Breaking Changes

• Commands slimmed to thin orchestrators — procedural logic extracted into 13 references/ files (~60-88% line reduction per command)
• Sequential Review Pattern removed — Layer 5 (Artifact Review) is now the single reviewer invocation per task
• State updates require explicit jq merge — phase commands no longer use ambiguous JSON literals that could overwrite existing state fields

Highlights

• Reference extraction — 8 bloated command files decomposed into reusable references/ docs (coordinator-pattern, verification-layers, failure-recovery, quick-mode, etc.)
• 3 subagent dispatch templates — standardized prompts for executor, reviewer, and research agents
• Recovery mode fix — fix-task completions bypass verification layers; Layer 3 checkmark count adjusted for recovery mode
• Agent colors diversified — each role now has a distinct color (no more 5 agents sharing cyan)
• Internal skills hidden — 4 background skills (delegation-principle, reality-verification, interview-framework, communication-style) set to user-invocable: false
• Consistent paths — all references use ${CLAUDE_PLUGIN_ROOT} and $SPEC_PATH variable
• Explicit teammate names — spawn steps now set canonical names matching shutdown recipients
• ralph_find_spec() used in quick mode intent classification (supports non-default specs dirs)
• research-prompt.md — added {BASE_PATH} and {TOPIC_SLUG} placeholders

Stats

• 53 files changed, 5,022 additions, 6,190 deletions (net -1,168 lines)
• ralph-specum 3.10.0 → 4.0.0
• ralph-speckit 0.5.0 → 0.5.1

What's New

v3.0.0+ - Self-contained Execution Loop

Smart Ralph is now fully self-contained with no external plugin dependencies.

Key Changes:

• 🎉 No more ralph-loop dependency - The execution loop is handled by the built-in stop-hook
• 📦 Simpler installation - Just one plugin to install
• 🔧 No version compatibility issues between plugins

Migration from v2.x

1. Update Smart Ralph to v3.0.0+
2. Restart Claude Code
3. Existing specs continue working - no changes needed
4. Optionally uninstall ralph-loop if you don't use it elsewhere

Installation

/plugin marketplace add tzachbon/smart-ralph
/plugin install ralph-specum@smart-ralph

Full changelog: v2.12.0...v3.1.1

Breaking Changes

Ralph Wiggum plugin now required for task execution.

Starting with v2.0.0, Smart Ralph delegates the execution loop to the official Ralph Wiggum plugin instead of using a custom stop-handler.

Before upgrading

Install the Ralph Wiggum dependency:

/plugin install ralph-wiggum@claude-plugins-official

Then restart Claude Code.

Migration Guide

See MIGRATION.md for detailed upgrade instructions.

What Changed

Highlights

• Deleted custom stop-handler.sh (274 lines)
• implement.md rewritten as thin wrapper invoking /ralph-loop
• Added stop-watcher.sh for logging/status (read-only, no loop control)
• cancel.md now calls /cancel-ralph for dual cleanup
• All existing spec files remain compatible (no changes needed)

Why This Change

• Less code to maintain
• Official plugin gets updates and bug fixes from Anthropic
• Better reliability for the execution loop
• Cleaner separation of concerns

Full Changelog

v1.7.0...v2.0.0