Release: v0.12.1

Agent Definitions

• "Prohibited Actions" → "Output Self-Check": 8 agents now use actionable self-check checklists instead of prohibition lists (code-verifier, investigator, scope-discoverer, solver, task-decomposer, task-executor-frontend, verifier, design-sync)
• Consolidated redundant sections: Merged duplicated responsibility descriptions in quality-fixer, quality-fixer-frontend, task-decomposer, task-executor-frontend, work-planner
• requirement-analyzer: Added affectedLayers output field for explicit layer routing in fullstack workflows

Fullstack Flow Fixes

• Added missing [Stop] marker to Large Scale Fullstack Step 1 (consistency with SKILL.md and Medium Scale)
• Added Medium Scale Fullstack flow table to monorepo-flow.md
• Split Layer Context templates by scale — Large Scale references PRD, Medium Scale references requirement-analyzer output
• Fixed section numbering gap in fullstack-implement.md

Skills

• Removed redundant "Continuous Improvement Mindset" sections from ai-development-guide, frontend-ai-guide, coding-principles, testing-principles
• Consolidated duplicated content in coding-principles and testing-principles

Skills Index

• Synchronized skills-index.yaml with actual SKILL.md headings: +54 missing sections, 8 name fixes, 1 phantom entry removed

Commands

• Improved CRITICAL warnings to explain rationale across design, plan, update-doc commands
• Clarified scope boundaries and completion behavior

No breaking changes.

Release: v0.12.0

Breaking Changes

• Removed /front-reverse-design command — absorbed into /reverse-engineer with fullstack option

New Features

• Fullstack reverse engineering — /reverse-engineer now supports a fullstack option that generates both backend and frontend Design Docs per feature unit
• Unified scope discovery — scope-discoverer performs a single-pass discovery combining user-value and technical perspectives, replacing the previous dual-mode (prd / design-doc) approach

Improvements

• Phase 2 (Design Doc generation) reuses Phase 1 scope results instead of re-running discovery, enforcing vertical integration between PRD and Design Doc units
• Discovery output now includes technicalProfile (primary modules, public interfaces, data flow, infrastructure dependencies)
• Added Granularity Criteria based on Vertical Slice principle for better unit boundary decisions

Release: v0.11.0

New Commands

• /fullstack-implement — End-to-end orchestration across backend and frontend layers. Creates separate Design Docs per layer, verifies cross-layer consistency via design-sync, and executes with layer-aware agent routing.
• /fullstack-build — Autonomous task execution with layer-aware routing. Routes *-backend-task-* files to backend agents and *-frontend-task-* files to frontend agents automatically.

Both commands require both plugins (dev-workflows + dev-workflows-frontend) installed.

How It Works

1. A single PRD covers the entire feature
2. Separate Design Docs are created for backend and frontend
3. design-sync verifies cross-layer consistency (API contracts, shared types)
4. Work plan composes vertical feature slices — each phase contains both backend and frontend tasks
5. Tasks are routed to the appropriate executor by filename pattern matching

Other Changes

• work-planner and plan template now accept multiple Design Docs
• task-decomposer supports layer-aware task file naming
• subagents-orchestration-guide references the new monorepo flow

No breaking changes to existing commands (/implement, /build, /front-build, etc.).

Release: v0.10.9

Add Bash Tool to 11 Agents

Added Bash to the tools frontmatter of 11 agents that were missing shell command access.

Agents with explicit needs

• investigator — date, git diff for change failure analysis
• verifier — date for information recency evaluation
• requirement-analyzer — date for current date retrieval
• prd-creator — date for current date retrieval
• technical-designer — date, date +%Y for year-aware searches
• document-reviewer — date +%Y for latest information verification

Agents that benefit during work process

• code-reviewer — Run tests/lints to verify quality
• code-verifier — Run tests to validate doc-code consistency
• integration-test-reviewer — Run tests to confirm pass/fail
• scope-discoverer — git log, package manager commands for dependency analysis
• technical-designer-frontend — date +%Y for year-aware searches, package checks

Release: v0.10.8

Design Document Quality Improvements

Added six enhancements to strengthen design document rigor across the creation and review workflow.

New Required Sections in Design Template

• Applicable Standards — Classify project standards as explicit (documented) or implicit (observed), requiring confirmation for implicit ones
• Code Inspection Evidence — Record all inspected files/functions with their relevance during investigation
• Data Representation Decision — Evaluate reuse-vs-new using semantic fit, responsibility fit, lifecycle fit, and boundary cost criteria
• Field Propagation Map — Track field status (preserved / transformed / dropped) at each component boundary

Technical Designer Updates

• Standards Identification Gate — Must identify and classify project standards before any investigation begins
• New checklist items enforce recording of all new required sections

Document Reviewer Updates

• Gate-based review structure — Step 3 now uses Gate 0 (structural existence) before Gate 1 (quality assessment); Gate 0 failure blocks quality review
• Rationale verification — Design decisions must reference identified standards or existing patterns
• Code inspection evidence review — Verify inspected files are relevant and flag missing key files
• Updated review criteria: Gate 0 pass is required for both "Approved" and "Approved with Conditions"

Release: v0.10.7

What's New

New Command: /update-doc

Added a new command to update existing design documents (Design Doc / PRD / ADR) with a proper review workflow.

Features:

• Identifies and selects target documents from docs/design/, docs/prd/, or docs/adr/
• Clarifies changes with user before updating
• Updates via technical-designer or prd-creator in update mode
• Validates through document-reviewer and design-sync
• Includes ADR update guidance (minor vs major changes)

Available in both plugins:

• dev-workflows (backend)
• dev-workflows-frontend (frontend)

Release: v0.10.6

New

• Add metronome as an external plugin to the marketplace
  • During repetitive tasks, Claude may switch to bulk bash operations under the guise of "working efficiently," potentially breaking files. Metronome detects that behavior and intercepts execution, nudging Claude to slow down and proceed step by step.
  • Install: /plugin install metronome@claude-code-workflows

Changed

• Update marketplace description to reflect broader scope (plugins, tools, and safety guardrails)
• Update README with External Plugins section

Release: v0.10.5

Highlights

This release improves command execution reliability by ensuring all steps are properly tracked in TodoWrite and delegated to subagents.

Changes

Command Structure Improvements

• First Action directive: Added First Action: Register Steps 0-N to TodoWrite before any execution to orchestrator commands
• Step 0 inclusion: Step 0 (skill execution) is now part of the main flow and tracked in TodoWrite
• Unified step notation: Standardized all commands to use ### Step N: format
• Explicit fix steps: Added dedicated steps for applying review fixes (ensures delegation to task-executor)

Removed Deprecated Patterns

• Removed Think harder/deeply expressions
• Removed @agent-name notation (replaced with Task tool invocation format)
• Removed indirect skill references (see documentation-criteria skill)

review.md Simplification

• Removed redundant rule-advisor step (code-reviewer already identifies fixes)
• Simplified conditional flow with single skip condition at Step 4
• Reduced steps from 10 to 9

add-integration-tests.md Enhancements

• Added Core Identity and Why Delegate sections
• Added Step 6: Apply Review Fixes for explicit fix delegation
• Embedded task file template directly in command

Fixed Issues

• Step 0 being skipped because it was outside TodoWrite registration scope
• Orchestrator performing direct edits instead of delegating to task-executor
• Subagent invocation format inconsistencies across commands

Release: v0.10.4

Improvements

• add-integration-tests command: Improved command format with explicit Task tool invocation blocks
  • Added **Role**: Orchestrator declaration
  • Added **Task tool invocation**: blocks with subagent_type and prompt for each sub-agent call
  • Added **Expected output**: for each step
  • Added **Flow control**: for review step branching
  • Aligned format with diagnose and reverse-engineer commands

Release: v0.10.3

Orchestration Workflow Improvements

Step Count Verification

Added explicit step counts to workflow flow headings (Large: 11 steps, Medium: 7 steps, Small: 2 steps). This enables orchestrators to self-verify that all required steps are executed without skipping.

Structured JSON Output for requirement-analyzer

Converted requirement-analyzer output to mandatory JSON format with:

• scopeDependencies: Questions that may change scale determination based on user answers
• adrRequired / adrReason: ADR necessity with explicit reasoning
• Removed redundant fields (PRD/Design Doc requirements are derivable from scale)

Improved Scale Determination

Added Grep tool to requirement-analyzer for more accurate file count estimation during scale assessment.

Explicit Stop Point Behavior

Added explicit requirement to use AskUserQuestion at all Stop points, ensuring proper user interaction during workflow execution.

Streamlined Response Specification

Updated Structured Response Specification to include only decision-relevant fields for each subagent, reducing context overhead.

Purpose-Driven First Action Rule

Clarified First Action Rule with purpose-driven description: pass requirements directly to requirement-analyzer for accurate analysis before workflow determination.