{"id":41274771,"url":"https://github.com/madebyaris/spec-kit-command-cursor","last_synced_at":"2026-01-23T02:30:44.895Z","repository":{"id":315537346,"uuid":"1059905582","full_name":"madebyaris/spec-kit-command-cursor","owner":"madebyaris","description":"SDD toolkit for Cursor IDE — /specify, /plan, /tasks to turn ideas into specs, plans, and actionable tasks.","archived":false,"fork":false,"pushed_at":"2025-12-25T18:53:51.000Z","size":369,"stargazers_count":111,"open_issues_count":5,"forks_count":13,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-12-27T05:48:15.458Z","etag":null,"topics":["ai-workflow","cursor","cursor-commands","developer-tools","documentation","github-spec-kit","planning","project-management","sdd","spec-driven-development","specifications","tasks","templates"],"latest_commit_sha":null,"homepage":"https://github.com/madebyaris/spec-kit-command-cursor","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/madebyaris.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-19T05:47:57.000Z","updated_at":"2025-12-26T02:04:44.000Z","dependencies_parsed_at":"2025-09-19T07:41:52.588Z","dependency_job_id":"6fa6672f-0276-4086-a459-d9144d7fbf7d","html_url":"https://github.com/madebyaris/spec-kit-command-cursor","commit_stats":null,"previous_names":["madebyaris/spec-kit-command-cursor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/madebyaris/spec-kit-command-cursor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madebyaris%2Fspec-kit-command-cursor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madebyaris%2Fspec-kit-command-cursor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madebyaris%2Fspec-kit-command-cursor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madebyaris%2Fspec-kit-command-cursor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/madebyaris","download_url":"https://codeload.github.com/madebyaris/spec-kit-command-cursor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madebyaris%2Fspec-kit-command-cursor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28678484,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-23T01:00:35.747Z","status":"online","status_checked_at":"2026-01-23T02:00:08.296Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-workflow","cursor","cursor-commands","developer-tools","documentation","github-spec-kit","planning","project-management","sdd","spec-driven-development","specifications","tasks","templates"],"created_at":"2026-01-23T02:30:44.816Z","updated_at":"2026-01-23T02:30:44.879Z","avatar_url":"https://github.com/madebyaris.png","language":"JavaScript","readme":"# 🚀 SDD Cursor Commands v3.0\n\n\u003cdiv align=\"center\"\u003e\n\n[![GitHub stars](https://img.shields.io/github/stars/madebyaris/spec-kit-command-cursor?style=social)](https://github.com/madebyaris/spec-kit-command-cursor/stargazers)\n[![GitHub forks](https://img.shields.io/github/forks/madebyaris/spec-kit-command-cursor?style=social)](https://github.com/madebyaris/spec-kit-command-cursor/network/members)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](http://makeapullrequest.com)\n\n**Agentic-First Spec-Driven Development for Cursor IDE**\n\n*AI agents that directly execute specifications - not vague descriptions, but explicit instructions*\n\n[🚀 Quick Start](#-quick-start) • [📖 Commands](#-sdd-commands) • [🎯 Examples](#-example-workflow) • [🤝 Contributing](#-contributing)\n\n\u003c/div\u003e\n\n---\n\n## 🆕 What's New in v3.0\n\n### Agentic-First Architecture\n\nSDD v3.0 transforms templates from descriptions into **direct agent instructions**:\n\n- **Role Declarations**: Every command starts with \"You are a [role]. Your job is [purpose].\"\n- **State Assertions**: AI outputs its mode and boundaries before starting\n- **Self-Correction Protocol**: Built-in mistake detection and recovery\n- **Mode Boundaries**: Explicit \"will do\" and \"will NOT do\" rules\n- **Verification Checkpoints**: Gates before file creation\n\n### New Commands\n\n| Command | Purpose |\n|---------|---------|\n| `/generate-prd` | Create PRDs through Socratic questioning |\n| `/audit` | Spec-driven technical audit (compare code against specs) |\n| `/refine` | Iterate on specs through discussion |\n\n### Cursor Mode Integration\n\nEach command now maps to the optimal Cursor mode:\n\n| SDD Commands | Cursor Mode |\n|--------------|-------------|\n| `/brief`, `/specify`, `/plan`, `/tasks` | Plan |\n| `/research` | Ask (read-only) |\n| `/implement`, `/execute-task` | Agent |\n| `/audit` | Debug |\n\n---\n\n## 🎯 What is Spec-Driven Development?\n\n\u003e **Stop coding blindly. Start building with purpose.**\n\nSpec-Driven Development creates detailed specifications **before** writing code:\n\n- 🎯 **Requirements are crystal clear** before implementation\n- 🏗️ **Technical decisions are well-planned** and documented\n- 📋 **Development tasks are structured** and manageable\n- 🤝 **AI agents execute systematically** with explicit instructions\n\n### The Agentic Difference\n\n**Old way (vague):**\n\u003e \"This command helps create specifications...\"\n\n**New way (agentic):**\n\u003e \"**You are a specification agent.** Your job is to create detailed requirements. **You WILL** ask clarifying questions and define acceptance criteria. **You will NOT** write implementation code or skip the plan presentation.\"\n\n---\n\n## 🚀 Quick Start\n\n### 1. Install\n```bash\ngit clone https://github.com/madebyaris/spec-kit-command-cursor.git\ncd spec-kit-command-cursor\n```\n\n### 2. Start Using\n```bash\n# Quick 30-minute planning (80% of features)\n/brief user-auth JWT authentication with login/logout\n\n# Full project roadmap\n/sdd-full-plan blog-platform Full-featured blog with CMS\n\n# Create PRD through questions\n/generate-prd mobile-app\n\n# Audit code against specs\n/audit user-auth Login failures on mobile\n```\n\n### 3. Understand the Workflow\n\nEvery command follows **plan-approve-execute**:\n\n```\nUser Command → AI Analyzes → Shows Plan → You Approve → AI Executes → Verifies\n```\n\n---\n\n## 📋 SDD Commands\n\n### 🚀 Primary Workflow (80% of features)\n\n| Command | Purpose | Output |\n|---------|---------|--------|\n| `/brief` | 30-min planning → start coding | `feature-brief.md` |\n| `/evolve` | Update specs during development | Updated brief with changelog |\n| `/refine` | Iterate on specs through discussion | Refined documentation |\n\n### 📊 Full Project Planning\n\n| Command | Purpose | Output |\n|---------|---------|--------|\n| `/sdd-full-plan` | Complete A-Z roadmap | Kanban board + tasks |\n| `/execute-task` | Run task from roadmap | Executes with appropriate SDD command |\n| `/generate-prd` | PRD via Socratic questions | `full-prd.md` + `quick-prd.md` |\n\n**🚀 NEW: `--until-finish` flag** - Add to any command above for automated execution!\n\n### 🏗️ Advanced Workflow (20% of complex features)\n\n| Command | Purpose | Output |\n|---------|---------|--------|\n| `/research` | Investigate patterns (read-only) | `research.md` |\n| `/specify` | Detailed requirements | `spec.md` |\n| `/plan` | Technical architecture | `plan.md` |\n| `/tasks` | Task breakdown | `tasks.md` |\n| `/implement` | Execute implementation | Code + `todo-list.md` |\n\n### 🔧 Utilities\n\n| Command | Purpose | Output |\n|---------|---------|--------|\n| `/upgrade` | Brief → Full SDD 2.0 | Complete planning suite |\n| `/audit` | Spec-driven technical audit | Audit report with fixes |\n| `/generate-rules` | Auto-generate coding rules | `.cursor/rules/*.mdc` |\n\n---\n\n## 🎨 Agentic Template Structure\n\nEvery command template follows this structure:\n\n```markdown\n# /command Command\n\n[Brief description]\n\n---\n\n## IMPORTANT: This is [Mode] Mode\n\n**You are a [role].** Your job is to [purpose].\n\n**Your role:**\n- [What you will do 1]\n- [What you will do 2]\n\n**Mode boundaries (What you will NOT do):**\n- [Forbidden action 1]\n- [Forbidden action 2]\n\n**Recommended Cursor Mode:** [Mode]\n\n---\n\n## State Assertion (REQUIRED)\n\n**Before starting, output:**\n```\n**SDD MODE: [Command]**\nMode: [planning|implementation|research|verification]\nPurpose: [Specific purpose]\nImplementation: [BLOCKED|AUTHORIZED]\n```\n\n---\n\n## Self-Correction Protocol\n\n**DETECT**: If you find yourself...\n**STOP**: Immediately halt\n**CORRECT**: \"I apologize - I was [mistake]. Let me return to [correct mode].\"\n**RESUME**: Continue correctly\n\n---\n\n## Instructions\n[Phase 1: Analysis → Phase 2: Planning → Phase 3: Execution → Phase 4: Verification]\n\n---\n\n## Output (REQUIRED)\n[Exact format for completion message]\n```\n\n---\n\n## 🎯 Example Workflows\n\n### Quick Feature (SDD 2.5)\n\n```bash\n# 1. Create 30-minute brief\n/brief checkout-flow Quick checkout for guests\n\n# 2. Start coding! Update as you discover things\n/evolve checkout-flow Added guest cart persistence\n\n# 3. Refine if needed\n/refine checkout-flow\n```\n\n### Full Project (sdd-full-plan)\n\n```bash\n# 1. Create complete roadmap\n/sdd-full-plan ecommerce-platform Multi-vendor marketplace\n\n# 2. Execute tasks from roadmap\n/execute-task epic-001\n/execute-task task-001-1\n\n# 3. Audit issues\n/audit task-001-1 Payment processing failing\n```\n\n### Complex Feature (SDD 2.0)\n\n```bash\n# 1. Research patterns\n/research payment-system Stripe integration patterns\n\n# 2. Define requirements\n/specify payment-system\n\n# 3. Design architecture\n/plan payment-system\n\n# 4. Break down tasks\n/tasks payment-system\n\n# 5. Implement\n/implement payment-system\n```\n\n### PRD Creation\n\n```bash\n# Create PRD through guided questions\n/generate-prd saas-dashboard\n\n# AI asks 5 strategic questions, then creates:\n# - full-prd.md (comprehensive)\n# - quick-prd.md (AI-optimized)\n```\n\n---\n\n## 📁 Project Structure\n\n```\nyour-project/\n├── .cursor/\n│   ├── commands/           # SDD slash commands\n│   │   ├── _shared/       # Shared agent protocols\n│   │   │   ├── agent-manual.md\n│   │   │   ├── self-correction.md\n│   │   │   └── cursor-modes.md\n│   │   ├── brief.md\n│   │   ├── research.md\n│   │   ├── specify.md\n│   │   ├── plan.md\n│   │   ├── tasks.md\n│   │   ├── implement.md\n│   │   ├── evolve.md\n│   │   ├── upgrade.md\n│   │   ├── refine.md\n│   │   ├── generate-prd.md\n│   │   ├── audit.md\n│   │   ├── generate-rules.md\n│   │   ├── sdd-full-plan.md\n│   │   └── execute-task.md\n│   └── rules/\n│       └── sdd-system.mdc  # Always-applied rules\n├── .sdd/\n│   ├── guidelines.md       # Development methodology\n│   ├── IMPLEMENTATION_GUIDE.md\n│   └── ROADMAP_FORMAT_SPEC.md\n├── specs/\n│   ├── active/            # Features in development\n│   │   └── [task-id]/\n│   │       ├── feature-brief.md\n│   │       ├── spec.md\n│   │       ├── plan.md\n│   │       └── tasks.md\n│   └── todo-roadmap/      # Project roadmaps\n│       └── [project-id]/\n│           ├── roadmap.json\n│           ├── roadmap.md\n│           └── tasks/\n└── src/                   # Your code\n```\n\n---\n\n## 🔧 Cursor Mode Integration\n\n### Mode Mapping\n\n| SDD Command | Cursor Mode | Why |\n|-------------|-------------|-----|\n| `/brief` | Plan | Create specs without code changes |\n| `/research` | Ask | Read-only exploration |\n| `/specify` | Plan | Define requirements |\n| `/plan` | Plan | Architecture design |\n| `/tasks` | Plan | Task breakdown |\n| `/implement` | Agent | Full multi-file changes |\n| `/audit` | Debug | Spec-driven audit with runtime evidence |\n\n### Switching Modes\n\nUse `Cmd+.` (Mac) or `Ctrl+.` (Windows/Linux) to switch modes.\n\n### Using Debug Mode with /audit\n\nCursor's built-in Debug Mode pairs perfectly with the `/audit` command:\n\n1. **Switch to Debug Mode** (`Cmd+.` or `Ctrl+.`)\n2. **Run `/audit [task-id]`** to compare code against specs\n3. **Leverage Debug Mode's features** for runtime evidence:\n   - Hypothesis generation\n   - Log instrumentation\n   - Runtime analysis\n\n---\n\n## 🔍 The /audit Command\n\nSpec-driven technical audit that compares implementation against specifications:\n\n```bash\n/audit user-auth Login failures on mobile\n```\n\n**What it does:**\n1. Reads specifications (spec.md, plan.md)\n2. Inspects actual implementation\n3. Compares code against requirements\n4. Generates Review Board with severity levels\n5. Proposes fixes only after investigation\n\n**Synergy with Debug Mode:**\nWhen running in Cursor's Debug Mode, `/audit` can leverage log instrumentation to gather runtime evidence alongside spec comparison.\n\n**Output:**\n```\n📋 Audit Report Ready\n\nSummary:\n- 🔴 Critical: 1 issue (SQL injection)\n- 🟠 Major: 2 issues (missing validation)\n- 🟡 Minor: 3 issues (naming, comments)\n\nTo fix: \"Fix #1\" or \"Fix all critical\"\n```\n\n---\n\n## 🚀 The `--until-finish` Flag\n\n**Automated execution mode** - run entire projects without stopping!\n\n```bash\n# Execute an entire epic automatically\n/execute-task epic-001 --until-finish\n\n# Create roadmap AND execute everything\n/sdd-full-plan my-project Complete app with auth --until-finish\n/pecut-all-in-one my-project Full SaaS dashboard --until-finish\n```\n\n**What it does:**\n1. Executes all tasks in dependency order\n2. No user approval needed between tasks\n3. **Stops on error** - reports issue for you to fix\n4. Resume with same command after fixing\n5. Continues until complete\n\n**Flow:**\n```\nStart → Task 1 ✅ → Task 2 ✅ → Task 3 ❌ Error → STOP → Fix → Resume → Task 3 ✅ → Done! 🎉\n```\n\n**Scope:**\n- `/execute-task [epic-id] --until-finish` - Executes that epic and all its subtasks\n- `/execute-task [task-id] --until-finish` - Executes from that task to end of epic\n- `/sdd-full-plan --until-finish` - Creates roadmap AND executes ALL tasks\n\nThis is **\"fire and forget\"** mode - start it and come back when your project is built!\n\n---\n\n## 📝 The /generate-prd Command\n\nCreate PRDs through guided Socratic questioning:\n\n```bash\n/generate-prd mobile-banking\n```\n\n**Questions asked:**\n1. What problem and goal?\n2. What are the must-have features?\n3. Any technical requirements?\n4. What's explicitly out of scope?\n5. Anything else I should know?\n\n**Output:**\n- `full-prd.md` - Comprehensive PRD\n- `quick-prd.md` - AI-optimized summary\n\n---\n\n## 🤝 Contributing\n\nWe ❤️ contributions!\n\n- 🐛 **Report bugs** - [Open an issue](https://github.com/madebyaris/spec-kit-command-cursor/issues)\n- 💡 **Suggest features** - [Start a discussion](https://github.com/madebyaris/spec-kit-command-cursor/discussions)\n- 🔧 **Submit PRs** - Improvements welcome!\n- ⭐ **Star this repo** - Show your support!\n\n### Recent Changes\n\n- ✅ v3.0: Agentic-first template rewrite\n- ✅ New commands: `/generate-prd`, `/audit`, `/refine`\n- ✅ **NEW: `--until-finish` flag** - Automated execution mode\n- ✅ Cursor mode integration (including Debug Mode)\n- ✅ Self-correction protocols\n- ✅ Shared agent protocols (`_shared/`)\n\n## 🙏 Acknowledgments\n\nSpecial thanks to [ClavixDev](https://github.com/ClavixDev) for providing valuable ideas and suggestions on how to improve this project!\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**Made with ❤️ by [Aris](https://github.com/madebyaris)**\n\n### 🎊 Try Your First Command!\n\n```bash\n/brief hello-world Create a simple hello world feature\n```\n\n[⬆️ Back to top](#-sdd-cursor-commands-v30)\n\n\u003c/div\u003e\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmadebyaris%2Fspec-kit-command-cursor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmadebyaris%2Fspec-kit-command-cursor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmadebyaris%2Fspec-kit-command-cursor/lists"}