Adam Slaker
dc29794efa
* chore: update .gitignore to include auto-generated files and security logs - Added entries for .security-key and logs/security/ to ignore auto-generated files and security logs. * fix(ACS-51): prevent task workflow from halting after planning stage Root cause: Frontend accepted incomplete plan data (empty phases array) during spec creation, which overwrote subtask state and left tasks stuck. Changes: - Add validatePlanData() to reject incomplete plans in task-store - Add reloadPlanForIncompleteTask() hook for resume functionality - Enhance logging in project-store for plan loading diagnostics - Add comprehensive unit tests for plan validation edge cases - Add integration tests for task lifecycle IPC events - Add E2E test specs for full task workflow The fix ensures incomplete plans are rejected while the backend's validation/auto-fix pipeline completes, preserving UI state until valid data arrives. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(ACS-55, ACS-71): ensure Kanban state transitions render correctly ACS-55: Task card was showing "planning" even after moving to "coding" phase - Phase transitions now bypass the 16ms batching window and apply immediately - Added debug logging when sequence number checks drop out-of-order updates - This ensures intermediate phases (planning→coding→qa) are never coalesced ACS-71: Task immediately moved to Human Review with zero subtasks - Exit handler now checks if subtasks exist before moving to human_review - Added validateStatusTransition() function to prevent invalid state changes - Blocks human_review when no subtasks exist (task still in planning) - Blocks phase regression from coding back to planning Changes: - agent-events-handlers.ts: Added validation function, fixed exit handler - useIpc.ts: Phase changes bypass batching, apply immediately - task-store.ts: Added logging for dropped out-of-order updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: prevent status flip-flop between Human Review and AI Review When a task completed, `updateTaskFromPlan` would override the correct 'human_review' status with 'ai_review' when all subtasks were complete, causing tasks to flip between statuses on refresh. Root cause: The function only checked for "active" phases (planning, coding, qa_review, qa_fixing). When phase was 'complete' or 'idle', it would recalculate status from subtasks and set 'ai_review'. Fix: - Add 'complete' and 'failed' as terminal phases that skip recalculation - Respect explicit 'human_review' status from plan file - Never downgrade from 'human_review' to 'ai_review' This completes the Kanban state management fixes for ACS-51, ACS-55, ACS-71. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: add missing SubtaskStatus import to task-store The SubtaskStatus type was used but not imported, causing TypeScript compilation to fail in CI. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: use secure temp directories in tests to fix CodeQL alerts Replace hardcoded /tmp/ paths with mkdtempSync for secure temp directory creation. This prevents TOCTOU (time-of-check-time-of-use) attacks by using randomly generated directory names. Files fixed: - e2e/task-workflow.spec.ts - __tests__/integration/task-lifecycle.test.ts Resolves CodeQL "Insecure temporary file" high severity alerts. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: address PR review findings for Kanban state management - Fix reloadPlanForIncompleteTask to update Zustand store after reload - Extend flip-flop prevention to include pr_created and done statuses - Use wouldPhaseRegress() utility instead of hardcoded phase checks - Gate debug logging with debugLog utility for production - Fix unsafe type assertion for plan status - Remove redundant gitignore entry (logs/security/) - Add test coverage for terminal phase and status preservation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: address follow-up PR review suggestions (5 LOW severity) - Add ExecutionPhase type cast after type guard check - Use crypto.randomUUID() for stronger subtask ID generation - Add optional chaining for defensive coding in useTaskDetail - Clarify comment about phase bypass batching behavior - Fix misleading test comment about human_review preservation - Update test regex to accept both UUID and fallback ID formats 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: address final 3 LOW severity suggestions from CodeRabbit - Remove unused electronAPI variable in task-lifecycle test - Add comment explaining defensive fallback for description field - Rename test to clarify status recalculation skip behavior 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Auto Claude
Autonomous multi-agent coding framework that plans, builds, and validates software for you.
Download
Stable Release
| Platform | Download |
|---|---|
| Windows | Auto-Claude-2.7.2-win32-x64.exe |
| macOS (Apple Silicon) | Auto-Claude-2.7.2-darwin-arm64.dmg |
| macOS (Intel) | Auto-Claude-2.7.2-darwin-x64.dmg |
| Linux | Auto-Claude-2.7.2-linux-x86_64.AppImage |
| Linux (Debian) | Auto-Claude-2.7.2-linux-amd64.deb |
Beta Release
⚠️ Beta releases may contain bugs and breaking changes. View all releases
| Platform | Download |
|---|---|
| Windows | Auto-Claude-2.7.2-beta.10-win32-x64.exe |
| macOS (Apple Silicon) | Auto-Claude-2.7.2-beta.10-darwin-arm64.dmg |
| macOS (Intel) | Auto-Claude-2.7.2-beta.10-darwin-x64.dmg |
| Linux | Auto-Claude-2.7.2-beta.10-linux-x86_64.AppImage |
| Linux (Debian) | Auto-Claude-2.7.2-beta.10-linux-amd64.deb |
| Linux (Flatpak) | Auto-Claude-2.7.2-beta.10-linux-x86_64.flatpak |
All releases include SHA256 checksums and VirusTotal scan results for security verification.
Requirements
- Claude Pro/Max subscription - Get one here
- Claude Code CLI -
npm install -g @anthropic-ai/claude-code - Git repository - Your project must be initialized as a git repo
Quick Start
- Download and install the app for your platform
- Open your project - Select a git repository folder
- Connect Claude - The app will guide you through OAuth setup
- Create a task - Describe what you want to build
- Watch it work - Agents plan, code, and validate autonomously
Features
| Feature | Description |
|---|---|
| Autonomous Tasks | Describe your goal; agents handle planning, implementation, and validation |
| Parallel Execution | Run multiple builds simultaneously with up to 12 agent terminals |
| Isolated Workspaces | All changes happen in git worktrees - your main branch stays safe |
| Self-Validating QA | Built-in quality assurance loop catches issues before you review |
| AI-Powered Merge | Automatic conflict resolution when integrating back to main |
| Memory Layer | Agents retain insights across sessions for smarter builds |
| GitHub/GitLab Integration | Import issues, investigate with AI, create merge requests |
| Linear Integration | Sync tasks with Linear for team progress tracking |
| Cross-Platform | Native desktop apps for Windows, macOS, and Linux |
| Auto-Updates | App updates automatically when new versions are released |
Interface
Kanban Board
Visual task management from planning through completion. Create tasks and monitor agent progress in real-time.
Agent Terminals
AI-powered terminals with one-click task context injection. Spawn multiple agents for parallel work.
Roadmap
AI-assisted feature planning with competitor analysis and audience targeting.
Additional Features
- Insights - Chat interface for exploring your codebase
- Ideation - Discover improvements, performance issues, and vulnerabilities
- Changelog - Generate release notes from completed tasks
Project Structure
Auto-Claude/
├── apps/
│ ├── backend/ # Python agents, specs, QA pipeline
│ └── frontend/ # Electron desktop application
├── guides/ # Additional documentation
├── tests/ # Test suite
└── scripts/ # Build utilities
CLI Usage
For headless operation, CI/CD integration, or terminal-only workflows:
cd apps/backend
# Create a spec interactively
python spec_runner.py --interactive
# Run autonomous build
python run.py --spec 001
# Review and merge
python run.py --spec 001 --review
python run.py --spec 001 --merge
See guides/CLI-USAGE.md for complete CLI documentation.
Development
Want to build from source or contribute? See CONTRIBUTING.md for complete development setup instructions.
For Linux-specific builds (Flatpak, AppImage), see guides/linux.md.
Security
Auto Claude uses a three-layer security model:
- OS Sandbox - Bash commands run in isolation
- Filesystem Restrictions - Operations limited to project directory
- Dynamic Command Allowlist - Only approved commands based on detected project stack
All releases are:
- Scanned with VirusTotal before publishing
- Include SHA256 checksums for verification
- Code-signed where applicable (macOS)
Available Scripts
| Command | Description |
|---|---|
npm run install:all |
Install backend and frontend dependencies |
npm start |
Build and run the desktop app |
npm run dev |
Run in development mode with hot reload |
npm run package |
Package for current platform |
npm run package:mac |
Package for macOS |
npm run package:win |
Package for Windows |
npm run package:linux |
Package for Linux |
npm run package:flatpak |
Package as Flatpak (see guides/linux.md) |
npm run lint |
Run linter |
npm test |
Run frontend tests |
npm run test:backend |
Run backend tests |
Contributing
We welcome contributions! Please read CONTRIBUTING.md for:
- Development setup instructions
- Code style guidelines
- Testing requirements
- Pull request process
Community
- Discord - Join our community
- Issues - Report bugs or request features
- Discussions - Ask questions
License
AGPL-3.0 - GNU Affero General Public License v3.0
Auto Claude is free to use. If you modify and distribute it, or run it as a service, your code must also be open source under AGPL-3.0.
Commercial licensing available for closed-source use cases.
