One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I do not know is a supported outcome.
This repository also configures its own agents. See what zetetic-team-subagents tells them →
Plugin Claude Code
Bundles 21 skills, 2 commands, 23 agents, 7 hooks, 1 MCP server · 2,000 tokens together
97 genius reasoning patterns from history's greatest minds. One epistemic standard none of them can bypass.
Plugin CodexGemini CLI
UX/UI design and WCAG 2.2 AA accessibility audit: name the user/task/success-criterion first, enforce accessibility as a constraint, walk the 10 Nielsen heuristics, and refuse dark patterns.
Plugin CodexGemini CLI
Synthesize conflicting evidence into a sourced, qualified conclusion with explicit counter-evidence and uncertainty.
Plugin CodexGemini CLI
Goal-driven iteration for any host: compile a goal contract with executable acceptance checks, plan against it, verify with real commands, and refine the next iteration from the evidence.
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: