← Back to list
jito-bundles Checked
Jito bundle submission for MEV protection on Solana — bundle building, tip strategies, block engi…
9.1Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "jito-bundles" skill by following the instructions at https://skill123.me/install/jito-bundles.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/jito-bundles.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 21 KBAbout this skill
Overview
Jito bundle submission for MEV protection on Solana — bundle building, tip strategies, block engine endpoints, and landing rate optimization
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/jito-bundles
Score breakdown
Trigger
7.5
Description covers What (bundle building, tip strategies, endpoints, landing optimization); When/When-Not delivered via the SKILL.md scenario table including 'No' rows (simple transfers) though not in the description itself; good MEV/MEV-protection keywords.
Structure
9.3
300-line SKILL.md with three references (api, tip strategies, best practices) and two scripts; Files section maps roles and modes; no redundant files.
Workflow
9.2
Excellent execution design: scenario applicability table, safety-warning gate, demo-by-default, tip safety cap, error/fix table, multi-region retry pattern, and an explicit pre-submission checklist as verification loop.
Content
9.0
Dense imperative writing with concrete lamport tables and runnable argparse examples; small code bugs in SKILL.md snippets (undefined keypair, missing asyncio import) slightly reduce executability of the inline examples.
Engineering
10.0
Valid frontmatter; both scripts have shebangs, dependency notes, usage examples, and demo modes; all referenced paths exist.
Security
10.0
6.0 manifest: data reads limited to declared env vars; side effects none (scripts print only); network only to official Jito block-engine hosts; credentials none (live mode explicitly avoids wallet keys); persistence none. Capabilities match declared scope. No injection, no obfuscation, no destructive commands. Risk gating for real-funds execution is exemplary.
Trade-execution skill for Jito bundle submission on Solana, with strong risk gating for a funds-spending skill: prominent SAFETY WARNING, --demo default mode, MAX_TIP_LAMPORTS 0.01 SOL hard cap, pre-submission safety checklist, and live mode deliberately does not submit (no wallet key handling). Scripts runnable with argparse, help text, and mock responses. Minor: SKILL.md snippets have small bugs (undefined keypair in build_protected_swap_bundle, missing asyncio import in submit_with_retry). 6.0 manifest: network destinations limited to the four official *.block-engine.jito.wtf endpoints matching the declared purpose; env reads JITO_BLOCK_ENGINE/SOLANA_RPC_URL declared; no credential access, no file writes, no persistence. Capabilities match declared scope; tip accounts listed are the public Jito tip accounts.