MCP App StoreMCP App Store
from solana-vibes-kit15
Phase-based adversarial security audit pipeline for Solana/Anchor codebases: scan, analyze, strategize, investigate, and report with parallel auditors and a str
Stronghold of Security (SOS) is a multi-phase audit skill for Solana/Anchor smart contracts. It orchestrates a pipeline that scans a codebase, builds a knowledge-base-backed index, deploys multiple parallel auditors to analyze distinct security lenses, synthesizes prioritized attack strategies, investigates hypotheses, and produces a final audit report and verification artifacts. The skill defines commands for each phase and a clear output structure under .audit/.
Use SOS when you need a comprehensive security review of a Solana/Anchor project — pre-mainnet audits, post-merge security checks, or regression verification after fixes. Invoke phase commands like /SOS:scan, /SOS:analyze, /SOS:strategize, /SOS:investigate, and /SOS:report to run each stage with fresh context windows.
Agents able to run CLAUDE CODE workflows, shell commands, and file-system operations (Claude Code, Copilot with shell access, CLI-capable agents).
Stronghold of Security (SOS) is a multi-phase adversarial security audit pipeline for Solana/Anchor smart contracts. It defines a 6-phase workflow (scan, analyze, strategize, investigate, report, verify) with 8-9 parallel auditor lenses and a 128-exploit-pattern knowledge base. No bundled scripts — the entire skill is a detailed orchestration guide for Claude Code CLI. Documentation is thorough with clear phase descriptions, commands table, and output structure.
Well-documented orchestration skill for Solana security audits. Large SKILL.md (~5KB body) is monolithic but internally well-structured. The version check mechanism is benign (git fetch + tag comparison). No security concerns — purely instructional with no executable code.
Forge — SVK Skill Builder
A meta-skill that scaffolds a 5‑phase pipeline to design, build, validate, and ship SVK skills with a strict shipping checklist and automation helpers.
Don't Break Shit (DBS)
Controlled change-management for large codebase modifications: guided brief → analysis → mapping → phased execution to avoid regressions and missed impacts.
SVK Update
Check for and selectively install updates to SVK skills by comparing installed versions against the latest git tags and reinstalling changed skills.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Monad Development
Practical developer skill for deploying and verifying smart contracts, configuring Foundry projects, and integrating frontends (viem/wagmi) on the Monad blockch
Reverse Engineer
Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Stellar iOS & Mac SDK
Native Swift SDK and guidance for building Stellar blockchain apps on iOS/macOS: transaction building, signing, Horizon queries, Soroban RPC, XDR handling, and
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r