No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by solana-foundation · Codex Skill · ★ 559
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is solana-dev-skill safe to install? View the security audit →
Solana Development Skill for Claude Code A comprehensive Claude Code skill for modern Solana development (January 2026 best practices). Overview This skill provides Claude Code with deep knowledge of the current Solana development ecosystem: UI: Solana Foundation framework-kit ( + ) SDK: (v5.x) for new client work Legacy Interop: for bridging to web3.js dependencies Programs: Anchor (default), Pinocchio for high-performance needs Testing: LiteSVM/Mollusk for unit tests, Surfpool for integration Codegen: Codama-first IDL and client generation Security: Comprehensive vulnerability patterns and prevention Toolchain: Version compatibility, common errors, and troubleshooting guides Installation Quick Install Manual Install Skill Structure skill/ ├── SKILL.md # Main skill definition (required) ├── frontend-framework-kit.md # UI patterns with framework-kit ├── kit-web3-interop.md # Kit ↔ web3.js boundary patterns ├── programs-anchor.md # Anchor program development ├── programs-pinocchio.md # Pinocchio (high-performance native) ├── testing.md # Testing (LiteSVM/Mollusk/Surfpool) ├── id
| Stars | 559 |
| Forks | 136 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75.1841455987924/100 |
| Open Issues | 20 |
| Last Updated | 2026-09-21 |
| Created | 2026-01-12 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~15k |
These tools work well together with solana-dev-skill for enhanced workflows:
Looking for a solana-dev-skill alternative? If you're comparing solana-dev-skill with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, a
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organ
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa
Explore other popular codex skill tools:
solana-dev-skill is Skills for agentic development on Solana. It is categorized as a Codex Skill with 559 GitHub stars.
solana-dev-skill is primarily written in TypeScript. It covers topics such as claude, codex, skills-sh.
You can find installation instructions and usage details in the solana-dev-skill GitHub repository at github.com/solana-foundation/solana-dev-skill. The project has 559 stars and 136 forks, indicating an active community.
solana-dev-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to solana-dev-skill on Agent Skills Hub include skillfile, Overture, hevy-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: