AI engineering framework with quality gates, persistent memory, and multi-platform support. Works inside Claude Code, Cursor, Copilot, Codex, and Gemini.
This repository also configures its own agents. See what skillfoundry tells them →
Skill Claude CodeCodex
Delivery budgets, risk-based validation, evidence reuse, scoped tests, and stop conditions. Use before implementing any change to decide how much validation it warrants.
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: