ac-framework 1.6.0 → 1.8.0

package/framework/.codex/skills/microtask-decomposition/SKILL.md

@@ -0,0 +1,368 @@
+---
+name: microtask-decomposition
+description: Level 2+ task decomposition. Use when a single task from tasks.md is STILL too complex (affects 3+ files or requires multiple logic blocks). Breaks tasks into MICROTASKS (1 file/function each) for granular implementation. NOT for initial task breakdown - OpenSpec already does that.
+license: MIT
+metadata:
+  author: AC Framework
+  version: "1.0"
+---
+
+# Microtask Decomposition
+
+**Level 2+ Decomposition: From Tasks to Microtasks**
+
+Divide complex tasks from `tasks.md` into atomic, single-file microtasks for granular tracking and implementation.
+
+## ⚠️ CRITICAL: When to Use This Skill
+
+### Use microtask-decomposition when:
+- A single task from `tasks.md` affects **3+ files**
+- A task requires **multiple distinct logic blocks**
+- You need to **parallelize sub-task execution**
+- A task is estimated at **>2 hours** of work
+- The task has **internal dependencies** that can be sequenced
+
+### Do NOT use when:
+- Creating initial tasks (use `openspec-new-change` or `openspec-ff-change`)
+- Task affects only 1-2 files (implement directly)
+- Task is simple and straightforward
+
+### The Hierarchy:
+```
+Change (openspec-new-change)
+  └─> Tasks (tasks.md) - Level 1
+      └─> Microtasks (this skill) - Level 2+
+          └─> Implementation
+```
+
+---
+
+## Instructions
+
+### Step 1: Identify the Complex Task
+
+Select ONE task from `tasks.md` that meets decomposition criteria:
+- [ ] Affects 3+ files
+- [ ] Contains multiple distinct operations
+- [ ] Estimated effort >2 hours
+- [ ] Has internal sequential dependencies
+
+**Example complex task:**
+```markdown
+- [ ] Implement user authentication with login, signup, password reset, and email verification
+```
+→ This affects multiple files and operations = DECOMPOSE
+
+### Step 2: Analyze Task Components
+
+Break down the task into its atomic operations:
+
+1. **List all files touched**
+2. **List all functions/methods needed**
+3. **Identify data flow between components**
+4. **Mark dependencies** (what must happen before what)
+
+### Step 3: Create Microtasks
+
+Each microtask must be:
+- **Single file** (or 1-2 closely related files)
+- **Single purpose** (one function or cohesive set)
+- **Independently testable**
+- **< 1 hour** estimated effort
+- **Clear completion criteria**
+
+**Microtask format:**
+```yaml
+microtask:
+  id: "mt-[number]"
+  parent_task: "task-id-from-tasks.md"
+  name: "Brief descriptive name"
+  description: "What this microtask accomplishes"
+  files:
+    - path/to/single-file.ext
+  dependencies:
+    - "mt-[prerequisite]"
+  estimated_time: "30min"
+  acceptance_criteria:
+    - "Criterion 1"
+    - "Criterion 2"
+```
+
+### Step 4: Map Dependencies
+
+Create a dependency graph:
+```
+mt-1: Database schema
+  └─> mt-2: User model
+      ├─> mt-3: Login endpoint
+      ├─> mt-4: Signup endpoint
+      └─> mt-5: Password reset service
+          └─> mt-6: Email verification
+              └─> mt-7: Integration tests
+```
+
+### Step 5: Assign Execution Order
+
+Group microtasks into execution phases:
+
+**Phase 1** (Foundation - Sequential):
+- mt-1, mt-2
+
+**Phase 2** (Core Features - Parallel):
+- mt-3, mt-4 (both depend on Phase 1)
+
+**Phase 3** (Extended Features - Sequential):
+- mt-5 (depends on Phase 2)
+
+**Phase 4** (Integration):
