - Jito and priority-fee execution
        |     - inventory and fill reporting
        |
        +--> EVM Rust worker
              - nonce ledger
              - gas and relay fanout
              - exact-hash confirmation

Swarm Roles

Market-Structure Swarm

  • Build a canonical instrumentId
  • Classify each venue as AMM, router, CLOB, or perp
  • Define which venue pairs are directly hedgeable

Execution Swarm

  • Solana executor owns Jito, blockhashes, fee markets, and retry policy
  • EVM executor owns nonces, gas policy, relay fanout, and confirmation

Risk Swarm

  • Net-edge thresholds
  • Inventory caps by venue and by chain
  • Staleness and latency gates
  • Kill switches and venue health

Integration Swarm

  • Expose report, venue, reuse, and next-step views through a single skill
  • Keep one top-level Clodds operator session that can dispatch subagent work and merge results

Recommended Immediate Steps

  1. Expand the planner to accept concrete Solana and EVM venues, not only market platforms.
  2. Feed normalized quotes from existing Clodds connectors into that planner.
  3. Build Rust sidecars for chain-native execution using p27 and op patterns.
  4. Replay quote streams and calibrate real fee and latency penalties from logs.
  5. Emit one post-trade evidence report per opportunity.

Live Scan Command

Step 2 above is implemented in src/trading/venue-arbitrage-scanner.ts and wired into this skill as /hft-arb scan. It pulls live round-trip quotes (buy then sell) from the venues below, feeds them into the shared venue-arbitrage planner, and reports any net-positive crossed plans. This is read-only — it never signs or sends a transaction.

  • Solana: Jupiter, Raydium, Orca, Meteora
  • EVM: Uniswap, 1inch, PancakeSwap, Lighter (Arbitrum only)
  • Cross-chain: scans both sides and compares, assuming pre-positioned inventory

Usage: /hft-arb scan <solana|evm|cross> <base> <quote> <size> [options]. Run /hft-arb scan help for the full option list (venue selection, chain, edge/notional thresholds, slippage, RPC override).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Rust Hft Arbitrage AI skill do?

Rust-first cross-venue HFT arbitrage specialist for Solana and EVM

Why use Rust Hft Arbitrage on TypingMind?

Because you install it once and use it with any model. Rust Hft Arbitrage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Rust Hft Arbitrage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/rust-hft-arbitrage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Rust Hft Arbitrage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Rust Hft Arbitrage?

As many as you like. As long as a model supports skills, you can use Rust Hft Arbitrage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Rust Hft Arbitrage AI skill free?

Yes. It is published on GitHub by alsk1992 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