@tudeorangbiasa/sdd-multiagent-opencode 0.1.0

package/.opencode/skills/sdd-evolve/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: sdd-evolve
+description: Spec evolution and downstream propagation for SDD workflows. Activates when updating specifications with discoveries, managing spec changes, or propagating staleness to downstream documents. Use with /evolve command.
+---
+
+## What I do
+
+- Update existing specs with new discoveries while preserving context
+- Maintain changelog entries for spec evolution tracking
+- Detect and mark stale downstream documents
+- Propagate changes through the spec → plan → tasks chain
+
+## When to use me
+
+Use this skill when:
+- Running `/evolve` command
+- Discoveries during development require spec updates
+- Architecture changes need documentation alignment
+- Need to track what changed and why
+
+## Evolution Protocol
+
+### Phase 1: Analysis
+1. Find existing specs in `specs/active/[task-id]/`
+2. Read all related files to understand current state
+3. Categorize the change:
+
+| Category | Impact | Examples |
+|----------|--------|----------|
+| Discovery | Low | Small findings, new constraint |
+| Refinement | Low | Clarifying requirements |
+| Addition | Medium | New requirement, new feature |
+| Modification | Medium | Changed approach, updated design |
+| Removal | High | Descoping, architecture change |
+
+### Phase 2: Planning
+Present evolution plan with:
+- Task ID and file to update
+- Change summary, type, and impact level
+- Before/after diff of relevant sections
+- Proposed changelog entry
+
+**Wait for user approval before proceeding.**
+
+### Phase 3: Execution
+1. Update spec file preserving context
+2. Add changelog entry
+3. Increment version number
+4. Update timestamp
+
+### Phase 4: Downstream Propagation
+
+Check for stale downstream documents:
+
+1. **List downstream files** — `plan.md`, `tasks.md`, `todo-list.md`
+2. **Assess impact** using change category:
+   - Discovery/Refinement → downstream usually unaffected
+   - Addition/Modification → `plan.md` and `tasks.md` likely stale
+   - Removal/Architecture → all downstream docs stale
+3. **Add staleness marker** to affected files:
+   ```
+   > **[STALE]** — Upstream spec updated on [DATE]. Review needed.
+   > Change: [Brief description] (spec.md v[VERSION])
+   ```
+4. **Report affected files** in evolution summary
+
+## Changelog Format
+
+### For feature-brief.md
+```markdown
+## Changelog
+
+| Version | Date | Changes | Reason |
+|---------|------|---------|--------|
+| 1.1 | [date] | [description] | [reason] |
+| 1.0 | [date] | Initial | |
+```
+
+### For spec.md
+```markdown
+## Revision History
+
+| Version | Date | Changes | Author |
+|---------|------|---------|--------|
+| 1.1 | [date] | [description] | [author] |
+| 1.0 | [date] | Initial specification | [author] |
+```
+
+## When to Suggest Upgrade
+
+Suggest `/upgrade` when:
+- Change fundamentally alters approach
+- Multiple related changes needed
+- Brief is no longer sufficient for scope
+- Architecture needs redesign

package/.opencode/skills/sdd-implementation/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: sdd-implementation
+description: Systematic code implementation patterns for SDD workflows. Activates when executing planned implementations, following todo-lists, or building features according to specifications. Use with /implement command.
+---
+
+## What I do
+
+- Guide systematic execution of planned implementations
+- Enforce todo-list discipline with progress tracking
+- Ensure code follows existing patterns and conventions
+- Handle blockers with structured escalation
+- Coordinate with sdd-verifier for post-implementation validation
+
+## When to use me
+
+Use this skill when:
+- Running `/implement` command
+- Executing tasks from a plan or roadmap
+- Need systematic progress tracking during implementation
+- Building features according to specifications
+
+## Implementation Protocol
+
+### Before Starting
+1. Read `plan.md`, `tasks.md`, `todo-list.md`, and `spec.md`
+2. Understand the full scope before writing code
+3. Identify potential blockers early
+
+### Execution Rules
+1. **Sequential order** — respect task dependencies
+2. **Mark progress** — update `- [ ]` to `- [x]` immediately
+3. **Document blockers** — never skip silently
+4. **Follow patterns** — use `codebase-memory-mcp` to find existing conventions
+5. **Write tests** — alongside implementation, not after
+
+### Blocker Handling
+```markdown
+- [ ] [BLOCKED: reason] Task description
+  - Attempted: [what you tried]
+  - Needs: [what's required to unblock]
+```
+
+### After Completion
+1. Spawn `sdd-verifier` to validate implementation
+2. Update todo-list with final status
+3. Document discoveries for `/evolve`
+
+## Code Quality Standards
+
+- Match existing naming conventions
+- Follow established error handling patterns
+- Use existing utility functions (check via `codebase-memory-mcp`)
+- Write tests for new functionality
+- No secrets or credentials in code
+
+## TDD Mode (Optional)
+
+When `--tdd` flag is specified, follow this protocol instead of the standard approach:
+
+### TDD Loop per Task
+
+1. **Write failing test first**
+   - Create test file: `tests/[feature].test.ts`
+   - Write test that describes expected behavior
+   - Run test → must fail with clear error
+
+2. **Implement minimum code**
+   - Write only what's needed to make test pass
+   - Do NOT add features beyond the test
+   - Do NOT refactor yet
+
+3. **Verify test passes**
+   - Run specific test
+   - Confirm pass before moving on
+
+4. **Refactor (optional)**
+   - Only after test passes
+   - Keep test passing during refactor
+
+### TDD Rules
+- Never write implementation before failing test
+- Test must fail BEFORE implementation starts
+- Only implement enough to pass the test
+- Refactor AFTER, not before
+
+## Output Templates
+
+Use `todo-compact.md` template from `.sdd/templates/`

package/.opencode/skills/sdd-planning/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: sdd-planning
+description: Architecture design and planning patterns for SDD workflows. Activates when generating technical plans, breaking down tasks, or creating feature briefs. Use with /brief, /plan, /tasks, /specify commands.
+---
+
+## What I do
+
+- Transform specifications into actionable technical plans
+- Guide architecture design with Mermaid diagrams
+- Break down features into 2-8 hour tasks with DAG dependencies
+- Create feature briefs for quick planning workflows
+- Estimate effort and identify technical risks
+
+## When to use me
+
+Use this skill when:
+- Running `/brief`, `/plan`, `/tasks`, or `/specify` commands
+- A spec exists and needs technical architecture
+- Breaking down a feature into implementation tasks
+- Need to estimate effort and identify risks
+
+## Planning Protocol
+
+### Brief Planning (30 min)
+1. Parse feature description, extract requirements
+2. Quick codebase scan for existing patterns
+3. Ask clarifying questions if needed
+4. Generate feature-brief.md with problem, users, requirements, approach
+
+### Full Planning (60 min)
+1. Read spec.md thoroughly
+2. Analyze codebase constraints via `codebase-memory-mcp`
+3. Design architecture with Mermaid diagrams
+4. Define components, APIs, data models
+5. Assess risks and open questions
+
+### Task Breakdown
+1. Read plan.md
+2. Organize into phases: Setup → Core → Integration → Polish
+3. Break into 2-8 hour tasks
+4. Define dependencies for DAG execution
+5. Populate `sdd.touchedFiles` for parallel execution safety
+
+## Estimation Heuristics
+
+| Size | Hours | Examples |
+|------|-------|----------|
+| S | 2-4h | Add endpoint, create component, add validation |
+| M | 4-8h | Implement feature, add integration, refactor module |
+| L | 8-16h | Complex feature, major refactor, new subsystem |
+| XL | 16h+ | ⚠️ Break this down further! |
+
+## Output Templates
+
+Use templates from `.sdd/templates/`:
+- `feature-brief-v2.md` for briefs
+- `spec-compact.md` for specifications
+- `plan-compact.md` for technical plans
+- `tasks-compact.md` for task breakdowns

package/.opencode/skills/sdd-research/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: sdd-research
+description: Structured investigation patterns for SDD workflows. Activates when researching technical approaches, evaluating external solutions, or investigating codebase patterns. Use with /research command.
+---
+
+## What I do
+
+- Guide systematic codebase exploration using `codebase-memory-mcp` tools
+- Structure external research with `exa_web_search_exa` for pattern investigation
+- Provide deep research methodology for high-stakes decisions
+- Generate comparison matrices and confidence assessments
+
+## When to use me
+
+Use this skill when:
+- Running `/research` command
+- Technical approach is unclear and needs investigation
+- Evaluating multiple technologies or approaches
+- Need to understand existing codebase patterns before planning
+
+## Research Protocol
+
+### Standard Research
+1. **Internal scan** — Use `codebase-memory-mcp` `search_graph` and `get_architecture` for existing patterns
+2. **External scan** — Use `exa_web_search_exa` for available solutions
+3. **Comparison** — Create pros/cons matrix for top 3 options
+4. **Recommendation** — Primary + alternative with rationale
+
+### Deep Research (`--deep` flag)
+1. **Pass 1 — Landscape:** `exa_web_search_exa` to identify top 3-5 candidates
+2. **Pass 2 — Documentation:** `webfetch` official docs, API references, pricing
+3. **Pass 3 — Validation:** Search for production reviews, benchmarks, comparisons
+4. **Pass 4 — Integration:** Search for integration guides with project stack
+
+### Source Evaluation
+| Reliability | Source Types |
+|-------------|-------------|
+| High | Official docs, RFCs, peer-reviewed benchmarks |
+| Medium | Established blogs, Stack Overflow (high votes), GitHub issues (resolved) |
+| Low | Personal blogs, forum posts, outdated articles |
+
+## Output Templates
+
+Use the research.md template from `.sdd/templates/research-compact.md`

package/.sdd/config.json

@@ -0,0 +1,36 @@
+{
+  "version": "1.0.0",
+  "project": {
+    "name": "SDD Multi-Agent OpenCode",
+    "description": "Spec-Driven Development framework for OpenCode with multi-agent orchestration",
+    "created": "2026-05-17"
+  },
+  "settings": {
+    "defaultFeaturePrefix": "feat-",
+    "autoNumberFeatures": true,
+    "requireReviews": true,
+    "collaborationMode": true,
+    "defaultWorkflow": "brief",
+    "planningTimeLimit": 30,
+    "maxParallelImplementers": 4,
+    "templates": {
+      "brief": ".sdd/templates/feature-brief-v2.md",
+      "spec": ".sdd/templates/spec-compact.md",
+      "plan": ".sdd/templates/plan-compact.md",
+      "tasks": ".sdd/templates/tasks-compact.md",
+      "research": ".sdd/templates/research-compact.md",
+      "todo": ".sdd/templates/todo-compact.md"
+    }
+  },
+  "directories": {
+    "specs": "specs",
+    "active": "specs/active",
+    "completed": "specs/completed",
+    "backlog": "specs/backlog"
+  },
+  "workflow": {
+    "phases": ["specify", "plan", "tasks", "implement", "review", "complete"],
+    "requiredFiles": ["spec.md", "plan.md", "tasks.md"],
+    "optionalFiles": ["progress.md", "reviews.md", "notes.md"]
+  }
+}

package/.sdd/templates/feature-brief-v2.md

@@ -0,0 +1,65 @@
+# Feature Brief: [Feature Name]
+
+**Task ID:** [task-id]
+**Created:** [date]
+**Status:** Ready for Development
+
+---
+
+## Problem Statement
+
+[What problem does this solve? 2-3 sentences]
+
+## Target Users
+
+[Who will use this? Be specific]
+
+## Core Requirements
+
+### Must Have
+- [ ] [Requirement 1]
+- [ ] [Requirement 2]
+- [ ] [Requirement 3]
+
+### Nice to Have
+- [ ] [Optional 1]
+- [ ] [Optional 2]
+
+## Technical Approach
+
+[High-level approach, 3-5 sentences]
+
+**Patterns to Follow:**
+- [Existing pattern 1 from codebase]
+- [Existing pattern 2 from codebase]
+
+**Key Decisions:**
+- [Decision 1]: [Rationale]
+- [Decision 2]: [Rationale]
+
+## Next Actions
+
+1. [ ] [First concrete step]
+2. [ ] [Second step]
+3. [ ] [Third step]
+
+## Success Criteria
+
+- [ ] [How we know it's done 1]
+- [ ] [How we know it's done 2]
+
+## Open Questions
+
+- [Any unresolved questions]
+
+---
+
+## Changelog
+
+| Version | Date | Changes | Reason |
+|---------|------|---------|--------|
+| 1.0 | [date] | Initial | |
+
+---
+
+*Brief created with SDD Multi-Agent OpenCode*

package/.sdd/templates/plan-compact.md

@@ -0,0 +1,50 @@
+# Technical Plan: [Feature Name]
+
+**Task ID:** [task-id]
+**Status:** Ready for Implementation
+**Based on:** spec.md / feature-brief.md
+
+## 1. System Architecture
+- Overview with diagram (if helpful)
+- Architecture decisions table (Decision | Choice | Rationale)
+
+## 2. Technology Stack
+- Layer | Technology | Version | Rationale table
+- Dependencies (JSON)
+
+## 3. Component Design
+- For each component: Purpose, Responsibilities, Interfaces, Dependencies
+
+## 4. Data Model
+- Entities with TypeScript interfaces
+- Relationships
+- Database schema (if applicable)
+
+## 5. API Contracts
+- Endpoints table (Method | Path | Description)
+- Request/Response examples
+
+## 6. Security Considerations
+- Authentication, Authorization, Data Protection
+- Security checklist
+
+## 7. Performance Strategy
+- Optimization targets, Caching, Scaling approach
+
+## 8. Implementation Phases
+- Phased approach with checkboxes
+
+## 9. Risk Assessment
+- Risk | Impact | Likelihood | Mitigation table
+
+## 10. Open Questions
+- Unresolved items requiring input
+
+## Next Steps
+- Review plan
+- Run `/tasks [task-id]` to generate tasks
+- Run `/implement [task-id]` to start building
+
+---
+
+*Plan created with SDD Multi-Agent OpenCode*

package/.sdd/templates/project-profile-template.json

@@ -0,0 +1,33 @@
+{
+  "projectState": "unknown",
+  "initialized": null,
+  "lastUpdated": null,
+  "stack": {
+    "framework": null,
+    "language": null,
+    "packageManager": null,
+    "styling": null
+  },
+  "commands": {
+    "dev": null,
+    "build": null,
+    "test": null,
+    "lint": null
+  },
+  "design": {
+    "sourceOfTruth": null,
+    "hasDesignMd": false,
+    "hasProductMd": false,
+    "componentRoots": []
+  },
+  "skillRouting": {
+    "uiDefault": "existing-design-system",
+    "visualVerification": "sdd-verifier",
+    "codeReview": "sdd-reviewer"
+  },
+  "sddSettings": {
+    "defaultBriefTemplate": "feature-brief-v2",
+    "autoCheckpoint": true,
+    "compactAtPercent": 80
+  }
+}

package/.sdd/templates/research-compact.md

@@ -0,0 +1,114 @@
+# Research: [Topic]
+
+**Task ID:** [task-id]
+**Date:** [date]
+**Status:** Complete
+
+---
+
+## Executive Summary
+
+[2-3 paragraph summary of key findings and initial recommendation]
+
+---
+
+## Codebase Analysis
+
+### Existing Patterns
+
+[Document patterns found in codebase with code examples]
+
+### Reusable Components
+
+[List components/utilities that can be reused]
+
+### Conventions to Follow
+
+[Coding conventions and architectural patterns to maintain]
+
+---
+
+## External Solutions
+
+### Option 1: [Name]
+
+**Overview:** [Description]
+
+**Pros:**
+- [Pro 1]
+- [Pro 2]
+
+**Cons:**
+- [Con 1]
+- [Con 2]
+
+**Implementation complexity:** [Low/Medium/High]
+**Team familiarity:** [Low/Medium/High]
+**Fit for our use case:** [High/Medium/Low]
+
+### Option 2: [Name]
+
+[Same structure]
+
+### Option 3: [Name]
+
+[Same structure]
+
+---
+
+## Comparison Matrix
+
+| Criteria | Option 1 | Option 2 | Option 3 |
+|----------|----------|----------|----------|
+| Performance | ⭐⭐⭐ | ⭐⭐ | ⭐⭐⭐ |
+| Complexity | ⭐⭐ | ⭐⭐⭐ | ⭐ |
+| Team fit | ⭐⭐⭐ | ⭐ | ⭐⭐ |
+| Maintenance | ⭐⭐ | ⭐⭐⭐ | ⭐⭐ |
+
+---
+
+## Recommendations
+
+### Primary Recommendation
+
+[Recommended approach with rationale]
+
+### Alternative Approach
+
+[Backup option if primary doesn't work]
+
+---
+
+## Open Questions
+
+- [Question for specification phase]
+- [Decision that needs stakeholder input]
+
+---
+
+## Sources (deep research only)
+
+| # | URL | Type | Reliability | Key Finding |
+|---|-----|------|-------------|-------------|
+| 1 | [url] | [Official docs / Benchmark / Blog / Discussion] | [High/Medium/Low] | [finding] |
+
+---
+
+## Confidence Assessment (deep research only)
+
+**Overall confidence:** [High/Medium/Low]
+**Reasoning:** [Why this confidence level]
+**Gaps:** [What we still don't know]
+**Suggested spike:** [If Low confidence — describe a 2-4h prototype to validate]
+
+---
+
+## Next Steps
+
+1. Review findings with team
+2. Proceed to `/specify` to define requirements
+3. Address open questions before proceeding
+
+---
+
+*Research completed with SDD Multi-Agent OpenCode*

package/.sdd/templates/roadmap-template.json

@@ -0,0 +1,29 @@
+{
+  "version": "1.0.0",
+  "project": {
+    "id": "[project-id]",
+    "title": "[Project Title]",
+    "description": "[Project Description]",
+    "sddVersion": "1.0.0",
+    "created": "[date]",
+    "status": "active",
+    "complexity": "medium"
+  },
+  "columns": {
+    "todo": { "title": "To Do", "order": 0 },
+    "in-progress": { "title": "In Progress", "order": 1 },
+    "review": { "title": "Review", "order": 2 },
+    "done": { "title": "Done", "order": 3 }
+  },
+  "tasks": [],
+  "epics": [],
+  "dag": {
+    "roots": [],
+    "parallelGroups": []
+  },
+  "statistics": {
+    "totalTasks": 0,
+    "completedTasks": 0,
+    "completionPercentage": 0
+  }
+}

package/.sdd/templates/roadmap-template.md

@@ -0,0 +1,66 @@
+# Project Roadmap: [Project Title]
+
+**Project ID:** [project-id]
+**Status:** Active
+**Complexity:** [Simple/Medium/Complex/Enterprise]
+**Created:** [date]
+
+---
+
+## Kanban Board
+
+### To Do
+| Task | Epic | Priority | Dependencies |
+|------|------|----------|-------------|
+| | | | |
+
+### In Progress
+| Task | Epic | Priority | Started |
+|------|------|----------|---------|
+| | | | |
+
+### Review
+| Task | Epic | Reviewer | Status |
+|------|------|----------|--------|
+| | | | |
+
+### Done
+| Task | Epic | Completed | Notes |
+|------|------|-----------|-------|
+| | | | |
+
+---
+
+## Epic Details
+
+### Epic 1: [Epic Name]
+- Task 1.1: [Description]
+- Task 1.2: [Description]
+
+### Epic 2: [Epic Name]
+- Task 2.1: [Description]
+
+---
+
+## Execution Commands
+
+```bash
+# Execute all tasks in parallel
+/execute-parallel [project-id] --until-finish
+
+# Execute single task
+/execute-task [task-id]
+
+# Resume after interruption
+/execute-parallel [project-id] --resume
+```
+
+---
+
+## Progress
+
+- Total: X | Done: Y (Z%) | In Progress: A | Blocked: B
+
+---
+
+*Roadmap created with SDD Multi-Agent OpenCode*