+- mt-6, mt-7 (depends on Phase 3)
+
+---
+
+## Output Format
+
+```
+## Microtask Decomposition Summary
+
+**Parent Task**: [task description from tasks.md]
+**Task ID**: [task identifier]
+**Total Microtasks**: [N]
+**Estimated Total Time**: [X hours]
+**Execution Phases**: [N phases]
+
+---
+
+### Microtask List
+
+#### Phase 1: Foundation
+
+**mt-1: [Name]**
+- **Files**: `file.ext`
+- **Description**: What to implement
+- **Dependencies**: None
+- **Estimated**: 30min
+- **Acceptance Criteria**:
+  - [ ] Criterion 1
+  - [ ] Criterion 2
+
+**mt-2: [Name]**
+- **Files**: `file.ext`
+- **Description**: What to implement
+- **Dependencies**: mt-1
+- **Estimated**: 45min
+- **Acceptance Criteria**:
+  - [ ] Criterion 1
+
+#### Phase 2: Core Features (Parallel)
+
+**mt-3: [Name]**
+- **Files**: `file.ext`
+- **Description**: What to implement
+- **Dependencies**: mt-2
+- **Estimated**: 30min
+- **Acceptance Criteria**:
+  - [ ] Criterion 1
+
+[Continue for all phases...]
+
+---
+
+### Dependency Graph
+
+```
+[ASCII art showing dependency relationships]
+```
+
+---
+
+### Execution Plan
+
+**Phase 1** (Foundation - Do first):
+- [ ] mt-1
+- [ ] mt-2
+
+**Phase 2** (Core - Parallelizable):
+- [ ] mt-3 (depends: mt-2)
+- [ ] mt-4 (depends: mt-2)
+
+**Phase 3** (Extended - Sequential):
+- [ ] mt-5 (depends: mt-3, mt-4)
+
+**Phase 4** (Final):
+- [ ] mt-6 (depends: mt-5)
+- [ ] mt-7 (depends: mt-6)
+
+---
+
+### Parent Task Update
+
+After decomposition, update the parent task in `tasks.md`:
+
+```markdown
+- [ ] Implement user authentication [DECOMPOSED INTO MICROTASKS]
+  - [ ] Phase 1: Foundation
+    - [ ] mt-1: Database schema
+    - [ ] mt-2: User model
+  - [ ] Phase 2: Core Features
+    - [ ] mt-3: Login endpoint
+    - [ ] mt-4: Signup endpoint
+  - [ ] Phase 3: Extended Features
+    - [ ] mt-5: Password reset service
+    - [ ] mt-6: Email verification
+  - [ ] Phase 4: Integration
+    - [ ] mt-7: Integration tests
+```
+```
+
+---
+
+## Example
+
+### Parent Task (from tasks.md):
+```markdown
+- [ ] Build complete authentication system with login, signup, password reset, email verification, and session management
+```
+
+### Microtask Decomposition:
+
+```
+## Microtask Decomposition Summary
+
+**Parent Task**: Build complete authentication system
+**Total Microtasks**: 9
+**Estimated Total Time**: 6 hours
+**Execution Phases**: 4
+
+---
+
+### Microtask List
+
+#### Phase 1: Data Layer
+
+**mt-1: User Database Schema**
+- **Files**: `database/migrations/001_users.sql`
+- **Description**: Create users table with fields: id, email, password_hash, verified, created_at
+- **Dependencies**: None
+- **Estimated**: 20min
+- **Acceptance**: Migration runs, schema matches requirements
+
+**mt-2: User Model/Entity**
+- **Files**: `src/models/User.js`
+- **Description**: User class with methods: create(), findByEmail(), verify(), updatePassword()
+- **Dependencies**: mt-1
+- **Estimated**: 30min
+- **Acceptance**: All CRUD operations work, password hashing implemented
+
+#### Phase 2: Core Auth Endpoints (Parallel)
+
+**mt-3: Login Endpoint**
+- **Files**: `src/routes/auth/login.js`
+- **Description**: POST /api/auth/login - validate credentials, create session/JWT
+- **Dependencies**: mt-2
+- **Estimated**: 30min
+- **Acceptance**: Returns token on success, proper error on failure
+
+**mt-4: Signup Endpoint**
+- **Files**: `src/routes/auth/signup.js`
+- **Description**: POST /api/auth/signup - validate email, hash password, create user
+- **Dependencies**: mt-2
+- **Estimated**: 30min
+- **Acceptance**: Creates user, sends verification email
+
+#### Phase 3: Extended Features
+
+**mt-5: Password Reset Service**
+- **Files**: `src/services/passwordReset.js`, `src/routes/auth/reset.js`
+- **Description**: Generate reset tokens, send emails, validate tokens
+- **Dependencies**: mt-3, mt-4
+- **Estimated**: 45min
+- **Acceptance**: Token generation, email sending, token validation work
+
+**mt-6: Email Verification**
+- **Files**: `src/services/verification.js`, `src/routes/auth/verify.js`
+- **Description**: Send verification emails, verify tokens, update user status
+- **Dependencies**: mt-5
+- **Estimated**: 30min
+- **Acceptance**: Email sent, token verified, user marked verified
+
+**mt-7: Session Management**
+- **Files**: `src/middleware/session.js`, `src/services/session.js`
+- **Description**: Validate sessions/JWT, refresh tokens, logout
+- **Dependencies**: mt-3
+- **Estimated**: 40min
+- **Acceptance**: Sessions validated, refresh works, logout clears session
+
+#### Phase 4: UI & Integration
+
+**mt-8: Auth UI Components**
+- **Files**: `src/components/LoginForm.jsx`, `src/components/SignupForm.jsx`
+- **Description**: Forms with validation, error handling, loading states
+- **Dependencies**: mt-3, mt-4
+- **Estimated**: 60min
+- **Acceptance**: Forms work, validation feedback, API integration
+
+**mt-9: Auth Integration Tests**
+- **Files**: `tests/integration/auth.test.js`
+- **Description**: End-to-end tests for all auth flows
+- **Dependencies**: mt-6, mt-7, mt-8
+- **Estimated**: 45min
+- **Acceptance**: All flows tested, edge cases covered
+```
+
+---
+
+## Integration with OpenSpec
+
+### After Microtask Decomposition:
+
+1. **Update `tasks.md`** with microtask breakdown
+2. **Execute with `openspec-apply-change`** per microtask:
+   ```
+   For each microtask:
+   - Focus on single file
+   - Implement
+   - Test
+   - Mark complete
+   ```
+3. **Track progress** in parent task
+
+### Workflow:
+```
+1. openspec-new-change → Creates tasks.md
+2. Identify complex task → Use microtask-decomposition
+3. Update tasks.md with microtasks
+4. openspec-apply-change → Implement each microtask
+5. Mark parent task complete when all microtasks done
+```
+
+---
+
+## Guardrails
+
+- **Maximum 1-2 files per microtask** - Keep them atomic
+- **Clear dependencies only** - No circular deps
+- **Estimates < 1 hour** - If longer, decompose further
+- **Testable independently** - Each should have clear done criteria
+- **Preserve parent context** - Link back to original task
+- **Don't over-decompose** - 2-3 file tasks don't need this
+
+---
+
+## Comparison: When to Use What
+
+| Situation | Use | Don't Use |
+|-----------|-----|-----------|
+| Initial task breakdown | `openspec-new-change` / `openspec-ff-change` | microtask-decomposition |
+| Task affects 1-2 files | Direct implementation | microtask-decomposition |
+| Task affects 3+ files, complex | microtask-decomposition | Direct implementation |
+| Need parallel execution | microtask-decomposition | Sequential approach |
+| Simple CRUD operation | Direct in tasks.md | microtask-decomposition |
+
+---
+
+## See Also
+
+- `openspec-new-change` - Create parent change
+- `openspec-continue-change` - Work on decomposed artifacts
+- `openspec-apply-change` - Implement each microtask
+- `spec-analysis` - Verify consistency after decomposition

package/framework/.codex/skills/openspec-apply-change/SKILL.md

@@ -15,7 +15,23 @@ Implement tasks from an OpenSpec change.
 
 **Steps**
 
-1. **Select the change**
+1. **Verify project initialization**
+
+   Check if the project is initialized:
+   ```bash
+   acfm spec status --json
+   ```
+   
+   **If not initialized** (`"initialized": false`):
+   ```bash
+   acfm spec init
+   ```
+   
+   **If initialized** (`"initialized": true`):
+   - Note the `dirName` field (either `.acfm` or `openspec`)
+   - Continue with the workflow
+
+2. **Select the change**
 
    If a name is provided, use it. Otherwise:
    - Infer from conversation context if the user mentioned a change
@@ -24,7 +40,7 @@ Implement tasks from an OpenSpec change.
 
    Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
 
-2. **Check status to understand the schema**
+3. **Check status to understand the schema**
    ```bash
    acfm spec status --change "<name>" --json
    ```
@@ -32,7 +48,7 @@ Implement tasks from an OpenSpec change.
    - `schemaName`: The workflow being used (e.g., "spec-driven")
    - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
 
-3. **Get apply instructions**
+4. **Get apply instructions**
 
    ```bash
    acfm spec instructions apply --change "<name>" --json
@@ -49,14 +65,14 @@ Implement tasks from an OpenSpec change.
    - If `state: "all_done"`: congratulate, suggest archive
    - Otherwise: proceed to implementation
 
-4. **Read context files**
+5. **Read context files**
 
    Read the files listed in `contextFiles` from the apply instructions output.
    The files depend on the schema being used:
    - **spec-driven**: proposal, specs, design, tasks
    - Other schemas: follow the contextFiles from CLI output
 
-5. **Show current progress**
+6. **Show current progress**
 
    Display:
    - Schema being used
@@ -64,7 +80,7 @@ Implement tasks from an OpenSpec change.
    - Remaining tasks overview
    - Dynamic instruction from CLI
 
-6. **Implement tasks (loop until done or blocked)**
+7. **Implement tasks (loop until done or blocked)**
 
    For each pending task:
    - Show which task is being worked on
@@ -79,7 +95,7 @@ Implement tasks from an OpenSpec change.
    - Error or blocker encountered → report and wait for guidance
    - User interrupts
 
-7. **On completion or pause, show status**
+8. **On completion or pause, show status**
 
    Display:
    - Tasks completed this session

package/framework/.codex/skills/openspec-archive-change/SKILL.md

@@ -15,7 +15,23 @@ Archive a completed change in the experimental workflow.
 
 **Steps**
 
-1. **If no change name provided, prompt for selection**
+1. **Verify project initialization**
+
+   Check if the project is initialized:
+   ```bash
+   acfm spec status --json
+   ```
+   
+   **If not initialized** (`"initialized": false`):
+   ```bash
+   acfm spec init
+   ```
+   
+   **If initialized** (`"initialized": true`):
+   - Note the `dirName` field (either `.acfm` or `openspec`)
+   - Continue with the workflow
+
+2. **If no change name provided, prompt for selection**
 
    Run `acfm spec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
 
@@ -24,7 +40,7 @@ Archive a completed change in the experimental workflow.
 
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
-2. **Check artifact completion status**
+3. **Check artifact completion status**
 
    Run `acfm spec status --change "<name>" --json` to check artifact completion.
 
@@ -37,7 +53,7 @@ Archive a completed change in the experimental workflow.
    - Use **AskUserQuestion tool** to confirm user wants to proceed
    - Proceed if user confirms
 
-3. **Check task completion status**
+4. **Check task completion status**
 
    Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
 
@@ -50,7 +66,7 @@ Archive a completed change in the experimental workflow.
 
    **If no tasks file exists:** Proceed without task-related warning.
 
-4. **Assess delta spec sync state**
+5. **Assess delta spec sync state**
 
    Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
 
@@ -65,7 +81,7 @@ Archive a completed change in the experimental workflow.
 
    If user chooses sync, execute /opsx:sync logic (use the openspec-sync-specs skill). Proceed to archive regardless of choice.
 
-5. **Perform the archive**
+6. **Perform the archive**
 
    Create the archive directory if it doesn't exist:
    ```bash
@@ -82,7 +98,7 @@ Archive a completed change in the experimental workflow.
    mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
    ```
 
-6. **Display summary**
+7. **Display summary**
 
    Show archive completion summary including:
    - Change name

package/framework/.codex/skills/openspec-bulk-archive-change/SKILL.md

@@ -17,13 +17,29 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 
 **Steps**
 
-1. **Get active changes**
+1. **Verify project initialization**
+
+   Check if the project is initialized:
+   ```bash
+   acfm spec status --json
+   ```
+   
+   **If not initialized** (`"initialized": false`):
+   ```bash
+   acfm spec init
+   ```
+   
+   **If initialized** (`"initialized": true`):
+   - Note the `dirName` field (either `.acfm` or `openspec`)
+   - Continue with the workflow
+
+2. **Get active changes**
 
    Run `acfm spec list --json` to get all active changes.
 
    If no active changes exist, inform user and stop.
 
-2. **Prompt for change selection**
+3. **Prompt for change selection**
 
    Use **AskUserQuestion tool** with multi-select to let user choose changes:
    - Show each change with its schema
@@ -32,7 +48,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 
    **IMPORTANT**: Do NOT auto-select. Always let the user choose.
 
-3. **Batch validation - gather status for all selected changes**
+4. **Batch validation - gather status for all selected changes**
 
    For each selected change, collect:
 
@@ -48,7 +64,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
       - List which capability specs exist
       - For each, extract requirement names (lines matching `### Requirement: <name>`)
 
-4. **Detect spec conflicts**
+5. **Detect spec conflicts**
 
    Build a map of `capability -> [changes that touch it]`:
 
@@ -59,7 +75,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 
    A conflict exists when 2+ selected changes have delta specs for the same capability.
 
-5. **Resolve conflicts agentically**
+6. **Resolve conflicts agentically**
 
    **For each conflict**, investigate the codebase:
 
@@ -79,7 +95,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
       - In what order (if both)
       - Rationale (what was found in codebase)
 
-6. **Show consolidated status table**
+7. **Show consolidated status table**
 
    Display a table summarizing all changes:
 
@@ -104,7 +120,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
    - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
    ```
 
-7. **Confirm batch operation**
+8. **Confirm batch operation**
 
    Use **AskUserQuestion tool** with a single confirmation:
 
@@ -116,7 +132,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
 
    If there are incomplete changes, make clear they'll be archived with warnings.
 
-8. **Execute archive for each confirmed change**
+9. **Execute archive for each confirmed change**
 
    Process changes in the determined order (respecting conflict resolution):
 
@@ -136,7 +152,7 @@ This skill allows you to batch-archive changes, handling spec conflicts intellig
       - Failed: error during archive (record error)
       - Skipped: user chose not to archive (if applicable)
 
-9. **Display summary**
+10. **Display summary**
 
    Show final results:
 

package/framework/.codex/skills/openspec-continue-change/SKILL.md

@@ -15,7 +15,23 @@ Continue working on a change by creating the next artifact.
 
 **Steps**
 
-1. **If no change name provided, prompt for selection**
+1. **Verify project initialization**
+
+   Check if the project is initialized:
+   ```bash
+   acfm spec status --json
+   ```
+   
+   **If not initialized** (`"initialized": false`):
+   ```bash
+   acfm spec init
+   ```
+   
+   **If initialized** (`"initialized": true`):
+   - Note the `dirName` field (either `.acfm` or `openspec`)
+   - Continue with the workflow
+
+2. **If no change name provided, prompt for selection**
 
    Run `acfm spec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.
 
@@ -29,7 +45,7 @@ Continue working on a change by creating the next artifact.
 
    **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
 
-2. **Check current status**
+3. **Check current status**
    ```bash
    acfm spec status --change "<name>" --json
    ```
@@ -38,7 +54,7 @@ Continue working on a change by creating the next artifact.
    - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
    - `isComplete`: Boolean indicating if all artifacts are complete
 
-3. **Act based on status**:
+4. **Act based on status**:
 
    ---
 
@@ -77,7 +93,7 @@ Continue working on a change by creating the next artifact.
    - This shouldn't happen with a valid schema
    - Show status and suggest checking for issues
 
-4. **After creating an artifact, show progress**
+5. **After creating an artifact, show progress**
    ```bash
    acfm spec status --change "<name>"
    ```

package/framework/.codex/skills/openspec-explore/SKILL.md

@@ -79,9 +79,25 @@ Depending on what the user brings, you might:
 
 You have full context of the OpenSpec system. Use it naturally, don't force it.
 
+### Verify project initialization
+
+At the start, check if the project is initialized:
+```bash
+acfm spec status --json
+```
+
+**If not initialized** (`"initialized": false`):
+```bash
+acfm spec init
+```
+
+**If initialized** (`"initialized": true`):
+- Note the `dirName` field (either `.acfm` or `openspec`)
+- Continue with the workflow
+
 ### Check for context
 
-At the start, quickly check what exists:
+Next, quickly check what exists:
 ```bash
 acfm spec list --json
 ```