cc-codeconductor 0.2.10 → 0.3.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cc-codeconductor",
-  "version": "0.2.10",
+  "version": "0.3.1",
   "description": "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
   "keywords": [
     "ai",

package/presets/agy/AGENTS.md

@@ -6,6 +6,26 @@ This file configures CodeConductor for **Google Antigravity CLI (agy)** and Anti
 
 ---
 
+## Behavioral Discipline
+
+These principles apply to **all agents** in every workflow. They reduce common
+LLM coding mistakes and bias toward caution over speed.
+
+1. **Think Before Coding** — State assumptions explicitly. If uncertain, ask. If
+   multiple interpretations exist, present them — don't pick silently. If a
+   simpler approach exists, say so.
+2. **Simplicity First** — Minimum code that solves the problem. No features
+   beyond what was asked. No abstractions for single-use code. No speculative
+   "flexibility." Ask: "Would a senior engineer say this is overcomplicated?"
+3. **Surgical Changes** — Touch only what you must. Don't "improve" adjacent
+   code. Match existing style. Remove only what YOUR changes made unused. Every
+   changed line must trace directly to the user's request.
+4. **Goal-Driven Execution** — Transform tasks into verifiable goals with
+   success criteria. For multi-step tasks, state a plan with verification
+   checks. Loop until verified.
+
+---
+
 ## Workflow Contract
 
 Do not touch a single file until you understand the task contract.
@@ -101,8 +121,13 @@ When multiple signals apply, take the highest risk level. Do not average.
 1. Validate the Task Card before doing anything else.
 2. Classify the risk level using the table above.
 3. Select and document the agent route.
-4. Surface blockers rather than working around them.
-5. Declare completion only when all Deliverables are produced and verified.
+4. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+5. Surface blockers rather than working around them.
+6. Declare completion only when all Deliverables are produced and verified.
 
 **Task Card validation — required fields before routing:**
 - Title (short description, max 80 chars)
@@ -263,6 +288,10 @@ High-risk checkpoint: [yes | no — if yes, describe what triggers a stop]
 3. Read the target files.
 4. Verify tests pass before starting.
 
+**Surgical Changes Rules:**
+- Modify ONLY planned files. Do not improve adjacent code, comments, or formatting.
+- Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
+
 **Implementation Summary format:**
 ```markdown
 ## Implementation Summary
@@ -323,6 +352,10 @@ High-risk checkpoint: [yes | no — if yes, describe what triggers a stop]
 
 **Model:** `{{MODEL_GEMINI}}`
 
+**Review Axes & Gates:**
+- **Simplicity Gate**: Flag overcomplicated/speculative code. Ask: "Would a senior engineer say this is overbuilt?"
+- **Surgical Changes**: Verify no adjacent or unrelated code was changed.
+
 **Review Report format:**
 ```markdown
 ## Review Report
@@ -351,4 +384,15 @@ High-risk checkpoint: [yes | no — if yes, describe what triggers a stop]
 
 **Model:** `{{MODEL_GEMINI}}`
 
+---
+
+## Loop Agent & Monorepos
+
+### Loop Agent Mode (Intense Workflows)
+- If tests fail, run the cycle: Implementer (applies fix) -> Tester (verifies suite) up to 3 times.
+- If still failing, stop and report back with findings.
+
+### Monorepo Workspaces
+- Focus operations strictly within the specified sub-package or workspace directory in the Task Card scope. Do not modify files or run commands outside this package directory.
+
 <!-- CODECONDUCTOR:END managed -->

package/presets/claude/CLAUDE.md

@@ -6,6 +6,24 @@ This is a framework, not a prompt collection. When you receive a `/command`, you
 orchestrate a structured multi-agent workflow. Each step is executed by a
 specialized role. Roles do not overlap. Steps are not skipped.
 
+## Behavioral Discipline
+
+These principles apply to **all agents** in every workflow. They reduce common
+LLM coding mistakes and bias toward caution over speed.
+
+1. **Think Before Coding** — State assumptions explicitly. If uncertain, ask. If
+   multiple interpretations exist, present them — don't pick silently. If a
+   simpler approach exists, say so.
+2. **Simplicity First** — Minimum code that solves the problem. No features
+   beyond what was asked. No abstractions for single-use code. No speculative
+   "flexibility." Ask: "Would a senior engineer say this is overcomplicated?"
+3. **Surgical Changes** — Touch only what you must. Don't "improve" adjacent
+   code. Match existing style. Remove only what YOUR changes made unused. Every
+   changed line must trace directly to the user's request.
+4. **Goal-Driven Execution** — Transform tasks into verifiable goals with
+   success criteria. For multi-step tasks, state a plan with verification
+   checks. Loop until verified.
+
 ---
 
 ## Core Terminology
@@ -45,8 +63,13 @@ verified.
 1. Validate the Task Card before doing anything else.
 2. Select the routing path based on the Routing Policy.
 3. Execute the correct agent sequence.
-4. Surface blockers rather than working around them.
-5. Declare completion only when all Deliverables are produced and verified.
+4. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+5. Surface blockers rather than working around them.
+6. Declare completion only when all Deliverables are produced and verified.
 
 **Task Card validation — required fields before routing:**
 
@@ -302,6 +325,7 @@ branch, declare done before running tests.
 - **No scope creep.** If the plan says "add one endpoint," add one endpoint.
 - **Run tests before declaring done.** If any test fails, investigate and fix
   before completing.
+- **Surgical Changes.** Modify ONLY planned files. Do not improve adjacent code, comments, or formatting. Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
 
 **Implementation Summary format:**
 
@@ -400,6 +424,8 @@ code.
 | Error handling | Are failure cases handled explicitly and safely?                 |
 | Test coverage  | Do the tests verify all acceptance criteria?                     |
 | Technical debt | Does the implementation introduce debt without acknowledging it? |
+| Simplicity     | Flag overcomplicated or speculative code (overbuilt patterns).   |
+| Surgical       | Verify that NO adjacent or unrelated code/comments were changed. |
 
 **Finding categories:**
 
@@ -564,6 +590,27 @@ dependencies, apply `.claude/skills/python-fastapi-stack/SKILL.md`.
 When the active task touches SQLAlchemy models, queries, sessions, bulk
 operations, or Alembic migrations, apply `.claude/skills/sqlalchemy/SKILL.md`.
 
+When the active task touches Next.js components, Server Actions, or App Router layouts,
+apply `.claude/skills/nextjs-typescript/SKILL.md`.
+
+When the active task touches Astro pages or configuration,
+apply `.claude/skills/astro/SKILL.md`.
+
+When the active task touches Android project files (Kotlin, Compose, Media3, Gradle),
+apply `.claude/skills/android/SKILL.md`.
+
+When the active task touches Laravel project files (Eloquent, blade, livewire, controllers, routes),
+apply `.claude/skills/laravel-specialist/SKILL.md`.
+
+When the active task touches PHP project files (PHPUnit, Composer, syntax, types),
+apply `.claude/skills/php-pro/SKILL.md`.
+
+When the active task touches backend security, authorization, or data verification,
+apply `.claude/skills/security/SKILL.md`.
+
+When the active task requires debugging frontend interactions or accessibility (a11y) checks,
+apply `.claude/skills/a11y-debugging/SKILL.md` and `.claude/skills/modern-web-guidance/SKILL.md`.
+
 When the user asks to create a Spring Boot feature (entity, service, controller,
 or tests), apply `.claude/skills/spring-boot-feature/SKILL.md`.
 
@@ -577,6 +624,19 @@ extending capabilities, apply `.claude/skills/find-skills/SKILL.md`.
 
 ---
 
+## Teammate & Loop Agent Rules
+
+### Teammate delegation (Presets supporting multi-teams)
+- Utilize parallel sub-agent execution by enabling `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` in `settings.json`.
+- Allocate tasks to specific teammates: use `sonnet` for Orchestrator and Architect, and delegate secondary tasks (e.g. testing, review, docs) to `haiku` to optimize token budgets.
+
+### Loop Agent Mode (Intense Workflows)
+- If tests or verifications fail, do not stop. Re-route the failure logs back to the Implementer teammate.
+- The workflow iterates: Implementer (applies fix) -> Tester (verifies suite).
+- Permit up to 3 self-correction iterations. If tests still fail, halt and escalate to the human with diagnostic details.
+
+---
+
 ## What Never Changes
 
 - Do not invoke the Implementer role without an accepted Technical Plan.

