opencode-goopspec 0.1.0

package/commands/goop-research.md

@@ -0,0 +1,98 @@
+---
+name: goop-research
+description: Start the Research phase - explore implementation approaches
+---
+
+# GoopSpec Research
+
+Gather context and explore implementation approaches before committing to a specification.
+
+## Usage
+
+```
+/goop-research
+```
+
+## Workflow Position
+
+```
+┌─────────────┐     ┌─────────────┐     ┌─────────────┐
+│    PLAN     │ ──▶ │  RESEARCH   │ ──▶ │   SPECIFY   │
+│  (Intent)   │     │  (Explore)  │     │ (Contract)  │
+└─────────────┘     └─────────────┘     └─────────────┘
+                          ↑
+                    (You are here)
+```
+
+The Research phase answers: **How should we build this?**
+
+## What Happens
+
+1. **Parallel Agent Spawning** - Multiple agents work simultaneously:
+   - **Researcher** - Deep domain research (technologies, patterns, best practices)
+   - **Explorer** - Codebase analysis (existing patterns, conventions, integration points)
+   - **Librarian** - Documentation gathering (API docs, library guides, examples)
+   - **Designer** - (UI tasks only) Visual research (patterns, components, UX)
+
+2. **Research Areas Covered:**
+   - Technology options and trade-offs
+   - Existing codebase patterns
+   - Domain knowledge and edge cases
+   - Security and performance considerations
+   - Industry standards and best practices
+
+3. **Consolidation** - Findings merged into RESEARCH.md with:
+   - Technology recommendations
+   - Codebase integration points
+   - Key decisions needed
+   - Risk assessment
+   - Estimated complexity
+
+4. **Memory Integration** - Past research and patterns retrieved
+
+## Artifacts Created
+
+- `RESEARCH.md` - Consolidated research findings
+- Technology comparison table
+- Recommended approach with rationale
+- Risk catalog
+- Integration points identified
+
+## Example
+
+After planning "Add user authentication":
+
+```
+/goop-research
+```
+
+Research agents explore:
+- JWT vs session-based auth
+- Existing auth patterns in codebase
+- Security best practices
+- Library options (jose, jsonwebtoken, etc.)
+- Integration with current user model
+
+## Next Steps
+
+After research:
+- `/goop-specify` - Lock the specification (CONTRACT GATE)
+
+## Quick Mode Shortcut
+
+For Quick tasks, Research phase is **SKIPPED entirely**:
+- Assumes existing patterns are sufficient
+- No parallel agent spawning
+- Jumps directly from Plan to Execute
+
+## Comprehensive Mode
+
+For Comprehensive tasks:
+- Deeper research per agent
+- More alternatives explored
+- Extended timeframe
+- User reviews RESEARCH.md before Specify
+
+---
+
+**GoopSpec**: Research thoroughly, decide confidently.

package/commands/goop-resume.md

@@ -0,0 +1,57 @@
+---
+name: goop-resume
+description: Resume from a checkpoint
+---
+
+# GoopSpec Resume
+
+Resume your work from a saved checkpoint.
+
+## Usage
+
+```
+/goop-resume [checkpoint-id]
+```
+
+## What Gets Restored
+
+When resuming:
+- Session context is restored
+- Current phase is set
+- Active spec is loaded
+- Todos are displayed
+- Modified files list is shown
+
+## Without Checkpoint ID
+
+If no checkpoint ID is provided, loads the **most recent** checkpoint.
+
+## Example
+
+```
+/goop-resume
+```
+
+Or specify a specific checkpoint:
+```
+/goop-resume checkpoint-abc123
+```
+
+## Workflow
+
+1. **Load checkpoint data**
+2. **Restore session context**
+3. **Display current todos**
+4. **Show relevant files**
+5. **Ready to continue work**
+
+## See Available Checkpoints
+
+To list all checkpoints:
+```
+Use the goop_checkpoint tool with action: "list"
+```
+
+---
+
+**GoopSpec**: Pick up exactly where you left off.

package/commands/goop-setup.md

@@ -0,0 +1,208 @@
+---
+name: goop-setup
+description: First-time GoopSpec setup wizard with model picker
+---
+
+# GoopSpec Setup Wizard
+
+You are helping the user set up GoopSpec for the first time. This wizard includes an in-depth model picker for configuring each agent.
+
+## Step 1: Detect Current Environment
+
+First, call the `goop_setup` tool with `action: "detect"` to see what's already configured:
+
+```
+goop_setup(action: "detect")
+```
+
+Review the output and share a brief summary with the user about their current state.
+
+## Step 2: Configuration Scope
+
+Ask: "Where should GoopSpec be configured?"
+
+Use the question tool to present these options:
+- **both** (Recommended) - Both global and project-specific settings
+- **global** - Only system-wide settings (~/.config/opencode/goopspec.json)
+- **project** - Only this project (.goopspec/config.json)
+
+## Step 3: MCP Preset
+
+Ask: "Which MCPs should be installed?"
+
+Use the question tool to present these options:
+- **recommended** - Context7 + Exa + Playwright (full GoopSpec workflow support)
+- **core** - Context7 + Exa only (minimal setup)
+- **none** - Skip MCP installation
+
+## Step 4: Default Agent
+
+Ask: "Should GoopSpec be set as your default agent?"
+
+Use the question tool:
+- **yes** - GoopSpec orchestrator will be the default for new sessions
+- **no** - Keep current default agent
+
+## Step 5: Model Configuration
+
+This is the key step. Ask: "Would you like to configure models for each agent?"
+
+Use the question tool:
+- **Quick setup** - Use recommended defaults for all agents
+- **Custom setup** - Choose models for each agent individually
+
+### If Quick Setup
+Use the defaults from agent files (user can change later):
+- goop-debugger: openai/gpt-5.2-codex
+- goop-designer: anthropic/claude-opus-4-5
+- goop-executor: openai/gpt-5.2-codex
+- goop-explorer: google/antigravity-gemini-3-flash
+- goop-librarian: openai/gpt-5.2
+- goop-orchestrator: anthropic/claude-opus-4-5
+- goop-planner: anthropic/claude-opus-4-5
+- goop-researcher: openai/gpt-5.2
+- goop-tester: opencode/kimi-k2.5-free
+- goop-verifier: openai/gpt-5.2-codex
+- goop-writer: google/antigravity-gemini-3-pro-high
+
+### If Custom Setup
+For EACH agent, present a model picker using the question tool. Include a "Custom model" option that allows free text entry.
+
+#### Agent Model Options
+
+**goop-debugger** (Systematic debugging with hypothesis testing):
+1. openai/gpt-5.2-codex
+2. anthropic/claude-opus-4-5
+3. opencode/kimi-k2.5-free
+- Custom model...
+
+**goop-designer** (Visual design planning and UI/UX reasoning):
+1. anthropic/claude-opus-4-5
+2. opencode/kimi-k2.5-free
+3. google/antigravity-gemini-3-pro-high
+- Custom model...
+
+**goop-executor** (Task execution with checkpoints and verification):
+1. openai/gpt-5.2-codex
+2. anthropic/claude-opus-4-5
+3. anthropic/claude-sonnet-4-5
+4. opencode/kimi-k2.5-free
+5. google/antigravity-gemini-3-pro-high
+6. opencode/glm-4.7-free
+- Custom model...
+
+**goop-explorer** (Fast codebase exploration and pattern extraction):
+1. google/antigravity-gemini-3-flash
+2. anthropic/claude-haiku-4-5
+3. opencode/minimax-m2.1-free
+- Custom model...
+
+**goop-librarian** (Codebase search and documentation retrieval):
+1. openai/gpt-5.2
+2. google/antigravity-gemini-3-flash
+3. anthropic/claude-sonnet-4-5
+- Custom model...
+
+**goop-orchestrator** (Primary orchestrator - spec clarity and wave execution):
+1. anthropic/claude-opus-4-5
+2. openai/gpt-5.2-codex
+3. opencode/kimi-k2.5-free
+4. anthropic/claude-sonnet-4-5
+- Custom model...
+
+**goop-planner** (Detailed execution plans with architectural precision):
+1. anthropic/claude-opus-4-5
+2. openai/gpt-5.2-codex
+3. opencode/kimi-k2.5-free
+4. anthropic/claude-sonnet-4-5
+- Custom model...
+
+**goop-researcher** (Comprehensive ecosystem research):
+1. openai/gpt-5.2
+2. anthropic/claude-sonnet-4-5
+3. opencode/kimi-k2.5-free
+4. opencode/glm-4.7-free
+- Custom model...
+
+**goop-tester** (Web frontend testing with Playwright):
+1. opencode/kimi-k2.5-free
+2. anthropic/claude-sonnet-4-5
+3. google/antigravity-gemini-3-flash
+- Custom model...
+
+**goop-verifier** (Post-execution verification with security focus):
+1. openai/gpt-5.2-codex
+2. anthropic/claude-opus-4-5
+- Custom model...
+
+**goop-writer** (Comprehensive documentation generation):
+1. google/antigravity-gemini-3-pro-high
+2. opencode/kimi-k2.5-free
+3. anthropic/claude-sonnet-4-5
+- Custom model...
+
+## Step 6: Preview the Plan
+
+After collecting all answers, call `goop_setup` with `action: "plan"` and the user's choices:
+
+```
+goop_setup(
+  action: "plan",
+  scope: "<user_choice>",
+  mcpPreset: "<user_choice>",
+  enableOrchestrator: <true/false>,
+  agentModels: {
+    "goop-orchestrator": "<model>",
+    "goop-planner": "<model>",
+    "goop-executor": "<model>",
+    // ... other agents
+  }
+)
+```
+
+Show the user a summary including:
+- Configuration scope
+- MCPs to install
+- Agent model assignments (in a table format)
+
+Ask for confirmation before proceeding.
+
+## Step 7: Apply Configuration
+
+If the user confirms, call `goop_setup` with `action: "apply"` and the same parameters.
+
+## Step 8: Verify and Complete
+
+After applying, summarize what was done:
+- List all agents and their assigned models
+- List MCPs installed
+- Show any warnings or notes
+
+Suggest next steps:
+- Run `/goop-status` to verify configuration
+- Start a new conversation to use GoopSpec
+- Try `/goop-discuss` to start your first spec-driven project
+
+## Tips for the Model Picker
+
+1. **Be conversational** - Don't just list options, explain the trade-offs
+2. **Group similar agents** - You can ask about related agents together (e.g., "orchestrator + planner" or "explorer + librarian")
+3. **Explain costs** - Opus models are more capable but expensive; free models (opencode/*) are great for budget-conscious users
+4. **Allow skipping** - If a user says "use defaults for the rest", accept that
+5. **Support bulk selection** - If a user says "use Claude Sonnet for everything", honor that
+
+## Available Models
+
+All models listed in the suggestions:
+- openai/gpt-5.2-codex
+- openai/gpt-5.2
+- anthropic/claude-opus-4-5
+- anthropic/claude-sonnet-4-5
+- anthropic/claude-haiku-4-5
+- google/antigravity-gemini-3-pro-high
+- google/antigravity-gemini-3-flash
+- opencode/kimi-k2.5-free
+- opencode/glm-4.7-free
+- opencode/minimax-m2.1-free
+
+Users can also enter any custom model name supported by their OpenCode installation.

package/commands/goop-specify.md

@@ -0,0 +1,145 @@
+---
+name: goop-specify
+description: Lock the specification - the CONTRACT between user and agent
+---
+
+# GoopSpec Specify
+
+Lock the specification - the binding contract that defines exactly what will be delivered.
+
+## Usage
+
+```
+/goop-specify
+```
+
+## Workflow Position
+
+```
+┌─────────────┐     ┌─────────────┐     ┌─────────────┐
+│    PLAN     │ ──▶ │  RESEARCH   │ ──▶ │   SPECIFY   │
+│  (Intent)   │     │  (Explore)  │     │ (Contract)  │
+└─────────────┘     └─────────────┘     └─────────────┘
+                                              ↑
+                                        (You are here)
+
+       ╔══════════════════════════════════════════════╗
+       ║          CONTRACT GATE                        ║
+       ║   User MUST confirm before execution begins   ║
+       ╚══════════════════════════════════════════════╝
+```
+
+The Specify phase answers: **What exactly will we deliver?**
+
+## What Happens
+
+1. **Synthesize Plan + Research** - Combine intent with technical approach
+2. **Define Must-Haves** - Observable, achievable, specific deliverables (3-7 items)
+3. **Set Boundaries** - Explicitly state what's out of scope
+4. **Create SPEC.md** - The locked specification document
+5. **Create BLUEPRINT.md** - Wave-based execution plan
+6. **Present Contract** - Show must-haves, nice-to-haves, out-of-scope
+7. **Wait for Confirmation** - User MUST type "confirm" to proceed
+
+## The Contract Concept
+
+Once locked, the specification becomes a binding agreement:
+- **Agent commits** to delivering must-haves
+- **User commits** to accepting if must-haves are met
+- **Changes require** explicit amendment via `/goop-amend`
+
+### Why Contracts Matter
+
+**Without a locked spec:**
+- Scope creeps silently
+- "Almost done" never ends
+- Success criteria shift
+- Both parties frustrated
+
+**With a locked spec:**
+- Clear deliverables
+- Measurable completion
+- Explicit change process
+- Satisfied expectations
+
+## Artifacts Created
+
+- `SPEC.md` - Locked specification with:
+  - Intent summary
+  - Must-haves (guaranteed)
+  - Nice-to-haves (best effort)
+  - Out-of-scope (explicitly excluded)
+  - Technical approach
+  - Target files
+  - Acceptance criteria
+
+- `BLUEPRINT.md` - Wave-based execution plan with:
+  - Wave 1: Foundation tasks
+  - Wave 2: Core tasks
+  - Wave 3: Integration tasks
+  - Wave 4: Polish tasks
+
+## Confirmation Prompt
+
+```
+╭─ ⬢ GoopSpec ───────────────────────────────────────╮
+│                                                    │
+│  🔒 CONTRACT GATE                                  │
+│                                                    │
+│  I'm ready to lock the specification.              │
+│                                                    │
+│  MUST HAVES (I commit to delivering):              │
+│  • User can log in with email/password             │
+│  • Session persists across refresh                 │
+│  • Error messages displayed                        │
+│                                                    │
+│  NICE TO HAVES (Best effort):                      │
+│  • Remember me option                              │
+│                                                    │
+│  OUT OF SCOPE:                                     │
+│  • OAuth providers (future enhancement)            │
+│  • Password reset (separate feature)               │
+│                                                    │
+│  ACCEPTANCE CRITERIA:                              │
+│  1. User can successfully log in                   │
+│  2. Tests pass for auth flow                       │
+│  3. Session management works                       │
+│                                                    │
+│  ─────────────────────────────────────────────     │
+│  Type "confirm" to lock and proceed.               │
+│  Type "amend" to request changes.                  │
+│                                                    │
+╰────────────────────────────────────────────────────╯
+```
+
+## Example
+
+After research on authentication:
+
+```
+/goop-specify
+```
+
+Agent creates SPEC.md and BLUEPRINT.md, then presents contract for confirmation.
+
+## Next Steps
+
+After confirmation:
+- `/goop-execute` - Start wave-based implementation
+
+If changes needed:
+- Type "amend" to modify specification before locking
+
+After locking:
+- `/goop-amend [change]` - Propose changes to locked spec
+
+## Quick Mode Shortcut
+
+For Quick tasks, Specify phase is **SKIPPED**:
+- Intent from Plan phase serves as implicit spec
+- No formal SPEC.md
+- Jumps directly to Execute
+
+---
+
+**GoopSpec**: Lock the contract, deliver with confidence.

package/commands/goop-status.md

@@ -0,0 +1,153 @@
+---
+name: goop-status
+description: Show GoopSpec status and progress
+---
+
+# GoopSpec Status
+
+Display the current status of your GoopSpec project and workflow progress.
+
+## Usage
+
+```
+/goop-status
+```
+
+## Information Shown
+
+### Project State
+- Initialized: Yes/No
+- Active: Yes/No
+- Current milestone (if any)
+- Task mode: Quick | Standard | Comprehensive | Milestone
+
+### Current Workflow
+- Phase: Plan | Research | Specify | Execute | Accept
+- Spec locked: Yes/No
+- Acceptance confirmed: Yes/No
+- Last activity timestamp
+
+### Execution Progress (if in Execute phase)
+- Current wave: N of M
+- Tasks completed in current wave
+- Total tasks completed
+- Recent commits
+
+### Contract Status
+- Specification locked at: [timestamp]
+- Must-haves: N total
+- Must-haves completed: N of M
+- Nice-to-haves completed: N of M
+
+### Checkpoints
+- Total checkpoints saved
+- Latest checkpoint info
+- Resume available: Yes/No
+
+### Memory Stats
+- Decisions logged: N
+- Observations saved: N
+- Patterns documented: N
+
+## Example Output
+
+```
+⬢ GoopSpec · Status
+──────────────────────────────────────────────────────
+
+Project: Initialized ✓
+Mode: Standard
+Milestone: Authentication System
+
+WORKFLOW:
+Phase: Execute (Wave 2 of 4)
+Spec Locked: Yes (2024-01-15 10:30)
+Acceptance: Pending
+
+PROGRESS:
+Wave 1: Foundation [COMPLETE] ✓
+  ☑ Task 1.1: Setup
+  ☑ Task 1.2: Config
+  ☑ Task 1.3: Base
+
+Wave 2: Core [IN PROGRESS]
+  ☑ Task 2.1: Auth
+  ◉ Task 2.2: Logic
+  ○ Task 2.3: Data
+
+Wave 3: Integration [PENDING]
+Wave 4: Polish [PENDING]
+
+MUST-HAVES: 2 of 3 complete
+☑ User can log in
+☑ Session persists
+○ Error messages displayed
+
+CHECKPOINTS: 2 saved
+Latest: checkpoint-xyz789 (30 mins ago)
+
+MEMORY: 5 decisions, 12 observations
+
+──────────────────────────────────────────────────────
+```
+
+## Phase-Specific Information
+
+### Plan Phase
+- Intent captured: Yes/No
+- Requirements categorized: Yes/No
+- Success criteria defined: Yes/No
+- Ready for research: Yes/No
+
+### Research Phase
+- Agents spawned: N
+- Research complete: Yes/No
+- RESEARCH.md created: Yes/No
+- Ready for specify: Yes/No
+
+### Specify Phase
+- SPEC.md created: Yes/No
+- BLUEPRINT.md created: Yes/No
+- Contract presented: Yes/No
+- User confirmed: Yes/No
+
+### Execute Phase
+- Current wave: N of M
+- Tasks complete: N of M
+- Deviations: N logged
+- Blockers: N active
+
+### Accept Phase
+- Verification complete: Yes/No
+- Must-haves verified: N of M
+- Tests passing: Yes/No
+- User accepted: Yes/No
+
+## Quick Actions
+
+From status view, you can:
+- `/goop-plan [intent]` - Start planning
+- `/goop-research` - Begin research
+- `/goop-specify` - Lock specification
+- `/goop-execute` - Continue execution
+- `/goop-accept` - Verify completion
+- `/goop-pause` - Save checkpoint
+- `/goop-resume` - Resume from checkpoint
+
+## Verbose Mode
+
+For detailed status:
+
+```
+/goop-status --verbose
+```
+
+Shows additional information:
+- Full task list with commit hashes
+- All deviations with details
+- Complete checkpoint history
+- Memory entries related to current work
+
+---
+
+**GoopSpec**: Know exactly where you stand.