Release v1.7.7

🎯 Improved /implement Command Stability

What's New

Enhanced the /implement command with phase-based execution flow to improve stability and prevent system crashes during autonomous operations.

Key Improvements

Phase-Based Execution System

• Clear Work Phase Identification: Instructions are now categorized into specific phases (implementation, planning, design, requirements) for precise routing
• Structured Decision Flow: Deterministic patterns for identifying user intent and selecting appropriate sub-agents
• Explicit Execution Protocols: Clear boundaries between phases with mandatory clarification for ambiguous requests

Crash Prevention Measures

• Rule-Advisor Recursion Prevention: Mandatory constraints to prevent rule-advisor invocation loops in autonomous mode
• High-Risk Agent Protection: Special handling for task-executor and quality-fixer to avoid system crashes
• System Stability Constraints: All sub-agent prompts now include crash prevention directives

Technical Details

• Updated both Japanese (commands-ja/implement.md) and English (commands-en/implement.md) command definitions
• Optimized English translations for maximum AI execution accuracy
• Clear responsibility boundaries between orchestration and direct implementation

Impact

This update significantly improves the reliability of the /implement command, especially during long-running autonomous operations, while maintaining the powerful sub-agent orchestration capabilities.

Release v1.7.6

What's Changed

• Enhanced agent implementation consistency with Design Doc compliance
• Improved TypeScript test design standards and type safety
• Added implementation sample verification to document-reviewer
• Added rule metadata synchronization command for post-edit optimization
• Fixed metadata inconsistencies in typescript-testing rules

Improvements

• Stronger AI execution precision through systematic rule enforcement
• Reduced manual review requirements
• Better code quality and maintainability
• Automated rule metadata maintenance with /sync-rules command
• Enhanced rule-advisor selection accuracy (estimated 15% improvement)

Fixes

• Resolved missing sections in typescript-testing.md metadata
• Replaced unclear /rule-maintenance with focused /sync-rules command

Full Changelog: v1.7.5...v1.7.6

Release v1.7.5

🔧 Enhanced Unused Exports Detection

New Features

• Improved unused exports script: Added check-unused-exports.js with better classification between truly unused exports and internal-only exports
• Auto-removal capability: Enhanced quality-fixer agents to automatically remove unused exports when detected by ts-prune (YAGNI principle enforcement)

Script Updates

• npm run check:unused: Now uses the enhanced script for precise detection
• npm run check:unused:all: Fallback to original ts-prune output for reference

Benefits

• Prevents technical debt: Automatically removes "just in case" exports that violate YAGNI principles
• Better precision: Distinguishes between truly unused exports and those used only within their module
• AI-optimized: Designed for maximum execution accuracy with clear, actionable detection criteria

Technical Details

• New script filters ts-prune output to separate truly unused exports from internal-only usage
• Quality-fixer agents now include unused export removal in their automatic fix range
• Supports both English and Japanese agent definitions

Release v1.7.4

🐛 Bug Fixes

Ensure Subagent Independence from CLAUDE.md Principles

• Fixed: Subagents now operate independently without referencing parent CLAUDE.md configuration
• Impact: Prevents configuration conflicts and ensures proper agent autonomy
• Details: Added explicit independence declarations to all agent specifications to prevent inheritance of project-specific rules that could interfere with agent-specific operations

Restore Task Executor Checkbox Update Functionality

• Fixed: Task executor agent now correctly updates checkbox states in task files
• Impact: Improved task tracking accuracy and progress visibility
• Details: Enhanced AI instructions with precise pattern matching for checkbox updates, ensuring reliable task status synchronization

🔧 Improvements

Enhanced Agent Specifications

• Added independence declarations to 10 agent types (both English and Japanese versions)
• Improved precision in task executor's checkbox update logic
• Strengthened agent autonomy for better execution accuracy

📦 Dependencies

• Updated package version to reflect bug fixes

🎯 Affected Components

• .claude/agents-en/* - All English agent specifications
• .claude/agents-ja/* - All Japanese agent specifications
• Task executor agent - Checkbox update functionality
• Quality fixer agent - Section reference corrections

Release v1.7.3

Bug Fixes

• task-executor: Fixed checkbox update functionality that was broken in v1.7.0
• Restored concrete 3-step progress update instructions for AI agents
• Replaced abstract "progress update" with precise sequential actions (4-1, 4-2, 4-3)
• Added [MANDATORY] enforcement keywords to prevent instruction skipping

Technical Changes

• Enhanced both Japanese and English task-executor agent definitions
• Improved AI execution accuracy by providing actionable instructions instead of abstract concepts
• Ensured consistent checkbox updates across task execution workflows

Release v1.7.2

🎉 New Features

Project Context Injection Command

Added /project-inject slash command for streamlined project setup when using the boilerplate for production projects.

What's New

• Interactive Context Configuration: No more manual placeholder replacements
• Bilingual Support: Available in both Japanese (/project-inject) and English
• AI-Optimized Output: Generates context following AI execution accuracy maximization criteria

How It Works

# Start with the boilerplate
npx github:shinpr/ai-coding-project-boilerplate my-project

# Configure your project context interactively
/project-inject

# The command will guide you through:
# - Problem your project solves
# - Target users and usage scenarios
# - Business constraints
# - Development structure

📝 Documentation Updates

README Improvements

• Added /project-inject to slash commands reference
• Updated project configuration workflow to use the new command
• Clarified initial setup process for production projects
• Updated FAQ section with new customization method

Workflow Enhancement

Before: Manual editing of placeholder text in project-context.md
After: Interactive command that ensures proper context structure

🔧 Technical Details

Command Structure

• Follows single responsibility principle for project-context.md
• Clear separation between project context and technical choices
• Structured output format optimized for AI comprehension

AI Execution Accuracy Criteria

The command generates context following these principles:

• Minimal yet efficient: Essential information only
• AI-decidable: Measurable and verifiable criteria
• Unambiguous: Specific numbers, conditions, and examples
• Positive framing: "Do this" rather than "Don't do that"

💡 Why This Matters

When using a boilerplate for real projects, the first critical step is adapting it to your specific needs. The /project-inject command transforms this from a manual, error-prone process into a guided, interactive experience that ensures:

1. Consistency: All projects follow the same context structure
2. Completeness: No critical information is missed
3. Clarity: AI assistants understand your project's essence
4. Efficiency: Get started faster with less configuration overhead

---

Full Changelog: v1.7.1...v1.7.2

Release v1.7.1

🐛 Bug Fixes

Fixed Section References in Agent Definitions

• Japanese version (.claude/agents-ja/quality-fixer.md):
  • Fixed incorrect section reference from "品質チェックフェーズ" to "品質チェックコマンドリファレンス"
• English version (.claude/agents-en/quality-fixer.md):
  • Fixed incorrect section reference from "Quality Check Commands" to "Quality Check Command Reference"

📝 Details

The quality-fixer agent definitions in both language versions were referencing a non-existent section name in the ai-development-guide.md file. This fix ensures that the agent definitions correctly point to the actual "Quality Check Command Reference" section, improving documentation accuracy and preventing confusion when agents reference rule files.

🔍 What Changed

• .claude/agents-ja/quality-fixer.md: Line 48 updated
• .claude/agents-en/quality-fixer.md: Line 30 updated
• package.json: Version bumped to 1.7.1
• package-lock.json: Version bumped to 1.7.1

📌 Note

This is a documentation fix that improves the accuracy of internal agent references. No functional changes to the code or behavior.

---

Full Changelog: v1.7.0...v1.7.1

Release v1.7.0

🚀 Enhanced AI Agent Specifications and Documentation

This release significantly improves AI execution accuracy through comprehensive enhancements to agent specifications, documentation templates, and development workflows.

✨ New Features

E2E Test Generator Agent

• Introduced e2e-test-generator agent for automated integration test skeleton creation
• Generates comprehensive test structures based on Design Documents
• Supports both API and UI testing patterns
• Automatically creates test fixtures and helper functions

🔧 Improvements

Enhanced Agent Specifications

Quality Fixer Agent

• Strengthened validation workflows with comprehensive error handling patterns
• Added structured approach for TypeScript project quality assurance
• Improved autonomous error resolution with zero-tolerance for quality issues
• Enhanced pre-commit hook handling and retry mechanisms

Task Executor Agent

• Added structured task decomposition with granular progress tracking
• Implemented real-time status updates and completion verification
• Enhanced error recovery patterns with automatic retry logic
• Improved task prioritization based on dependencies

Technical Designer Agent

• Clarified ADR (Architecture Decision Record) decision-making process
• Enhanced Design Document structure with acceptance criteria
• Improved technical trade-off analysis and documentation
• Added integration point specifications

