agentic-code 0.5.1 → 0.6.1

package/.agents/tasks/task-analysis.md

@@ -3,20 +3,20 @@
 ## Required Rules [MANDATORY - MUST BE ACTIVE]
 
 **RULE AVAILABILITY VERIFICATION:**
-1. [VERIFY ACTIVE] `.agents/rules/core/metacognition.md` (loaded at session start)
-2. [LOAD IF NOT ACTIVE] `.agents/context-maps/task-rule-matrix.yaml`
+1. [VERIFY ACTIVE] `.agents/skills/metacognition/SKILL.md` (loaded at session start)
+2. [LOAD IF NOT ACTIVE] `.agents/context-maps/task-skills-matrix.yaml`
 
 **LOADING PROTOCOL:**
 - STEP 1: VERIFY metacognition.md is active from initial session setup
-- STEP 2: CHECK if task-rule-matrix.yaml is active in working memory
-- STEP 3: If task-rule-matrix.yaml NOT active → Execute BLOCKING READ
+- STEP 2: CHECK if task-skills-matrix.yaml is active in working memory
+- STEP 3: If task-skills-matrix.yaml NOT active → Execute BLOCKING READ
 - STEP 4: CONFIRM all rules active before proceeding with task analysis
 
 **EVIDENCE REQUIRED:**
 ```
 Rule Status Verification:
 ✓ metacognition.md - ACTIVE (from session setup)
-✓ task-rule-matrix.yaml - ACTIVE (loaded/verified)
+✓ task-skills-matrix.yaml - ACTIVE (loaded/verified)
 ```
 
 ## Purpose
@@ -103,7 +103,7 @@ Count affected components:
 ### Step 4: Execute Rule Selection [BLOCKING CHECKPOINT]
 
 **EXECUTION GATES - System HALTS if any step skipped:**
-1. [BLOCKING READ] `task-rule-matrix.yaml` from `.agents/context-maps/`
+1. [BLOCKING READ] `task-skills-matrix.yaml` from `.agents/context-maps/`
 2. [MANDATORY MATCHING] Task type + scale against matrix
 3. [CLASSIFICATION OUTPUT]:
    - Required rules: IMMEDIATE BLOCKING READ
@@ -116,10 +116,10 @@ Count affected components:
    ✓ [filepath] - [reason for loading]
    ✓ [filepath] - [applied to which aspect]
    ```
-6. [PLAN INJECTION] IMMEDIATELY inject all identified BLOCKING READs to work plan:
+6. [TASK TRACKING] IMMEDIATELY add all identified BLOCKING READs to your internal task management (Task List):
    ```
-   [PLAN INJECTION FROM task-analysis - Rule Selection]
-   Injected BLOCKING READs from rule selection:
+   [BLOCKING READs FROM task-analysis - Rule Selection]
+   Added to Task List:
    ✓ [filepath] - required rule
    ✓ [filepath] - conditional rule (condition met)
    ```
@@ -144,11 +144,11 @@ Determine what's needed:
 Based on scale and complexity:
 - **Small Scale (1-2 files)**: Direct task execution, no workflow needed
 - **Medium/Large Scale (3+ files)**: RECOMMEND agentic-coding.md workflow
-  - Ask: "This task would benefit from a structured workflow with design document and work plan. Proceed? [Y/n]"
+  - Ask: "This task would benefit from a structured workflow with design document and Work Plan. Proceed? [Y/n]"
   - If YES: Load and follow agentic-coding.md
   - If NO: Execute individual task definitions directly
 
-### Step 8: Mandatory Plan Injection [BLOCKING - AUTOMATIC EXECUTION]
+### Step 8: Mandatory Task Tracking [BLOCKING - AUTOMATIC EXECUTION]
 
 **FOR ALL TASKS WITH BLOCKING READ REQUIREMENTS:**
 
@@ -157,34 +157,34 @@ Based on scale and complexity:
    - From task definitions to be executed
    - From rules that will be loaded
 
-2. **[AUTOMATIC INJECTION]** Add ALL identified BLOCKING READs to work plan:
+2. **[ADD TO TASK LIST]** Add ALL identified BLOCKING READs to your internal task management (Task List):
    ```
-   Plan Injection Required:
+   Task List - BLOCKING READs:
    □ BLOCKING READ: [file path] - [reason/phase]
    □ BLOCKING READ: [file path] - [reason/phase]
    □ Rule Status Verification after each BLOCKING READ
    ```
 
-3. **[EVIDENCE REQUIRED]** Show plan injection confirmation:
+3. **[EVIDENCE REQUIRED]** Show task tracking confirmation:
    ```
-   [PLAN INJECTION COMPLETED]
+   [TASK TRACKING COMPLETED]
    Identified BLOCKING READs from:
    ✓ Workflow phases: [list files]
    ✓ Task definitions: [list files]
    ✓ Required rules: [list files]
 
-   Injected to plan:
+   Added to Task List:
    ✓ Total BLOCKING READs: [count]
    ✓ Verification gates: [count]
    ```
 
 4. **[ENFORCEMENT]** CANNOT proceed without:
-   - ALL BLOCKING READs identified and injected
-   - Plan injection evidence shown above
-   - Each BLOCKING READ as explicit task in work plan
+   - ALL BLOCKING READs identified and added to Task List
+   - Task tracking evidence shown above
+   - Each BLOCKING READ as explicit item in Task List
 
 **VIOLATION HANDLING:**
-- Missing any BLOCKING READ from plan = IMMEDIATE HALT
+- Missing any BLOCKING READ from Task List = IMMEDIATE HALT
 - Skipping any BLOCKING READ during execution = CRITICAL ERROR
 - Proceeding without verification = RETURN TO TASK ANALYSIS
 

package/.agents/tasks/technical-design.md

@@ -2,50 +2,50 @@
 
 ## Required Rules [MANDATORY - MUST BE ACTIVE]
 
-**RULE AVAILABILITY VERIFICATION:**
-1. [VERIFY ACTIVE] `.agents/rules/core/metacognition.md` (loaded at session start)
-2. [LOAD IF NOT ACTIVE] `.agents/rules/core/documentation-criteria.md`
-3. [CONDITIONAL LOAD] `.agents/rules/contextual/architecture/implementation-approach.md` (if Medium scale 3+ files OR Large scale)
+**SKILL AVAILABILITY VERIFICATION:**
+1. [VERIFY ACTIVE] `.agents/skills/metacognition/SKILL.md` (loaded at session start)
+2. [LOAD IF NOT ACTIVE] `.agents/skills/documentation-criteria/SKILL.md`
+3. [CONDITIONAL LOAD] `.agents/skills/implementation-approach/SKILL.md` (if Medium scale 3+ files OR Large scale)
 
 **LOADING PROTOCOL:**
-- STEP 1: VERIFY metacognition.md is active from initial session setup
-- STEP 2: CHECK if documentation-criteria.md is active in working memory
-- STEP 3: If documentation-criteria.md NOT active → Execute BLOCKING READ
-- STEP 4: EVALUATE conditions for implementation-approach.md (Medium/Large scale: 3+ files)
-- STEP 5: If conditions met AND implementation-approach.md NOT active → Execute BLOCKING READ
-- STEP 6: CONFIRM all required rules active before proceeding
+- STEP 1: VERIFY metacognition/SKILL.md is active from initial session setup
+- STEP 2: CHECK if documentation-criteria/SKILL.md is active in working memory
+- STEP 3: If documentation-criteria/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 4: EVALUATE conditions for implementation-approach/SKILL.md (Medium/Large scale: 3+ files)
+- STEP 5: If conditions met AND implementation-approach/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 6: CONFIRM all required skills active before proceeding
 
-## Plan Injection Requirement [MANDATORY]
+## Task Tracking Requirement [MANDATORY]
 
-**Upon reading this file, IMMEDIATELY inject to work plan:**
+**Upon reading this file, IMMEDIATELY add to your internal task management (Task List):**
 1. All BLOCKING READs identified in Loading Protocol above:
-   - `.agents/rules/core/documentation-criteria.md` (if not active)
-   - `.agents/rules/contextual/architecture/implementation-approach.md` (if conditions met)
+   - `.agents/skills/documentation-criteria/SKILL.md` (if not active)
+   - `.agents/skills/implementation-approach/SKILL.md` (if conditions met)
 2. Mark each with "[From technical-design.md]" source tag
-3. Show evidence of injection:
+3. Show evidence:
    ```
-   [PLAN INJECTION FROM technical-design.md]
-   Injected to work plan:
-   ✓ BLOCKING READ: documentation-criteria.md - ADR/Design Doc criteria
-   ✓ BLOCKING READ: implementation-approach.md - strategy selection (if applicable)
+   [TASK TRACKING FROM technical-design.md]
+   Added to Task List:
+   ✓ BLOCKING READ: documentation-criteria/SKILL.md - ADR/Design Doc criteria
+   ✓ BLOCKING READ: implementation-approach/SKILL.md - strategy selection (if applicable)
    Status: VERIFIED
    ```
 
-**ENFORCEMENT:** Cannot proceed without Plan Injection evidence
+**ENFORCEMENT:** Cannot proceed without Task Tracking evidence
 
 **EVIDENCE REQUIRED:**
 ```
-Rule Status Verification:
-✓ metacognition.md - ACTIVE
-✓ documentation-criteria.md - ACTIVE
-✓ implementation-approach.md - [ACTIVE/NOT NEEDED]
+Skill Status Verification:
+✓ metacognition/SKILL.md - ACTIVE
+✓ documentation-criteria/SKILL.md - ACTIVE
+✓ implementation-approach/SKILL.md - [ACTIVE/NOT NEEDED]
 ```
 
 ## Phase Entry Gate [BLOCKING - SYSTEM HALT IF VIOLATED]
 
 **CHECKPOINT: System CANNOT proceed until ALL boxes checked:**
-☐ [VERIFIED] Plan Injection completed (from task-analysis.md Step 8)
-☐ [VERIFIED] Work plan contains "BLOCKING READ technical-design.md" item
+☐ [VERIFIED] Task Tracking completed (from task-analysis.md Step 8)
+☐ [VERIFIED] Task List contains "BLOCKING READ technical-design.md" item
 ☐ [VERIFIED] Project structure confirmed
 ☐ [VERIFIED] PRD reviewed (if exists) with requirements understood
 ☐ [VERIFIED] Related design documents investigation COMPLETED with evidence

package/.agents/tasks/technical-document-review.md

@@ -2,16 +2,16 @@
 
 ## Required Rules [MANDATORY - MUST BE ACTIVE]
 
-**RULE AVAILABILITY VERIFICATION:**
-1. [LOAD IF NOT ACTIVE] `.agents/rules/core/documentation-criteria.md`
-2. [CONDITIONAL LOAD] `.agents/rules/core/testing-strategy.md` (if reviewing Design Doc with test strategy)
+**SKILL AVAILABILITY VERIFICATION:**
+1. [LOAD IF NOT ACTIVE] `.agents/skills/documentation-criteria/SKILL.md`
+2. [CONDITIONAL LOAD] `.agents/skills/testing-strategy/SKILL.md` (if reviewing Design Doc with test strategy)
 
 **LOADING PROTOCOL:**
-- STEP 1: CHECK if documentation-criteria.md is active in working memory
-- STEP 2: If documentation-criteria.md NOT active → Execute BLOCKING READ
-- STEP 3: EVALUATE if testing-strategy.md needed (Design Doc with test strategy section)
+- STEP 1: CHECK if documentation-criteria/SKILL.md is active in working memory
+- STEP 2: If documentation-criteria/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 3: EVALUATE if testing-strategy/SKILL.md needed (Design Doc with test strategy section)
 - STEP 4: If needed AND NOT active → Execute BLOCKING READ
-- STEP 5: CONFIRM all required rules active before proceeding
+- STEP 5: CONFIRM all required skills active before proceeding
 
 ## Purpose
 
@@ -56,7 +56,7 @@ Confirm document type and determine validation baseline:
 - Default templates by type:
   - Design Doc → `.agents/tasks/technical-design.md`
   - ADR → ADR section in `.agents/tasks/technical-design.md`
-  - PRD → PRD section in `.agents/rules/core/documentation-criteria.md`
+  - PRD → PRD section in `.agents/skills/documentation-criteria/SKILL.md`
 
 ### Stage 2: Structure Compliance Check
 

package/.agents/tasks/work-planning.md

@@ -2,65 +2,65 @@
 
 ## Required Rules [MANDATORY - MUST BE ACTIVE]
 
-**RULE AVAILABILITY VERIFICATION:**
-1. [VERIFY ACTIVE] `.agents/rules/core/metacognition.md` (loaded at session start)
-2. [LOAD IF NOT ACTIVE] `.agents/rules/language/rules.md`
-3. [LOAD IF NOT ACTIVE] `.agents/rules/language/testing.md`
-4. [LOAD IF NOT ACTIVE] `.agents/rules/core/documentation-criteria.md`
+**SKILL AVAILABILITY VERIFICATION:**
+1. [VERIFY ACTIVE] `.agents/skills/metacognition/SKILL.md` (loaded at session start)
+2. [LOAD IF NOT ACTIVE] `.agents/skills/coding-rules/SKILL.md`
+3. [LOAD IF NOT ACTIVE] `.agents/skills/testing/SKILL.md`
+4. [LOAD IF NOT ACTIVE] `.agents/skills/documentation-criteria/SKILL.md`
 
 **LOADING PROTOCOL:**
-- STEP 1: VERIFY metacognition.md is active from initial session setup
-- STEP 2: CHECK if language/rules.md is active in working memory
-- STEP 3: If language/rules.md NOT active → Execute BLOCKING READ
-- STEP 4: CHECK if testing.md is active in working memory
-- STEP 5: If testing.md NOT active → Execute BLOCKING READ
-- STEP 6: CHECK if documentation-criteria.md is active in working memory
-- STEP 7: If documentation-criteria.md NOT active → Execute BLOCKING READ
-- STEP 8: CONFIRM all rules active before proceeding with work planning
-
-## Plan Injection Requirement [MANDATORY]
-
-**Upon reading this file, IMMEDIATELY inject to work plan:**
+- STEP 1: VERIFY metacognition/SKILL.md is active from initial session setup
+- STEP 2: CHECK if coding-rules/SKILL.md is active in working memory
+- STEP 3: If coding-rules/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 4: CHECK if testing/SKILL.md is active in working memory
+- STEP 5: If testing/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 6: CHECK if documentation-criteria/SKILL.md is active in working memory
+- STEP 7: If documentation-criteria/SKILL.md NOT active → Execute BLOCKING READ
+- STEP 8: CONFIRM all skills active before proceeding with work planning
+
+## Task Tracking Requirement [MANDATORY]
+
+**Upon reading this file, IMMEDIATELY add to your internal task management (Task List):**
 1. All BLOCKING READs identified in Loading Protocol above:
-   - `.agents/rules/language/rules.md` (if not active)
-   - `.agents/rules/language/testing.md` (if not active)
-   - `.agents/rules/core/documentation-criteria.md` (if not active)
+   - `.agents/skills/coding-rules/SKILL.md` (if not active)
+   - `.agents/skills/testing/SKILL.md` (if not active)
+   - `.agents/skills/documentation-criteria/SKILL.md` (if not active)
 2. Mark each with "[From work-planning.md]" source tag
-3. Show evidence of injection:
+3. Show evidence:
    ```
-   [PLAN INJECTION FROM work-planning.md]
-   Injected to work plan:
-   ✓ BLOCKING READ: language/rules.md - development standards
-   ✓ BLOCKING READ: language/testing.md - TDD process
-   ✓ BLOCKING READ: documentation-criteria.md - documentation standards
+   [TASK TRACKING FROM work-planning.md]
+   Added to Task List:
+   ✓ BLOCKING READ: coding-rules/SKILL.md - development standards
+   ✓ BLOCKING READ: testing/SKILL.md - TDD process
+   ✓ BLOCKING READ: documentation-criteria/SKILL.md - documentation standards
    Status: VERIFIED
    ```
 
-**ENFORCEMENT:** Cannot proceed without Plan Injection evidence
+**ENFORCEMENT:** Cannot proceed without Task Tracking evidence
 
 **EVIDENCE REQUIRED:**
 ```
-Rule Status Verification:
-✓ metacognition.md - ACTIVE (from session setup)
-✓ language/rules.md - ACTIVE (loaded/verified)
-✓ language/testing.md - ACTIVE (loaded/verified)
-✓ documentation-criteria.md - ACTIVE (loaded/verified)
+Skill Status Verification:
+✓ metacognition/SKILL.md - ACTIVE (from session setup)
+✓ coding-rules/SKILL.md - ACTIVE (loaded/verified)
+✓ testing/SKILL.md - ACTIVE (loaded/verified)
+✓ documentation-criteria/SKILL.md - ACTIVE (loaded/verified)
 ```
 
 ## Phase Entry Gate [BLOCKING - SYSTEM HALT IF VIOLATED]
 
 **CHECKPOINT: System CANNOT proceed until ALL boxes checked:**
 ☐ [VERIFIED] THIS FILE (`work-planning.md`) has been READ and is active
-☐ [VERIFIED] Plan Injection completed (from work-planning.md Plan Injection Requirement)
+☐ [VERIFIED] Task Tracking completed (from work-planning.md Task Tracking Requirement)
 ☐ [VERIFIED] All required rules listed above are LOADED and active
-☐ [VERIFIED] Work plan contains ALL BLOCKING READs from this file
+☐ [VERIFIED] Task List contains ALL BLOCKING READs from this file
 ☐ [VERIFIED] Design document EXISTS at `docs/design/[feature]-design.md`
 ☐ [VERIFIED] User has APPROVED the design
 ☐ [VERIFIED] Test skeletons exist (if applicable for test-driven approach)
 ☐ [VERIFIED] SESSION_BASELINE_DATE established and active
 
 **METACOGNITION GATE [MANDATORY]:**
-BEFORE creating work plan, execute metacognition assessment:
+BEFORE creating Work Plan document, execute metacognition assessment:
 - Understand the design intent and goals
 - Verify task decomposition strategy aligns with 1-commit principle
 - Confirm dependencies are logical and achievable
@@ -71,7 +71,7 @@ IF attempting to skip → CRITICAL ERROR
 
 ## Purpose
 
-Create work plans with decomposed tasks.
+Create Work Plan documents with decomposed tasks.
 
 ## When to Use
 
@@ -95,7 +95,7 @@ Create work plans with decomposed tasks.
 
 ### 1. Plan Structure
 
-Create work plan with:
+Create Work Plan document with:
 - **Overview**: What's being built/changed
 - **Phases**: Logical groupings of work
 - **Tasks**: Individual implementation units
@@ -149,9 +149,9 @@ Create work plan with:
 
 ### Exit Conditions
 - [ ] Test passes
-- [ ] Quality checks pass with 0 errors (per language/testing.md standards)
+- [ ] Quality checks pass with 0 errors (per testing/SKILL.md standards)
 - [ ] Changes committed to git
-- [ ] Task checkbox marked [x] in work plan
+- [ ] Task checkbox marked [x] in Work Plan document
 
 ### Dependencies
 - Depends on: Task [X]

package/.agents/workflows/agentic-coding.md

@@ -11,15 +11,15 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 ## Phase 0: PRD Creation (Large scale only)
 
 ### Pre-Phase Gates [BLOCKING - CANNOT PROCEED WITHOUT]:
-1. **[VERIFY PLAN INJECTION]** Confirm work plan contains ALL required BLOCKING READs for this phase
+1. **[VERIFY TASK TRACKING]** Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. **[BLOCKING READ]** Execute Read on `.agents/tasks/prd-creation.md`
 3. **[VERIFY]** prd-creation.md is ACTIVE in working memory
 4. **[VERIFY]** All rules required by prd-creation.md are LOADED (per its Required Rules section)
-5. **[VERIFY]** Plan Injection from prd-creation.md completed
+5. **[VERIFY]** Task Tracking from prd-creation.md completed
 6. **[CONFIRM]** Entry gates in prd-creation.md are satisfied
 
-**ENFORCEMENT**: NO requirements work until prd-creation.md confirmed active and Plan Injection verified
+**ENFORCEMENT**: NO requirements work until prd-creation.md confirmed active and Task Tracking verified
 
 ### Internal Checklist:
 ```
@@ -67,7 +67,7 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 ## Phase 2: Technical Design
 
 ### Pre-Phase Gates [BLOCKING - CANNOT PROCEED WITHOUT]:
-1. **[VERIFY PLAN INJECTION]** Confirm work plan contains ALL required BLOCKING READs for this phase
+1. **[VERIFY TASK TRACKING]** Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. **[BLOCKING READ]** Execute Read on `.agents/tasks/technical-design.md`
 3. **[VERIFY]** technical-design.md is ACTIVE in working memory
@@ -76,7 +76,7 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 
 **ENFORCEMENT**:
 - NO design work until technical-design.md confirmed active
-- NO proceeding without Plan Injection verification for ALL BLOCKING READs
+- NO proceeding without Task Tracking verification for ALL BLOCKING READs
 
 ### Pre-Design Requirements:
 ```
@@ -126,19 +126,19 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 
 ## Phase 3: Acceptance Test Generation
 
-**PHASE ORDERING RATIONALE**: Test skeletons MUST be generated BEFORE work planning. Test structures define verification boundaries that determine task decomposition granularity. Work plans depend on these test specifications to map implementation units to concrete verification points.
+**PHASE ORDERING RATIONALE**: Test skeletons MUST be generated BEFORE work planning. Test structures define verification boundaries that determine task decomposition granularity. Work Plan documents depend on these test specifications to map implementation units to concrete verification points.
 
 ### Pre-Phase Gates [BLOCKING - CANNOT PROCEED WITHOUT]:
-1. **[VERIFY PLAN INJECTION]** Confirm work plan contains ALL required BLOCKING READs for this phase
+1. **[VERIFY TASK TRACKING]** Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. **[BLOCKING READ]** Execute Read on `.agents/tasks/acceptance-test-generation.md`
 3. **[VERIFY]** acceptance-test-generation.md is ACTIVE in working memory
 4. **[VERIFY]** All rules required by acceptance-test-generation.md are LOADED (per its Required Rules section)
-5. **[VERIFY]** Plan Injection from acceptance-test-generation.md completed
+5. **[VERIFY]** Task Tracking from acceptance-test-generation.md completed
 6. **[CONFIRM]** Entry gates in acceptance-test-generation.md are satisfied
 7. **[VERIFY]** Design document EXISTS and contains Acceptance Criteria section
 
-**ENFORCEMENT**: NO test generation until acceptance-test-generation.md confirmed active and Plan Injection verified
+**ENFORCEMENT**: NO test generation until acceptance-test-generation.md confirmed active and Task Tracking verified
 
 ### Internal Checklist:
 ```
@@ -184,17 +184,17 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 **PHASE DEPENDENCY**: This phase REQUIRES completed test skeletons from Phase 3. Task decomposition uses test verification points as boundaries for work units. Each implementation task maps to specific test cases for validation.
 
 ### Pre-Phase Gates [BLOCKING - CANNOT PROCEED WITHOUT]:
-1. **[VERIFY PLAN INJECTION]** Confirm work plan contains ALL required BLOCKING READs for this phase
+1. **[VERIFY TASK TRACKING]** Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. **[BLOCKING READ]** Execute Read on `.agents/tasks/work-planning.md`
 3. **[VERIFY]** work-planning.md is ACTIVE in working memory
 4. **[VERIFY]** All rules required by work-planning.md are LOADED (per its Required Rules section)
-5. **[VERIFY]** Plan Injection from work-planning.md completed
+5. **[VERIFY]** Task Tracking from work-planning.md completed
 6. **[CONFIRM]** Entry gates in work-planning.md are satisfied
 7. **[VERIFY]** Design document APPROVED by user
 8. **[VERIFY]** Test skeletons from Phase 3 EXIST in test directories
 
-**ENFORCEMENT**: NO work plan creation until work-planning.md confirmed active and Plan Injection verified
+**ENFORCEMENT**: NO Work Plan document creation until work-planning.md confirmed active and Task Tracking verified
 
 ### Internal Checklist:
 ```
@@ -219,21 +219,21 @@ Execute phases sequentially. For Large scale (6+ files), include PRD phase.
 
 ### STOP POINT: Work Plan Approval [BLOCKING GATE]
 **SYSTEM HALT - CANNOT WRITE CODE WITHOUT:**
-1. Work plan document EXISTS at `docs/plans/YYYYMMDD-{type}-{description}.md`
-2. **[VERIFY INJECTION]** Plan MUST contain ALL BLOCKING READs identified in task-analysis Step 8:
+1. Work Plan document EXISTS at `docs/plans/YYYYMMDD-{type}-{description}.md`
+2. **[VERIFY TASK LIST]** Task List MUST contain ALL BLOCKING READs identified in task-analysis Step 8:
    - Every BLOCKING READ from workflow phases
    - Every BLOCKING READ from task definitions
    - Every BLOCKING READ from required rules
-   - Each marked with source: "[From Plan Injection]"
+   - Each marked with source: "[From Task Tracking]"
 3. Each task has MEASURABLE completion criteria
 4. User EXPLICITLY approves plan
 
 **GATE VERIFICATION:**
 ```
-Plan Location: docs/plans/[filename].md
+Work Plan Location: docs/plans/[filename].md
 Task Count: [N] tasks defined
-BLOCKING READs in plan: [count] items
-Plan Injection Status: [COMPLETE/INCOMPLETE]
+BLOCKING READs in Task List: [count] items
+Task Tracking Status: [COMPLETE/INCOMPLETE]
 User Approval: [AWAITING/RECEIVED]
 ```
 
@@ -245,15 +245,15 @@ User Approval: [AWAITING/RECEIVED]
 
 ### Pre-Implementation Gates [BLOCKING - CANNOT START WITHOUT]:
 ```
-1. [VERIFY PLAN INJECTION] Confirm work plan contains ALL required BLOCKING READs for this phase
+1. [VERIFY TASK TRACKING] Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. [BLOCKING READ] Execute Read on `.agents/tasks/implementation.md`
 3. [VERIFY] implementation.md is ACTIVE in working memory
 4. [VERIFY] All rules required by implementation.md are LOADED (per its Required Rules section)
-5. [VERIFY] Plan Injection from implementation.md completed
+5. [VERIFY] Task Tracking from implementation.md completed
 6. [CONFIRM] Entry gates in implementation.md are satisfied
-7. [VERIFY] Work plan document EXISTS and has been APPROVED
-8. [CONFIRM] Current task identified from work plan
+7. [VERIFY] Work Plan document EXISTS and has been APPROVED
+8. [CONFIRM] Current task identified from Work Plan document
 ```
 
 **CRITICAL ENFORCEMENT**:
@@ -263,16 +263,16 @@ User Approval: [AWAITING/RECEIVED]
 
 ### Execution Pattern [ENFORCED SEQUENCE]:
 ```
-For each task in work plan:
+For each task in Work Plan document:
   1. [METACOGNITION PRE] Execute "When Starting Work" checklist from metacognition protocol
-  2. [TRACKING] Mark task as in_progress in task tracking
+  2. [TRACKING] Mark task as in_progress in your internal task management (Task List)
   3. [IMPLEMENT] Write code following ALL loaded rules (TDD: RED-GREEN-REFACTOR)
   4. [VERIFY] Run ALL quality check commands - MUST have 0 errors
   5. [COMMIT] Git commit with descriptive message for this task
-  6. [UPDATE] Mark task checkbox complete [x] in work plan document
+  6. [UPDATE] Mark task checkbox complete [x] in Work Plan document
   7. [GATE CHECK] ALL completion criteria must pass
   8. [METACOGNITION POST] Execute "After Completion" checklist
-  9. [TRACKING] Mark task complete in task tracking
+  9. [TRACKING] Mark task complete in Task List
   10. [CHECKPOINT] Cannot start next task until all steps complete
 ```
 
@@ -290,15 +290,15 @@ For each task in work plan:
 ## Phase 6: Quality Assurance
 
 ### Pre-Phase Gates [BLOCKING - CANNOT PROCEED WITHOUT]:
-1. **[VERIFY PLAN INJECTION]** Confirm work plan contains ALL required BLOCKING READs for this phase
+1. **[VERIFY TASK TRACKING]** Confirm Task List contains ALL required BLOCKING READs for this phase
    - If missing any: HALT - Return to task-analysis.md Step 8
 2. **[BLOCKING READ]** Execute Read on `.agents/tasks/quality-assurance.md`
 3. **[VERIFY]** quality-assurance.md is ACTIVE in working memory
 4. **[VERIFY]** All rules required by quality-assurance.md are LOADED (per its Required Rules section)
-5. **[VERIFY]** Plan Injection from quality-assurance.md completed
-6. **[CONFIRM]** All implementation tasks marked complete in work plan
+5. **[VERIFY]** Task Tracking from quality-assurance.md completed
+6. **[CONFIRM]** All implementation tasks marked complete in Work Plan document
 
-**ENFORCEMENT**: NO quality checks until quality-assurance.md confirmed active and Plan Injection verified
+**ENFORCEMENT**: NO quality checks until quality-assurance.md confirmed active and Task Tracking verified
 
 ### Internal Checklist:
 ```

package/AGENTS.md

@@ -2,7 +2,7 @@
 
 ## ABSOLUTE PRINCIPLES
 
-1. **EXECUTE all rules and requirements in task/rule files - no exceptions**
+1. **EXECUTE all rules and requirements in task/skill files - no exceptions**
 2. **COMPLETE all entry and exit conditions for every task**
 3. **STOP at gates - proceed only when conditions are met**
 
@@ -10,7 +10,7 @@
 
 **Complete before any other operation:**
 1. Execute `date` command → Store as SESSION_BASELINE_DATE
-2. Apply `.agents/rules/core/metacognition.md` → Keep active entire session
+2. Apply `.agents/skills/metacognition/SKILL.md` → Keep active entire session
 3. Use SESSION_BASELINE_DATE for all date references (WebSearch, docs, etc.)
 4. Verify project structure with `ls -la`
 
@@ -20,7 +20,12 @@
 
 ## Task Analysis - Required First Step
 
-**ALWAYS start here for any user request:**
+**Early Exit Check (BEFORE loading task-analysis.md):**
+Does this task require reading code files to decide HOW to execute it?
+- **NO** → Execute directly, skip task-analysis.md
+- **YES** → Load and follow task-analysis.md
+
+**If not early exit, start here for any user request:**
 1. Apply `.agents/tasks/task-analysis.md`
 2. Follow its output to select the appropriate path:
 
@@ -39,7 +44,7 @@
 ### Plan Injection [MANDATORY ENFORCEMENT]
 **All tasks require Plan Injection for BLOCKING READs:**
 - Task-analysis.md Step 8 scans and identifies ALL BLOCKING READ requirements
-- Work plans MUST contain every BLOCKING READ from workflow/tasks/rules
+- Work plans MUST contain every BLOCKING READ from workflow/tasks/skills
 - Each phase verifies its BLOCKING READs are in the plan
 - Gates verify Plan Injection evidence before proceeding
 - Missing ANY BLOCKING READ = IMMEDIATE HALT
@@ -47,13 +52,13 @@
 ### Task Definition Loading
 **Task definitions define WHAT to build - never skip them:**
 - Verify entry gates before proceeding
-- Follow Required Rules section in each task definition
+- Follow Required Skills section in each task definition
 
-### Rule Application
-**Apply rules based on task type from task-analysis:**
-- Rules are loaded progressively as needed
-- Each task definition specifies its required rules
-- Unload task-specific rules after completion
+### Skill Application
+**Apply skills based on task type from task-analysis:**
+- Skills are loaded progressively as needed
+- Each task definition specifies its required skills
+- Unload task-specific skills after completion
 
 ### Quality Standards
 **Before marking any task complete:**
@@ -82,7 +87,7 @@ Common approval points:
 **Universal quality requirements:**
 - Follow TDD process for all code changes
 - All quality checks must pass with 0 errors
-- Follow standards defined in language-specific rules
+- Follow standards defined in language-specific skills
 - Each task definition specifies its quality gates
 
 ## Metacognition Checkpoints
@@ -97,17 +102,17 @@ Perform self-assessment at these mandatory points:
 ## Context Management
 
 **Guidelines**:
-- Load rules progressively, not all at once
-- Unload task-specific rules after completion
-- Keep only frequently-used rules loaded
+- Load skills progressively, not all at once
+- Unload task-specific skills after completion
+- Keep only frequently-used skills loaded
 - If context feels constrained, ask user for cleanup guidance
 
 ## Error Recovery
 
 When stuck or encountering errors:
 1. Re-read current task definition
-2. Check if required rules are loaded
-3. Look for anti-patterns in ai-development-guide.md
+2. Check if required skills are loaded
+3. Look for anti-patterns in ai-development-guide skill
 4. If unable to resolve, ask user for clarification
 
 ## File Organization
@@ -124,33 +129,21 @@ When stuck or encountering errors:
 - agentic-coding.md: Medium/Large scale workflow
 
 **Context Maps** (.agents/context-maps/):
-- task-rule-matrix.yaml: Task-to-rule mappings
-
-**Core Rules** (.agents/rules/core/):
-- metacognition.md: Self-assessment
-- ai-development-guide.md: Anti-patterns
-- documentation-criteria.md: Documentation criteria
-
-**Language Rules** (.agents/rules/language/):
-- rules.md: Development rules
-- testing.md: Testing standards
-
-**Contextual Rules** (.agents/rules/contextual/):
-- architecture/: Implementation approaches
+- task-skills-matrix.yaml: Task-to-skill mappings
 
 ## Anti-Patterns to Avoid
 
 1. **Skipping task-analysis.md** → ALWAYS start with task analysis
-2. **Loading all rules upfront** → Load progressively based on task needs
+2. **Loading all skills upfront** → Load progressively based on task needs
 3. **Ignoring task entry/exit conditions** → Verify gates at each step
 4. **Working without task definitions** → Task definitions define WHAT to build
-6. **Assuming workflow is always needed** → Small tasks can use direct task definitions
-7. **Premature workflow selection** → Let task-analysis determine the approach
+5. **Assuming workflow is always needed** → Small tasks can use direct task definitions
+6. **Premature workflow selection** → Let task-analysis determine the approach
 
 ## Success Metrics
 
 Track internally:
 - Task completion rate
-- Rules actually used vs loaded
+- Skills actually used vs loaded
 - Quality checks passing rate (should be 100%)
 - Appropriate path selection (direct vs workflow)