{"slug":"ice-framework","title":"ice-framework","description":"The ICE Plugin — an open-source Claude Code plugin packaging the ICE planning framework (Intent, Constraints, Expectations) as a distributable skill for the Claude Code marketplace.\n\nICE structures planning conversations between human and AI before implementation begins, surfacing requirements through structured dialogue, enforcing critical review, and producing a documented blueprint. It reduces agreement bias and vague-input failures.\n\nThe plugin packages the following skills:\n\n/ice — Full ICE planning session with blueprint output\n/q — Clarifying questions before starting work\n/challenge — Challenge assumptions from hostile positions\n/verify — Sceptical review of AI output before accepting","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-10T12:00:00.763Z","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/Topsy31/ICE.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"ice-framework","source":{"sha":"67ec6959892ac560aabda02d82b28a99345f2d6e","url":"https://github.com/Topsy31/ICE.git","source":"url"},"homepage":"https://interloquial.com","description":"The ICE Plugin — an open-source Claude Code plugin packaging the ICE planning framework (Intent, Constraints, Expectations) as a distributable skill for the Claude Code marketplace.\n\nICE structures planning conversations between human and AI before implementation begins, surfacing requirements through structured dialogue, enforcing critical review, and producing a documented blueprint. It reduces agreement bias and vague-input failures.\n\nThe plugin packages the following skills:\n\n/ice — Full ICE planning session with blueprint output\n/q — Clarifying questions before starting work\n/challenge — Challenge assumptions from hostile positions\n/verify — Sceptical review of AI output before accepting"}]}}