Work Planner Agent

• Integrated Design Document alignment for cohesive planning
• Enhanced phase-based implementation approach
• Added E2E verification procedures for each phase
• Improved risk assessment and mitigation strategies

Documentation Templates

Design Document Template

• Added structured E2E verification procedures
• Enhanced integration point specifications
• Improved acceptance criteria definitions
• Clarified technical dependency mappings

Work Plan Template

• Added phase-specific E2E verification steps
• Integrated Design Document cross-references
• Enhanced completion criteria with quality gates
• Improved progress tracking mechanisms

📚 Documentation Updates

• Refined sub-agent documentation with clearer usage patterns
• Enhanced capability descriptions and limitations
• Improved examples for agent collaboration patterns
• Added troubleshooting guides for common scenarios

🎯 Key Benefits

1. Improved AI Execution Accuracy: Better structured guidance leads to more precise task execution
2. Enhanced Error Prevention: Comprehensive validation patterns reduce runtime failures
3. Clearer Completion Criteria: Well-defined success metrics ensure quality deliverables
4. Better Task Management: Structured decomposition enables efficient parallel execution
5. Stronger Quality Assurance: Multi-layered validation ensures production-ready code

Release v1.6.7

🎯 Highlights

This release significantly improves AI execution accuracy by clarifying the existing code investigation process and preventing duplicate implementations.

✨ What's New

Enhanced Code Investigation Process

• Pattern 5 Added: New anti-pattern "Insufficient Existing Code Investigation" to prevent duplicate implementations
• Pre-implementation Checks: All AI agents now enforce thorough existing code investigation before implementation
• Better Decision Recording: Design Docs now require explicit documentation of similar functionality searches and decisions

📝 Changes

Documentation Improvements

• Added Pattern 5 to AI Development Guide for preventing architectural inconsistencies
• Enhanced technical-designer agent with similar functionality search workflow
• Updated task-executor with pre-implementation verification steps
• Strengthened code-reviewer validation checklist
• Improved work-planner with code investigation references

Technical Enhancements

• Added code-reading and best-practices tags to rules index
• Synchronized all improvements between Japanese and English documentation
• Clarified "Existing Codebase Analysis" section requirements in Design Docs

🔧 Developer Impact

This update ensures:

• Reduced Duplicate Code: AI agents will detect and reuse existing implementations
• Better Architecture Consistency: Similar functionality is handled uniformly across the codebase
• Clearer Decision Trail: All implementation decisions are documented with rationale
• Improved Code Quality: Pre-implementation checks prevent architectural drift

📚 Documentation

The following key processes have been clarified:

1. Search for similar functionality before implementation
2. Decision workflow: Use existing / Improve with ADR / Create new
3. Record all decisions in Design Doc's "Existing Codebase Analysis" section

---

Full Changelog: v1.6.6...v1.6.7

Release v1.6.6

🎯 Overview

This patch release clarifies the orchestrator's commit execution responsibility in the sub-agents documentation, ensuring more explicit and reliable operation instructions for AI agents.

✨ What's Changed

Documentation Improvements

• Clarified Orchestrator Commit Responsibilities - The sub-agents guide now explicitly states that the orchestrator (Claude/Me) is responsible for executing git commits during autonomous execution mode
  • Updated both Japanese and English documentation for consistency
  • Added explicit mention of using the Bash tool for commit execution
  • Improved clarity in the quality assurance workflow

Key Enhancements

• 🎭 Explicit Execution Entity: Changed from generic "Create commit" to "Me: Execute git commit" in workflow diagrams
• ✅ Clear Approval Flow: Emphasized immediate git commit execution after quality-fixer's approved: true confirmation
• 📝 Optimized Descriptions: Removed redundant text to ensure reliable operation regardless of context capacity
• 🌐 Bilingual Consistency: Maintained perfect parity between Japanese and English documentation

📊 Impact

These changes ensure:

• More reliable autonomous execution cycles
• Clearer understanding of responsibility boundaries between agents
• Reduced ambiguity in commit execution workflows
• Better AI agent comprehension of orchestration tasks

🔧 Technical Details

Files Modified

• docs/guides/ja/sub-agents.md - Japanese version updates
• docs/guides/en/sub-agents.md - English version updates
• package.json - Version bump to 1.6.6
• package-lock.json - Version sync