package/presets/claude/skills/android/SKILL.md

@@ -0,0 +1,119 @@
+---
+id: android
+version: 1.0.0
+name: Android + Kotlin (Jetpack Compose & Media3)
+description: >
+  Provides expert knowledge for building modern native Android apps using Kotlin, Jetpack Compose, Material Design 3, MVI architecture, Hilt dependency injection, and Media3/ExoPlayer.
+
+user-invokable: true
+license: MIT
+metadata:
+  author: lgzarturo
+  category: mobile
+
+compatibility:
+  tools: [claude, codex, gemini, agy, opencode]
+  stacks:
+    languages: [kotlin, java]
+    frameworks: [android]
+
+risk:
+  level: medium
+  can_execute_shell: true
+  can_modify_files: true
+  requires_network: false
+
+inputs: []
+
+outputs: []
+
+quality:
+  reviewed_by: codeconductor-core
+  version: 0.1.0
+---
+
+# Android + Kotlin (Jetpack Compose & Media3)
+
+This playbook defines the architecture, UI design system, performance guidelines, and testing strategy for native Android applications.
+
+---
+
+## 1. Lead Architect & Modularization
+
+### Architecture (MVI / MVVM with Clean Architecture)
+- Prefer **MVI (Model-View-Intent)** for state management. Ensure a strict unidirectional data flow:
+  - **UiState**: Single source of truth for the UI state.
+  - **UiIntent**: Actions initiated by the user or system.
+  - **UiEffect**: One-time events (navigation, toasts, snackbars).
+- Separate the project into clean logical modules:
+  - `app`: Application entry point, launcher activity, global dependency injection configuration.
+  - `core`: Shared resources, network layer, media playback logic (ExoPlayer/Media3), storage.
+  - `feature`: Individual business features (isolated and independent of other features).
+
+### Dependency Injection (Hilt)
+- Annotate the Application class with `@HiltAndroidApp`.
+- Annotate Activities and Fragments with `@AndroidEntryPoint`.
+- Use constructor injection for ViewModels with `@HiltViewModel`.
+
+---
+
+## 2. Jetpack Compose UI/UX
+
+### Recomposition & State Management
+- Consume `StateFlow` from ViewModels safely using `collectAsStateWithLifecycle()` to respect the activity lifecycle.
+- Keep data models immutable. Mark configuration classes with `@Immutable` or `@Stable` to prevent redundant recompositions.
+- Use `contentType` and `key` in `LazyColumn` and `LazyRow` to optimize item recycling and rendering performance.
+- Avoid fixed hardcoded margins. Apply `WindowInsets` to support modern edge-to-edge screens.
+
+---
+
+## 3. Performance & Multimedia (Media3 / ExoPlayer)
+
+### Playback & Services
+- Run `ExoPlayer` / `Media3` inside a robust `Foreground Service` (using `MediaSessionService`) to ensure playback continues when the app is in the background.
+- Clean up resources: release player instances in `onDestroy` or when the service is stopped.
+- Control wake locks strictly to avoid draining the user's battery when playback is paused.
+
+### Kotlin Coroutines & Threading
+- Always inject `CoroutineDispatcher` instances instead of hardcoding them:
+  - `Dispatchers.IO`: Database access, network operations, file reading.
+  - `Dispatchers.Default`: CPU-intensive operations (parsing JSON, filtering large lists).
+  - `Dispatchers.Main`: UI modifications and light interactions.
+
+### R8 & Resource Optimization
+- Enable shrinking and obfuscation in production builds:
+  - `isMinifyEnabled = true`
+  - `isShrinkResources = true`
+- Convert all static images to the modern `WebP` format to minimize the application binary size.
+
+---
+
+## 4. Quality Assurance & Automated Testing
+
+### Unit Testing
+- Use JUnit 5 and MockK for mocking dependencies.
+- Test ViewModels and Reducers by asserting StateFlow updates. Use `Turbine` to easily test Kotlin Flows.
+- Mock all multimedia/ExoPlayer components to avoid loading actual audio/video resources in unit tests.
+
+### UI Testing
+- Create UI tests using Compose test rules: `createComposeRule()` or `createAndroidComposeRule<MainActivity>()`.
+- Assert correct rendering, visibility states, and user interactions without executing real network calls.
+
+---
+
+## 5. Key Gradle & ADB Commands
+
+Use these commands for building, checking code style, running tests, and profiling performance:
+
+| Command | Action |
+| ------- | ------ |
+| `./gradlew init` | Initialize a new Gradle project structure. |
+| `./gradlew app:dependencies` | List all dependencies of the application module. |
+| `./gradlew assembleDebug` | Validate compilation and generate debug APK. |
+| `./gradlew ktlintCheck` | Run KtLint check to enforce Kotlin style guidelines. |
+| `./gradlew lintDebug` | Run Android Lint tool to inspect code quality and UI issues. |
+| `./gradlew testDebugUnitTest` | Run unit tests for debug build variant. |
+| `./gradlew connectedAndroidTest` | Run instrumented UI tests on connected emulator or device. |
+| `./gradlew assembleRelease` | Generate release build variant with R8 optimizations. |
+| `adb shell dumpsys batterystats` | Profile system battery consumption metrics. |
+| `adb shell am dumpheap <package> heap.hprof` | Dump application heap memory file for profiling. |

package/presets/claude/skills/laravel-specialist/SKILL.md

@@ -0,0 +1,264 @@
+---
+name: laravel-specialist
+description: Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers, implementing Sanctum auth flows, building Livewire components, optimising Eloquent queries, or writing Pest/PHPUnit tests for Laravel features.
+license: MIT
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.1.0"
+  domain: backend
+  triggers: Laravel, Eloquent, PHP framework, Laravel API, Artisan, Blade templates, Laravel queues, Livewire, Laravel testing, Sanctum, Horizon
+  role: specialist
+  scope: implementation
+  output-format: code
+  related-skills: fullstack-guardian, test-master, devops-engineer, security-reviewer
+---
+
+# Laravel Specialist
+
+Senior Laravel specialist with deep expertise in Laravel 10+, Eloquent ORM, and modern PHP 8.2+ development.
+
+## Core Workflow
+
+1. **Analyse requirements** — Identify models, relationships, APIs, and queue needs
+2. **Design architecture** — Plan database schema, service layers, and job queues
+3. **Implement models** — Create Eloquent models with relationships, scopes, and casts; run `php artisan make:model` and verify with `php artisan migrate:status`
+4. **Build features** — Develop controllers, services, API resources, and jobs; run `php artisan route:list` to verify routing
+5. **Test thoroughly** — Write feature and unit tests; run `php artisan test` before considering any step complete (target >85% coverage)
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| Eloquent ORM | `references/eloquent.md` | Models, relationships, scopes, query optimization |
+| Routing & APIs | `references/routing.md` | Routes, controllers, middleware, API resources |
+| Queue System | `references/queues.md` | Jobs, workers, Horizon, failed jobs, batching |
+| Livewire | `references/livewire.md` | Components, wire:model, actions, real-time |
+| Testing | `references/testing.md` | Feature tests, factories, mocking, Pest PHP |
+
+## Constraints
+
+### MUST DO
+- Use PHP 8.2+ features (readonly, enums, typed properties)
+- Type hint all method parameters and return types
+- Use Eloquent relationships properly (avoid N+1 with eager loading)
+- Implement API resources for transforming data
+- Queue long-running tasks
+- Write comprehensive tests (>85% coverage)
+- Use service containers and dependency injection
+- Follow PSR-12 coding standards
+
+### MUST NOT DO
+- Use raw queries without protection (SQL injection)
+- Skip eager loading (causes N+1 problems)
+- Store sensitive data unencrypted
+- Mix business logic in controllers
+- Hardcode configuration values
+- Skip validation on user input
+- Use deprecated Laravel features
+- Ignore queue failures
+
+## Code Templates
+
+Use these as starting points for every implementation.
+
+### Eloquent Model
+
+```php
+<?php
+
+declare(strict_types=1);
+
+namespace App\Models;
+
+use Illuminate\Database\Eloquent\Factories\HasFactory;
+use Illuminate\Database\Eloquent\Model;
+use Illuminate\Database\Eloquent\Relations\BelongsTo;
+use Illuminate\Database\Eloquent\Relations\HasMany;
+use Illuminate\Database\Eloquent\SoftDeletes;
+
+final class Post extends Model
+{
+    use HasFactory, SoftDeletes;
+
+    protected $fillable = ['title', 'body', 'status', 'user_id'];
+
+    protected $casts = [
+        'status' => PostStatus::class, // backed enum
+        'published_at' => 'immutable_datetime',
+    ];
+
+    // Relationships — always eager-load via ::with() at call site
+    public function author(): BelongsTo
+    {
+        return $this->belongsTo(User::class, 'user_id');
+    }
+
+    public function comments(): HasMany
+    {
+        return $this->hasMany(Comment::class);
+    }
+
+    // Local scope
+    public function scopePublished(Builder $query): Builder
+    {
+        return $query->where('status', PostStatus::Published);
+    }
+}
+```
+
+### Migration
+
+```php
+<?php
+
+use Illuminate\Database\Migrations\Migration;
+use Illuminate\Database\Schema\Blueprint;
+use Illuminate\Support\Facades\Schema;
+
+return new class extends Migration
+{
+    public function up(): void
+    {
+        Schema::create('posts', function (Blueprint $table): void {
+            $table->id();
+            $table->foreignId('user_id')->constrained()->cascadeOnDelete();
+            $table->string('title');
+            $table->text('body');
+            $table->string('status')->default('draft');
+            $table->timestamp('published_at')->nullable();
+            $table->softDeletes();
+            $table->timestamps();
+        });
+    }
+
+    public function down(): void
+    {
+        Schema::dropIfExists('posts');
+    }
+};
+```
+
+### API Resource
+
+```php
+<?php
+
+declare(strict_types=1);
+
+namespace App\Http\Resources;
+
+use Illuminate\Http\Request;
+use Illuminate\Http\Resources\Json\JsonResource;
+
+final class PostResource extends JsonResource
+{
+    public function toArray(Request $request): array
+    {
+        return [
+            'id'           => $this->id,
+            'title'        => $this->title,
+            'body'         => $this->body,
+            'status'       => $this->status->value,
+            'published_at' => $this->published_at?->toIso8601String(),
+            'author'       => new UserResource($this->whenLoaded('author')),
+            'comments'     => CommentResource::collection($this->whenLoaded('comments')),
+        ];
+    }
+}
+```
+
+### Queued Job
+
+```php
+<?php
+
+declare(strict_types=1);
+
+namespace App\Jobs;
+
+use App\Models\Post;
+use Illuminate\Bus\Queueable;
+use Illuminate\Contracts\Queue\ShouldQueue;
+use Illuminate\Foundation\Bus\Dispatchable;
+use Illuminate\Queue\InteractsWithQueue;
+use Illuminate\Queue\SerializesModels;
+
+final class PublishPost implements ShouldQueue
+{
+    use Dispatchable, InteractsWithQueue, Queueable, SerializesModels;
+
+    public int $tries = 3;
+    public int $backoff = 60;
+
+    public function __construct(
+        private readonly Post $post,
+    ) {}
+
+    public function handle(): void
+    {
+        $this->post->update([
+            'status'       => PostStatus::Published,
+            'published_at' => now(),
+        ]);
+    }
+
+    public function failed(\Throwable $e): void
+    {
+        // Log or notify — never silently swallow failures
+        logger()->error('PublishPost failed', ['post' => $this->post->id, 'error' => $e->getMessage()]);
+    }
+}
+```
+
+### Feature Test (Pest)
+
+```php
+<?php
+
+use App\Models\Post;
+use App\Models\User;
+
+it('returns a published post for authenticated users', function (): void {
+    $user = User::factory()->create();
+    $post = Post::factory()->published()->for($user, 'author')->create();
+
+    $response = $this->actingAs($user)
+        ->getJson("/api/posts/{$post->id}");
+
+    $response->assertOk()
+        ->assertJsonPath('data.status', 'published')
+        ->assertJsonPath('data.author.id', $user->id);
+});
+
+it('queues a publish job when a draft is submitted', function (): void {
+    Queue::fake();
+    $user = User::factory()->create();
+    $post = Post::factory()->draft()->for($user, 'author')->create();
+
+    $this->actingAs($user)
+        ->postJson("/api/posts/{$post->id}/publish")
+        ->assertAccepted();
+
+    Queue::assertPushed(PublishPost::class, fn ($job) => $job->post->is($post));
+});
+```
+
+## Validation Checkpoints
+
+Run these at each workflow stage to confirm correctness before proceeding:
+
+| Stage | Command | Expected Result |
+|-------|---------|-----------------|
+| After migration | `php artisan migrate:status` | All migrations show `Ran` |
+| After routing | `php artisan route:list --path=api` | New routes appear with correct verbs |
+| After job dispatch | `php artisan queue:work --once` | Job processes without exception |
+| After implementation | `php artisan test --coverage` | >85% coverage, 0 failures |
+| Before PR | `./vendor/bin/pint --test` | PSR-12 linting passes |
+
+## Knowledge Reference
+
+Laravel 10+, Eloquent ORM, PHP 8.2+, API resources, Sanctum/Passport, queues, Horizon, Livewire, Inertia, Octane, Pest/PHPUnit, Redis, broadcasting, events/listeners, notifications, task scheduling
+
+[Documentation](https://jeffallan.github.io/claude-skills/skills/backend/laravel-specialist/)