{"slug":"16minds","title":"16minds","description":"16-minds summons agents modeled on 16 distinct personality types — each with its own values, thinking patterns, and tone — to debate, review, or advise on any topic. Each personality is written directly into an independent prompt, so outputs carry visibly different voices instead of the averaged answer a single agent tends to produce.\n\nThree commands cover the range:\n  - /mind <type> — a single type's opinion\n  - /pair <a> <b> — a two-type debate (open → rebut → reply / synthesize)\n  - /minds — fan out to all 16 in parallel, then synthesize\n\nThree modes (light / middle / heavy) trade depth for token cost.\n\nThe /minds synthesis follows a fixed 4-section rubric — score distribution, axes of disagreement, easily-overlooked perspectives, and landing-zone candidates with per-candidate \"types likely to agree / fit / risk\" — to keep 16-voice output structured rather than scattershot. The --save flag writes the full execution log to a file for use as article material or decision logs.\n\nBuilt for decisions where a single averaged answer would lose the edges: idea generation, design judgment, code review, and life/career questions.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-04T12:03:33.240Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/yukurash/16minds-plugin.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"16minds","source":{"sha":"00f3bd5f0f6d9d34a6df91e061afa5846f8d4bc6","url":"https://github.com/yukurash/16minds-plugin.git","source":"url"},"homepage":"https://github.com/yukurash/16minds-plugin","description":"16-minds summons agents modeled on 16 distinct personality types — each with its own values, thinking patterns, and tone — to debate, review, or advise on any topic. Each personality is written directly into an independent prompt, so outputs carry visibly different voices instead of the averaged answer a single agent tends to produce.\n\nThree commands cover the range:\n  - /mind <type> — a single type's opinion\n  - /pair <a> <b> — a two-type debate (open → rebut → reply / synthesize)\n  - /minds — fan out to all 16 in parallel, then synthesize\n\nThree modes (light / middle / heavy) trade depth for token cost.\n\nThe /minds synthesis follows a fixed 4-section rubric — score distribution, axes of disagreement, easily-overlooked perspectives, and landing-zone candidates with per-candidate \"types likely to agree / fit / risk\" — to keep 16-voice output structured rather than scattershot. The --save flag writes the full execution log to a file for use as article material or decision logs.\n\nBuilt for decisions where a single averaged answer would lose the edges: idea generation, design judgment, code review, and life/career questions."}]}}