@iamnishankhan/opencode-kit-grok 1.0.0

package/kit/.opencode/commands/plan.md

@@ -0,0 +1,89 @@
+---
+description: Create project plan using project-planner agent. No code writing - only plan file generation.
+agent: project-planner
+---
+# /plan - Project Planning Mode
+
+$ARGUMENTS
+
+---
+
+## 🔴 CRITICAL RULES
+
+1. **NO CODE WRITING** - This command creates plan file only
+2. **Use project-planner agent** - NOT OpenCode kit Agent's native Plan mode
+3. **Socratic Gate** - Ask clarifying questions before planning
+4. **Dynamic Naming** - Plan file named based on task
+
+---
+
+## Task
+
+Delegate to the `@project-planner` subagent (or switch agent) with this context:
+
+```
+CONTEXT:
+- User Request: $ARGUMENTS
+- Mode: PLANNING ONLY (no code)
+- Output: {task-slug}.md in project root (dynamic naming)
+
+NAMING RULES:
+1. Extract 2-3 key words from request
+2. Lowercase, hyphen-separated
+3. Max 30 characters
+4. Example: "e-commerce cart" → ecommerce-cart.md
+
+RULES:
+1. Follow project-planner.md Phase -1 (Context Check)
+2. Follow project-planner.md Phase 0 (Socratic Gate)
+3. Create {slug}.md with task breakdown
+4. DO NOT write any code files
+5. REPORT the exact file name created
+```
+
+---
+
+## Expected Output
+
+| Deliverable | Location |
+|-------------|----------|
+| Project Plan | `{task-slug}.md` in project root |
+| Task Breakdown | Inside plan file |
+| Agent Assignments | Inside plan file |
+| Verification Checklist | Phase X in plan file |
+
+---
+
+## After Planning
+
+Tell user:
+```
+[OK] Plan created: {slug}.md in project root
+
+Next steps:
+- Review the plan
+- Run `/create` to start implementation
+- Or modify plan manually
+```
+
+---
+
+## Naming Examples
+
+| Request | Plan File |
+|---------|-----------|
+| `/plan e-commerce site with cart` | `ecommerce-cart.md` |
+| `/plan mobile app for fitness` | `fitness-app.md` |
+| `/plan add dark mode feature` | `dark-mode.md` |
+| `/plan fix authentication bug` | `auth-fix.md` |
+| `/plan SaaS dashboard` | `saas-dashboard.md` |
+
+---
+
+## Usage
+
+```
+/plan e-commerce site with cart
+/plan mobile app for fitness tracking
+/plan SaaS dashboard with analytics
+```

package/kit/.opencode/commands/preview.md

@@ -0,0 +1,80 @@
+---
+description: Preview server start, stop, and status check. Local development server management.
+---
+# /preview - Preview Management
+
+$ARGUMENTS
+
+---
+
+## Task
+
+Manage preview server: start, stop, status check.
+
+### Commands
+
+```
+/preview           - Show current status
+/preview start     - Start server
+/preview stop      - Stop server
+/preview restart   - Restart
+/preview check     - Health check
+```
+
+---
+
+## Usage Examples
+
+### Start Server
+```
+/preview start
+
+Response:
+🚀 Starting preview...
+   Port: 3000
+   Type: Next.js
+
+✅ Preview ready!
+   URL: http://localhost:3000
+```
+
+### Status Check
+```
+/preview
+
+Response:
+=== Preview Status ===
+
+🌐 URL: http://localhost:3000
+📁 Project: C:/projects/my-app
+🏷️ Type: nextjs
+💚 Health: OK
+```
+
+### Port Conflict
+```
+/preview start
+
+Response:
+⚠️ Port 3000 is in use.
+
+Options:
+1. Start on port 3001
+2. Close app on 3000
+3. Specify different port
+
+Which one? (default: 1)
+```
+
+---
+
+## Technical
+
+Auto preview uses `auto_preview.py` script:
+
+```bash
+python .opencode/scripts/auto_preview.py start [port]
+python .opencode/scripts/auto_preview.py stop
+python .opencode/scripts/auto_preview.py status
+```
+

package/kit/.opencode/commands/remember.md

@@ -0,0 +1,67 @@
+---
+description: Save information to persistent memory for cross-session recall. Stores preferences, conventions, decisions, and context.
+agent: orchestrator
+---
+# /remember — Persistent Memory Management
+
+$ARGUMENTS
+
+---
+
+## 🔴 CRITICAL RULES
+
+1. **Load memory-system skill** — Read `.opencode/skills/memory-system/SKILL.md` first
+2. **Never auto-delete memories** — Always ask user before pruning
+3. **Keep index under 200 lines** — Warn if approaching limit
+4. **Distill, don't copy** — Save insights, not full conversations
+
+---
+
+## Task
+
+Use the `memory-system` skill to save information:
+
+```
+CONTEXT:
+- User wants to remember: $ARGUMENTS
+- Memory location: .opencode/memory/
+
+WORKFLOW:
+1. CLASSIFY the information type: user | feedback | project | reference
+2. CHECK if relevant topic file exists in .opencode/memory/
+3. SAVE to appropriate topic file (create if needed)
+4. UPDATE .opencode/memory/MEMORY.md index with one-line pointer
+5. CONFIRM to user what was saved
+
+RULES:
+1. Follow memory-system/SKILL.md taxonomy
+2. Keep index entries under 150 characters
+3. Topic files must have frontmatter (type, created, updated)
+4. Don't save information derivable from code
+5. Don't save temporary debug context
+```
+
+---
+
+## Expected Output
+
+```
+[OK] Saved to memory
+
+Type: [user/feedback/project/reference]
+File: .opencode/memory/[topic-file].md
+Entry: [one-line summary of what was saved]
+
+This will be available in future sessions.
+```
+
+---
+
+## Usage Examples
+
+```
+/remember I prefer using bun instead of npm
+/remember Our API uses JWT with httpOnly cookies
+/remember The production server is at api.example.com:8080
+/remember I like concise responses with tables
+```

package/kit/.opencode/commands/status.md

@@ -0,0 +1,86 @@
+---
+description: Display agent and project status. Progress tracking and status board.
+agent: orchestrator
+---
+# /status - Show Status
+
+$ARGUMENTS
+
+---
+
+## Task
+
+Show current project and agent status.
+
+### What It Shows
+
+1. **Project Info**
+   - Project name and path
+   - Tech stack
+   - Current features
+
+2. **Agent Status Board**
+   - Which agents are running
+   - Which tasks are completed
+   - Pending work
+
+3. **File Statistics**
+   - Files created count
+   - Files modified count
+
+4. **Preview Status**
+   - Is server running
+   - URL
+   - Health check
+
+---
+
+## Example Output
+
+```
+=== Project Status ===
+
+📁 Project: my-ecommerce
+📂 Path: C:/projects/my-ecommerce
+🏷️ Type: nextjs-ecommerce
+📊 Status: active
+
+🔧 Tech Stack:
+   Framework: next.js
+   Database: postgresql
+   Auth: clerk
+   Payment: stripe
+
+✅ Features (5):
+   • product-listing
+   • cart
+   • checkout
+   • user-auth
+   • order-history
+
+⏳ Pending (2):
+   • admin-panel
+   • email-notifications
+
+📄 Files: 73 created, 12 modified
+
+=== Agent Status ===
+
+✅ database-architect → Completed
+✅ backend-specialist → Completed
+🔄 frontend-specialist → Dashboard components (60%)
+⏳ test-engineer → Waiting
+
+=== Preview ===
+
+🌐 URL: http://localhost:3000
+💚 Health: OK
+```
+
+---
+
+## Technical
+
+Status uses these scripts:
+- `python .opencode/scripts/session_manager.py status`
+- `python .opencode/scripts/auto_preview.py status`

package/kit/.opencode/commands/test.md

@@ -0,0 +1,143 @@
+---
+description: Test generation and test running command. Creates and executes tests for code.
+---
+# /test - Test Generation and Execution
+
+$ARGUMENTS
+
+---
+
+## Purpose
+
+This command generates tests, runs existing tests, or checks test coverage.
+
+---
+
+## Sub-commands
+
+```
+/test                - Run all tests
+/test [file/feature] - Generate tests for specific target
+/test coverage       - Show test coverage report
+/test watch          - Run tests in watch mode
+```
+
+---
+
+## Behavior
+
+### Generate Tests
+
+When asked to test a file or feature:
+
+1. **Analyze the code**
+   - Identify functions and methods
+   - Find edge cases
+   - Detect dependencies to mock
+
+2. **Generate test cases**
+   - Happy path tests
+   - Error cases
+   - Edge cases
+   - Integration tests (if needed)
+
+3. **Write tests**
+   - Use project's test framework (Jest, Vitest, etc.)
+   - Follow existing test patterns
+   - Mock external dependencies
+
+---
+
+## Output Format
+
+### For Test Generation
+
+```markdown
+## 🧪 Tests: [Target]
+
+### Test Plan
+| Test Case | Type | Coverage |
+|-----------|------|----------|
+| Should create user | Unit | Happy path |
+| Should reject invalid email | Unit | Validation |
+| Should handle db error | Unit | Error case |
+
+### Generated Tests
+
+`tests/[file].test.ts`
+
+[Code block with tests]
+
+---
+
+Run with: `npm test`
+```
+
+### For Test Execution
+
+```
+🧪 Running tests...
+
+✅ auth.test.ts (5 passed)
+✅ user.test.ts (8 passed)
+❌ order.test.ts (2 passed, 1 failed)
+
+Failed:
+  ✗ should calculate total with discount
+    Expected: 90
+    Received: 100
+
+Total: 15 tests (14 passed, 1 failed)
+```
+
+---
+
+## Examples
+
+```
+/test src/services/auth.service.ts
+/test user registration flow
+/test coverage
+/test fix failed tests
+```
+
+---
+
+## Test Patterns
+
+### Unit Test Structure
+
+```typescript
+describe('AuthService', () => {
+  describe('login', () => {
+    it('should return token for valid credentials', async () => {
+      // Arrange
+      const credentials = { email: 'test@test.com', password: 'pass123' };
+      
+      // Act
+      const result = await authService.login(credentials);
+      
+      // Assert
+      expect(result.token).toBeDefined();
+    });
+
+    it('should throw for invalid password', async () => {
+      // Arrange
+      const credentials = { email: 'test@test.com', password: 'wrong' };
+      
+      // Act & Assert
+      await expect(authService.login(credentials)).rejects.toThrow('Invalid credentials');
+    });
+  });
+});
+```
+
+---
+
+## Key Principles
+
+- **Test behavior not implementation**
+- **One assertion per test** (when practical)
+- **Descriptive test names**
+- **Arrange-Act-Assert pattern**
+- **Mock external dependencies**

package/kit/.opencode/commands/verify.md

@@ -0,0 +1,71 @@
+---
+description: Verify code changes work by running them. Proves through execution, not just inspection.
+---
+# /verify — Prove Code Works
+
+$ARGUMENTS
+
+---
+
+## 🔴 CRITICAL RULES
+
+1. **Load verify-changes skill** — Read `.opencode/skills/verify-changes/SKILL.md` first
+2. **Execute, don't inspect** — Run the code, don't just read it
+3. **Report evidence** — Show actual output, not assumptions
+4. **Cover edge cases** — Test error paths, not just happy path
+
+---
+
+## Task
+
+Use the `verify-changes` skill to prove code works:
+
+```
+CONTEXT:
+- What to verify: $ARGUMENTS
+- If empty: verify the most recent code changes in this session
+
+WORKFLOW:
+1. IDENTIFY what changed (files, functions, behavior)
+2. DETERMINE verification method (build, test, run, curl)
+3. EXECUTE verification commands
+4. REPORT evidence of success or failure
+5. FLAG anything that couldn't be verified automatically
+
+RULES:
+1. Follow verify-changes/SKILL.md protocol
+2. "It should work" is NOT verification — run it
+3. Test error paths, not just success paths
+4. Report with actual command output as evidence
+```
+
+---
+
+## Expected Output
+
+```
+## Verification Report
+
+### Changes Verified
+- [file/change 1]: ✅ Pass
+- [file/change 2]: ✅ Pass
+
+### Evidence
+- Build: ✅ Compiled without errors
+- Tests: ✅ [N]/[N] passing
+- Runtime: ✅ [specific verification result]
+
+### Not Verified
+- [anything that needs manual testing]
+```
+
+---
+
+## Usage Examples
+
+```
+/verify
+/verify the login endpoint handles expired tokens
+/verify build passes after refactoring
+/verify the new component renders correctly
+```

package/kit/.opencode/memory/MEMORY.md

@@ -0,0 +1,6 @@
+# Memory Index
+
+## Project
+- [project] Always create a new dedicated branch for major code changes → project-conventions.md
+- [project] OpenCode kit only supports Gemini CLI and OpenCode (not other AI coding tools) → project-conventions.md
+- [project] Component metadata uses SemVer while toolkit releases use CalVer → tech-decisions.md

package/kit/.opencode/memory/feedback-history.md

@@ -0,0 +1,9 @@
+---
+type: feedback
+created: 2026-07-18
+updated: 2026-07-18
+---
+
+# Feedback History
+
+No durable corrective feedback has been recorded yet.

package/kit/.opencode/memory/project-conventions.md

@@ -0,0 +1,16 @@
+---
+type: project
+created: 2026-05-25
+updated: 2026-07-12
+---
+
+# Project Conventions
+
+## Git Workflow
+- Always create a new dedicated branch for major code changes.
+- Branch name format should follow: `feature/[task-slug]` or `fix/[bug-slug]`.
+
+## Supported AI platforms (OpenCode kit)
+- OpenCode kit **only supports Gemini CLI and OpenCode**.
+- Do not claim compatibility with Claude Code, Cursor, Copilot, Windsurf, or other assistants unless the user explicitly expands scope.
+- Copy on the website, docs, FAQ, README, and marketing should describe OpenCode kit as a toolkit for Gemini CLI / OpenCode-style agent setups.

package/kit/.opencode/memory/tech-decisions.md

@@ -0,0 +1,10 @@
+---
+type: project
+created: 2026-07-18
+updated: 2026-07-18
+---
+
+# Technical Decisions
+
+- Component metadata uses SemVer while the toolkit release keeps CalVer.
+- `manifest.json` and `manifest.lock.json` must remain synchronized with component frontmatter.

package/kit/.opencode/memory/user-preferences.md

@@ -0,0 +1,9 @@
+---
+type: user
+created: 2026-07-18
+updated: 2026-07-18
+---
+
+# User Preferences
+
+No durable user preferences have been recorded yet.

package/kit/.opencode/opencode.json

@@ -0,0 +1,15 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "default_agent": "orchestrator",
+  "instructions": [
+    "AGENTS.md"
+  ],
+  "agent": {
+    "orchestrator": {
+      "mode": "primary"
+    },
+    "project-planner": {
+      "mode": "primary"
+    }
+  }
+}

package/kit/.opencode/scripts/README.md

@@ -0,0 +1,95 @@
+# AG Kit Runtime Scripts
+
+## Entry points
+
+### `validate_kit.py`
+
+Self-validates the `.opencode/` package. It checks JSON, strict SemVer frontmatter, workflow/agent/skill references, manifest and lock synchronization, generated dependency docs, memory contracts, local Markdown links, Python syntax, referenced script paths, and documented inventory counts.
+
+```bash
+python .opencode/scripts/validate_kit.py
+python .opencode/scripts/validate_kit.py --json
+```
+
+
+### `generate_manifest.py`
+
+Builds deterministic `manifest.json` and `manifest.lock.json` files from component frontmatter. Use `--check` in CI to fail on registry drift.
+
+```bash
+python .opencode/scripts/generate_manifest.py
+python .opencode/scripts/generate_manifest.py --check
+```
+
+### `dependency_graph.py`
+
+Builds `DEPENDENCY_GRAPH.md` from workflow and agent dependencies. Use `--check` to verify that the generated graph is current.
+
+```bash
+python .opencode/scripts/dependency_graph.py
+python .opencode/scripts/dependency_graph.py --check
+```
+
+### `checklist.py`
+
+Runs the fast project validation path. URL checks are automatically skipped when `--url` is not supplied.
+
+```bash
+python .opencode/scripts/checklist.py .
+python .opencode/scripts/checklist.py . --url http://localhost:3000
+python .opencode/scripts/checklist.py . --report .opencode/reports/checklist.json
+```
+
+### `verify_all.py`
+
+Runs the broad release suite. `--no-runtime` excludes Lighthouse and Playwright; `--no-e2e` excludes Playwright only.
+
+```bash
+python .opencode/scripts/verify_all.py . --no-runtime
+python .opencode/scripts/verify_all.py . --url http://localhost:3000 --report verification.json
+```
+
+### `session_manager.py`
+
+Prints project type, package metadata, feature hints, and file counts.
+
+```bash
+python .opencode/scripts/session_manager.py status .
+```
+
+### `auto_preview.py`
+
+Starts, stops, or inspects a detected local preview server.
+
+```bash
+python .opencode/scripts/auto_preview.py start 3000
+python .opencode/scripts/auto_preview.py status
+python .opencode/scripts/auto_preview.py stop
+```
+
+## Runtime prerequisites
+
+Most scripts use only the Python standard library. Optional checks require the corresponding project tools:
+
+- Lighthouse: `npm install -g lighthouse`
+- Playwright: `pip install playwright && playwright install chromium`
+- Node lint/test commands: project package manager and configured scripts
+- Python lint/test commands: project-configured tools such as Ruff, MyPy, or pytest
+
+Missing URL-based tools produce a failed runtime check rather than a false pass. Missing non-applicable build outputs are reported as skipped/pass with an explanatory message.
+
+## Exit-code contract
+
+- `0`: check passed or was not applicable
+- `1`: findings met the configured failure threshold
+- `2`: invalid command usage or missing input path
+
+The master runners use subprocess exit codes as the source of truth and can emit a full JSON report with commands, durations, stdout, stderr, and status.
+
+## Regression tests
+
+Toolkit scripts include regression tests for self-validation, component SemVer, manifest/lock integrity, dependency graph synchronization, memory contracts, security scanning, dependency and bundle analysis, and toolkit-root discovery.
+
+```bash
+python -m unittest discover -s .opencode/scripts/tests -v
+```