agents-best-practices: A provider-neutral Agent Skill library for designing, auditing, and refactoring agentic harnesses compatible with Codex and Claude Code. It covers the full control plane of an agent runtime: typed tool design, permission checks, context management, memory, and observability. Targeted at developers building production-ready agent systems across any domain or AI provider.; SchemaPin: SchemaPin enables tool developers to sign schemas and skill folders with ECDSA P-256 keys, and AI agents to verify schema integrity. Public keys are discovered via .well-known/schemapin.json, and Trust-On-First-Use pinning prevents key substitution. It supports key revocation, trust bundles, and multiple languages (Python, JS, Go, Rust).
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Signing and verifying tool schemas for AI agents to prevent tampering