- Updated AGENTS.md to include CLI tools usage and configuration details.
- Introduced a new script template for both Bash and Python, outlining usage context, calling conventions, and implementation guidelines.
- Provided examples for common patterns in both Bash and Python scripts.
- Established a directory convention for script organization and naming.
- Add multi-perspective brainstorming workflow
- Support creative, pragmatic, and systematic analysis
- Include diverge-converge cycles with user interaction
- Add deep dive, devil's advocate, and idea merging
- Document thought evolution in brainstorm.md
- Introduced `analyze-with-file` command for collaborative analysis.
- Implemented session management for new and continued analysis sessions.
- Developed structured phases for topic understanding, exploration, discussion, and conclusion synthesis.
- Created detailed documentation for the workflow, including examples and implementation details.
- Added Codex prompt for deep analysis and exploration of codebase and concepts.
According to OpenAI Codex skill specification, SKILL.md files must have both
'name' and 'description' fields in YAML frontmatter. Added missing 'name' field
to all three skills:
- CCW Loop
- CCW Loop-B
- Parallel Dev Cycle
Also enhanced ccw-loop description with Chinese trigger keywords for better
multi-language support.
- Introduced a new specification for agent communication optimization focusing on file references instead of content transfer to enhance efficiency and reduce message size.
- Established a coordination protocol detailing communication channels, message formats, and dependency resolution strategies among agents (RA, EP, CD, VAS).
- Created a unified progress format specification for all agents, standardizing documentation structure and versioning practices.
Changed loadClaudeCliTools() to only load tools explicitly defined
in user config. Previously, DEFAULT_TOOLS_CONFIG.tools was spread
before user tools, causing all default tools to be loaded even if
not present in user config.
User config now has complete control over which tools are loaded.
- Introduced the `/workflow:clean` command for intelligent code cleanup.
- Implemented mainline detection to identify active development branches and core modules.
- Added drift analysis to discover stale sessions, abandoned documents, and dead code.
- Included safe execution features with staged deletion and confirmation.
- Documented usage, execution process, and implementation details in `clean.md`.
- Implemented issue discovery prompt to analyze code from various perspectives (bug, UX, test, quality, security, performance, maintainability, best-practices).
- Created structured issue generation prompt from GitHub URLs or text descriptions, including clarity detection and optional clarification questions.
- Introduced CCW Loop-B hybrid orchestrator pattern for iterative development, featuring a coordinator and specialized workers with batch wait support.
- Defined state management, session structure, and output schemas for the CCW Loop-B workflow.
- Added error handling and best practices documentation for the new features.
- Implemented the VALIDATE action to run tests, check coverage, and generate reports.
- Created orchestrator for managing CCW Loop execution using Codex subagent pattern.
- Defined state schema for unified loop state management.
- Updated action catalog with new actions and their specifications.
- Enhanced CLI and issue routes to support new features and data structures.
- Improved documentation for Codex subagent design principles and action flow.
- Introduced Lite-Plan-B for hybrid mode planning with multi-agent parallel exploration and primary agent merge/clarify/plan capabilities.
- Added Lite-Plan-C for Codex subagent orchestration, featuring intelligent task analysis, parallel exploration, and adaptive planning based on task complexity.
- Both workflows include detailed execution processes, session setup, and structured output formats for exploration and planning results.
- Introduced a new agent: universal-executor, designed for versatile task execution across various domains with a systematic approach.
- Added comprehensive documentation for Codex subagents, detailing core architecture, API usage, lifecycle management, and output templates.
- Created a new markdown file for Codex subagent usage guidelines, emphasizing parallel processing and structured deliverables.
- Updated codex_prompt.md to clarify the deprecation of custom prompts in favor of skills for reusable instructions.
- ccw issue commands must run from main repo (not worktree)
- Add worktree execution pattern: fetch solution -> cd worktree -> implement -> cd main -> done
- Replace TodoWrite with update_plan for Codex compatibility
- Add rule 10: worktree ccw commands from main repo
- Use absolute paths via git rev-parse --show-toplevel
- Add cleanup traps for graceful failure handling (EXIT/INT/TERM)
- Add git worktree prune at startup for stale worktrees
- Validate main repo state before merge (fallback to PR if dirty)
- Change default to "Create PR" for parallel execution safety
- Move worktree directory to .ccw/worktrees/ (gitignored)
- Consolidate Agent and CLI prompt builders into single buildExecutionPrompt()
- Replace file-based task format with scope + modification_points structure
- Simplify to 4-part task template: Modification Points → How → Reference → Done
- Remove duplicate formatTaskForCLI and buildCLIPrompt functions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- issue-plan-agent.md: Use `ccw issue solution` instead of Bash echo
- issue-plan.md (codex): Use `ccw issue solution` endpoint
- issue-queue.md (codex): Remove assigned_executor from schema
All solution creation now uses the dedicated CLI endpoint for:
- Auto-increment ID: SOL-{issue-id}-{seq}
- Proper JSONL format with trailing newline
- Multi-solution support per issue
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update solution-schema.json pattern to support new format
- Add Solution ID Format specification to plan.md
- Fix JSON parsing with extractJsonFromMarkdown + try-catch
- Update all examples in agent and prompt files:
- issue-plan-agent.md
- issue-queue-agent.md
- issue-execute.md
- issue-queue.md
- queue.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Changed queue structure from 'queue' to 'tasks' in various files for clarity.
- Updated CLI commands to reflect new task ID usage instead of queue ID.
- Enhanced queue management with new delete functionality for historical queues.
- Improved metadata handling and task execution tracking.
- Updated dashboard and issue manager views to accommodate new task structure.
- Bumped version to 6.3.8 in package.json and package-lock.json.
- Added JSON-based settings management in Config class for embedding and LLM configurations.
- Introduced methods to save and load settings from a JSON file.
- Updated BaseEmbedder and its subclasses to include max_tokens property for better token management.
- Enhanced chunking strategy to support recursive splitting of large symbols with improved overlap handling.
- Implemented comprehensive tests for recursive splitting and chunking behavior.
- Added CLI tools configuration management for better integration with external tools.
- Introduced a new command for compacting session memory into structured text for recovery.
- Updated embedding_manager.py to include backend parameter in model configuration.
- Modified model_manager.py to utilize cache_name for ONNX models.
- Refactored hybrid_search.py to improve embedder initialization based on backend type.
- Added backend column to vector_store.py for better model configuration management.
- Implemented migration for existing database to include backend information.
- Enhanced API settings implementation with comprehensive provider and endpoint management.
- Introduced LiteLLM integration guide detailing configuration and usage.
- Added examples for LiteLLM usage in TypeScript.
- Introduced `execute.md` for sequential task execution from session folder with detailed execution rules, task tracking, and error handling.
- Added `lite-execute.md` for lightweight task execution from a JSON plan file, emphasizing serial execution and dependency management.
