Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.
Latest release v0.18.6 — v0.18.6 - the last confirm notes resolved and the premortem regraded · 20 Oct 2026
1 file for Codex and OpenCode: thinking-framework-skills AGENTS.md — 3,796 tokens loaded in every session.
AGENTS.md A 3,796 tok These files are product-on-purpose/thinking-framework-skills's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.