Skill Claude Code
Pre-implementation research layer — identifies external components in requirements, researches each one from official sources, and produces a structured handoff report before any code is written.
Skill Codex
Research external APIs and SDKs before coding. Identifies every external component in a requirements file, browses official sources, and produces a structured handoff report with facts, risks, and answered questions.
Command Claude Code
Risk-rank a list of Solana contract addresses in parallel — identity + Rico Maps forensics — for curating which tokens your app should support.
Command Claude Code
Deployment Intelligence for Anchor programs. Run before anchor deploy so you know how much SOL you need and the exact ordered transaction sequence — instead of working it out by hand.
Command Claude Code
The Exploit Pattern Database — research-to-enforcement on real on-chain incidents. Each catalogued exploit is mapped to the bundled brainblast rule that statically detects its root-cause pattern, so the code that lost the funds is the exact code the rule fails on.
Command Claude Code
Fee Config Validator: the generalized Bags exploit. A curated catalog of the silent zero-revenue class — revenue-bearing config fields (fees, royalties, rewards) that, if omitted or set to zero, quietly collect nothing forever. The call succeeds, nothing reverts, and a creator/treasury/holder simply earns $0.
Command Claude Code
Inspect a serialized Solana transaction before signing it — the AI-agent transaction firewall.
Command Claude Code
Generate brainblast security rules from an Anchor IDL. The generated rule scans your program's Rust source and verifies it actually declares every account constraint the IDL promises — every isSigner account must be a Signer , every isMut account must carry mut/init. A missing constraint is a silent authorization hole.
Command Claude Code
Live On-Chain Intelligence: is the oracle fresh? Before you price anything against a Pyth / Switchboard / Chainlink feed, check when its account was last written.
Command Claude Code
The Protocol Pack Library. Every Solana app is built on some combination of Jupiter, Raydium, Pyth, Meteora, Jito, … — each with its own silent footguns. Opt into research-and-enforcement for the exact stack you build on.
Command Claude Code
Launch pre-flight for pump.fun / SPL token builders. Run before you list or integrate a token.
Command Claude Code
Runs a two-part token check on any Solana contract address (CA).
Command Claude Code
A 0–100 trust score and A–F grade for any deployed Solana program: upgrade authority (renounced > DAO > multisig > single-key), verified build, audits, directory curation, and cross-cluster parity — with a transparent factor breakdown.
Command Claude Code
Update Brainblast to the latest release. Run this command: curl -fsSL https://raw.githubusercontent.com/DSB-117/brainblast/main/install.sh | BRAINBLASTREF=latest sh.
Command Claude Code
Run the brainblast skill. Research every external component in the requirements before any code is written. Arguments (requirements file path, if provided): $ARGUMENTS.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: