@ngxtm/devkit 3.19.0 → 3.21.0

package/merged-commands/skill/optimize.md

@@ -4,7 +4,7 @@ argument-hint: [skill-name] [prompt]
 ---
 
 Think harder.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Arguments

package/merged-commands/skill/plan.md

@@ -4,7 +4,7 @@ argument-hint: [skill-name] [prompt]
 ---
 
 Think harder.
-First: Activate `skill-creator` skill and `claude-code-guide` subagent.
+First: Activate `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 Employ `sequential-thinking` or `problem-solving` skills for complex problem-solving that requires structured analysis
 Finally, when creating a plan, activate `planning` skill.

package/merged-commands/skill/sync.md

@@ -95,15 +95,31 @@ For each item in `external-skills`:
 
 ### Step 5: Evaluate Rules
 
+**IMPORTANT:** Never overwrite or sync rules in `rules/base/`. Base rules are devkit-native and managed manually. Only evaluate rules in tech-specific directories.
+
 For each item in `rules.new`:
 1. Read the rule content from `path` field
 2. Classify: useful (covers new pattern) or skip (duplicate/too generic)
-3. In `--auto` mode: sync all useful
-4. In interactive mode: ask user
+3. Count lines — if > 50 lines, flag as "verbose, needs compaction"
+4. In `--auto` mode: sync all useful (compact verbose ones automatically)
+5. In interactive mode: ask user
 
 For each item in `rules.updated`:
 1. Compare upstream and local content
 2. Accept meaningful updates, skip trivial ones
+3. Count lines — if > 50 lines, flag as "verbose, needs compaction"
+
+**Note:** Size-based compaction applies to RULES only. Skills are loaded on-demand and do not need compaction.
+
+### Step 5.5: Compact Verbose Rules
+
+For each rule flagged as verbose (> 50 lines):
+1. Read full content
+2. Compact while preserving: core patterns, conventions, do's/don'ts, lookup tables, key code examples (max 1-2)
+3. Remove: redundant explanations, excessive examples, sections repeating what Claude already knows, full example interactions/dialogs
+4. Target: ≤ 50 lines for tech rules
+5. In `--auto` mode: compact automatically
+6. In interactive mode: show line count before/after, ask user
 
 ### Step 6: Apply Changes
 
@@ -134,7 +150,7 @@ npm run build
 
 Stage and commit the changes:
 ```bash
-git add skills/ rules/ merged-commands/ SKILLS_INDEX.md skills-index.json skills-compact.json skills-graph.json rules-index.json
+git add skills/ rules/ merged-commands/ templates/ SKILLS_INDEX.md skills-index.json skills-compact.json skills-graph.json rules-index.json
 ```
 
 Commit message format:
@@ -162,9 +178,17 @@ If stash was created earlier: `git stash pop` to restore user's changes.
 - Always update version tracking
 - Never overwrite devkit-specific frontmatter (`triggers`, `role`, `scope`, `output-format`)
 
-### Rules
-- **Accept**: Rule covers useful pattern not in existing rules
+### Rules (loaded every turn — context cost matters)
+- **Accept**: Useful pattern, ≤ 50 lines
+- **Compact**: Useful but > 50 lines → reduce while preserving core content
 - **Skip**: Duplicate or too generic
+- **Protect**: Never touch rules/base/ (devkit-native)
+
+### Skills (loaded on-demand — no compaction needed)
+- **Useful**: Covers distinct domain, well-structured SKILL.md, actionable patterns/commands
+- **Duplicate**: Similar name or description to existing skill in skills-compact.json
+- **Skip**: Too niche, low quality, just "be a senior X engineer" boilerplate
+- No size-based compaction — verbose skills are acceptable
 
 ## Important
 

package/merged-commands/skill/update.md

@@ -4,7 +4,7 @@ argument-hint: [skill-name] [prompt]
 ---
 
 Think harder.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Arguments
@@ -23,11 +23,11 @@ Always keep in mind that `SKILL.md` and reference files should be token consumpt
 ## IMPORTANT NOTES:
 - ALWAYS make changes to skills in the project-scope `.claude/skills/` directory (UNLESS you're allowed to).
 - DO NOT make any changes to skills in the home/user-scope `~/.claude/skills/` directory (UNLESS you're allowed to).
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
+- If you're given nothing, use `AskUserQuestion` tool for clarifications and Task agent for research to research about the topic: Task(subagent_type="general-purpose", prompt="You are a researcher. Research...", description="Research topic").
+- If you're given an URL, it's documentation page, use Task agent for exploration to explore every internal link and report back to main agent, don't skip any link: Task(subagent_type="general-purpose", prompt="You are an explorer. Explore all internal links...", description="Explore URL").
+- If you receive a lot of URLs, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you receive a lot of files, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple Task agents for exploration to explore it in parallel, then report back to main agent.
 - Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
 - Each skill teaches Claude how to perform a specific development task, not what a tool does.
 - Claude Code can activate multiple skills automatically to achieve the user's request.

package/merged-commands/subagent-driven-development.md

@@ -5,11 +5,11 @@ risk: unknown
 source: community
 ---
 
-# Subagent-Driven Development
+# Task Agent-Driven Development
 
-Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
+Execute plan by dispatching fresh Task agent per task, with two-stage review after each: spec compliance review first, then code quality review.
 
-**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
+**Core principle:** Fresh Task agent per task + two-stage review (spec then quality) = high quality, fast iteration
 
 ## When to Use
 
@@ -33,7 +33,7 @@ digraph when_to_use {
 
 **vs. Executing Plans (parallel session):**
 - Same session (no context switch)
-- Fresh subagent per task (no context pollution)
+- Fresh Task agent per task (no context pollution)
 - Two-stage review after each task: spec compliance first, then code quality
 - Faster iteration (no human-in-loop between tasks)
 
@@ -45,55 +45,55 @@ digraph process {
 
     subgraph cluster_per_task {
         label="Per Task";
-        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
-        "Implementer subagent asks questions?" [shape=diamond];
+        "Dispatch implementer Task agent (./implementer-prompt.md)" [shape=box];
+        "Implementer Task agent asks questions?" [shape=diamond];
         "Answer questions, provide context" [shape=box];
-        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
-        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
-        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
-        "Implementer subagent fixes spec gaps" [shape=box];
-        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
-        "Code quality reviewer subagent approves?" [shape=diamond];
-        "Implementer subagent fixes quality issues" [shape=box];
+        "Implementer Task agent implements, tests, commits, self-reviews" [shape=box];
+        "Dispatch spec reviewer Task agent (./spec-reviewer-prompt.md)" [shape=box];
+        "Spec reviewer Task agent confirms code matches spec?" [shape=diamond];
+        "Implementer Task agent fixes spec gaps" [shape=box];
+        "Dispatch code quality reviewer Task agent (./code-quality-reviewer-prompt.md)" [shape=box];
+        "Code quality reviewer Task agent approves?" [shape=diamond];
+        "Implementer Task agent fixes quality issues" [shape=box];
         "Mark task complete in TodoWrite" [shape=box];
     }
 
     "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
     "More tasks remain?" [shape=diamond];
-    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
+    "Dispatch final code reviewer Task agent for entire implementation" [shape=box];
     "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
 
-    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)";
-    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
-    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
-    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
-    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
-    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
-    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
-    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
-    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
-    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
-    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
-    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
-    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
-    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer Task agent (./implementer-prompt.md)";
+    "Dispatch implementer Task agent (./implementer-prompt.md)" -> "Implementer Task agent asks questions?";
+    "Implementer Task agent asks questions?" -> "Answer questions, provide context" [label="yes"];
+    "Answer questions, provide context" -> "Dispatch implementer Task agent (./implementer-prompt.md)";
+    "Implementer Task agent asks questions?" -> "Implementer Task agent implements, tests, commits, self-reviews" [label="no"];
+    "Implementer Task agent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer Task agent (./spec-reviewer-prompt.md)";
+    "Dispatch spec reviewer Task agent (./spec-reviewer-prompt.md)" -> "Spec reviewer Task agent confirms code matches spec?";
+    "Spec reviewer Task agent confirms code matches spec?" -> "Implementer Task agent fixes spec gaps" [label="no"];
+    "Implementer Task agent fixes spec gaps" -> "Dispatch spec reviewer Task agent (./spec-reviewer-prompt.md)" [label="re-review"];
+    "Spec reviewer Task agent confirms code matches spec?" -> "Dispatch code quality reviewer Task agent (./code-quality-reviewer-prompt.md)" [label="yes"];
+    "Dispatch code quality reviewer Task agent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer Task agent approves?";
+    "Code quality reviewer Task agent approves?" -> "Implementer Task agent fixes quality issues" [label="no"];
+    "Implementer Task agent fixes quality issues" -> "Dispatch code quality reviewer Task agent (./code-quality-reviewer-prompt.md)" [label="re-review"];
+    "Code quality reviewer Task agent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
     "Mark task complete in TodoWrite" -> "More tasks remain?";
-    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
-    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
-    "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch";
+    "More tasks remain?" -> "Dispatch implementer Task agent (./implementer-prompt.md)" [label="yes"];
+    "More tasks remain?" -> "Dispatch final code reviewer Task agent for entire implementation" [label="no"];
+    "Dispatch final code reviewer Task agent for entire implementation" -> "Use superpowers:finishing-a-development-branch";
 }
 ```
 
 ## Prompt Templates
 
-- `./implementer-prompt.md` - Dispatch implementer subagent
-- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
-- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent
+- `./implementer-prompt.md` - Dispatch implementer Task agent
+- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer Task agent
+- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer Task agent
 
 ## Example Workflow
 
 ```
-You: I'm using Subagent-Driven Development to execute this plan.
+You: I'm using Task Agent-Driven Development to execute this plan.
 
 [Read plan file once: docs/plans/feature-plan.md]
 [Extract all 5 tasks with full text and context]
@@ -102,7 +102,7 @@ You: I'm using Subagent-Driven Development to execute this plan.
 Task 1: Hook installation script
 
 [Get Task 1 text and context (already extracted)]
-[Dispatch implementation subagent with full task text + context]
+[Dispatch implementation Task agent with full task text + context]
 
 Implementer: "Before I begin - should the hook be installed at user or system level?"
 
@@ -126,7 +126,7 @@ Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
 Task 2: Recovery modes
 
 [Get Task 2 text and context (already extracted)]
-[Dispatch implementation subagent with full task text + context]
+[Dispatch implementation Task agent with full task text + context]
 
 Implementer: [No questions, proceeds]
 Implementer:
@@ -169,10 +169,10 @@ Done!
 ## Advantages
 
 **vs. Manual execution:**
-- Subagents follow TDD naturally
+- Task agents follow TDD naturally
 - Fresh context per task (no confusion)
-- Parallel-safe (subagents don't interfere)
-- Subagent can ask questions (before AND during work)
+- Parallel-safe (Task agents don't interfere)
+- Task agent can ask questions (before AND during work)
 
 **vs. Executing Plans:**
 - Same session (no handoff)
@@ -182,7 +182,7 @@ Done!
 **Efficiency gains:**
 - No file reading overhead (controller provides full text)
 - Controller curates exactly what context is needed
-- Subagent gets complete information upfront
+- Task agent gets complete information upfront
 - Questions surfaced before work begins (not after)
 
 **Quality gates:**
@@ -193,7 +193,7 @@ Done!
 - Code quality ensures implementation is well-built
 
 **Cost:**
-- More subagent invocations (implementer + 2 reviewers per task)
+- More Task agent invocations (implementer + 2 reviewers per task)
 - Controller does more prep work (extracting all tasks upfront)
 - Review loops add iterations
 - But catches issues early (cheaper than debugging later)
@@ -203,40 +203,40 @@ Done!
 **Never:**
 - Skip reviews (spec compliance OR code quality)
 - Proceed with unfixed issues
-- Dispatch multiple implementation subagents in parallel (conflicts)
-- Make subagent read plan file (provide full text instead)
-- Skip scene-setting context (subagent needs to understand where task fits)
-- Ignore subagent questions (answer before letting them proceed)
+- Dispatch multiple implementation Task agents in parallel (conflicts)
+- Make Task agent read plan file (provide full text instead)
+- Skip scene-setting context (Task agent needs to understand where task fits)
+- Ignore Task agent questions (answer before letting them proceed)
 - Accept "close enough" on spec compliance (spec reviewer found issues = not done)
 - Skip review loops (reviewer found issues = implementer fixes = review again)
 - Let implementer self-review replace actual review (both are needed)
 - **Start code quality review before spec compliance is ✅** (wrong order)
 - Move to next task while either review has open issues
 
-**If subagent asks questions:**
+**If Task agent asks questions:**
 - Answer clearly and completely
 - Provide additional context if needed
 - Don't rush them into implementation
 
 **If reviewer finds issues:**
-- Implementer (same subagent) fixes them
+- Implementer (same Task agent) fixes them
 - Reviewer reviews again
 - Repeat until approved
 - Don't skip the re-review
 
-**If subagent fails task:**
-- Dispatch fix subagent with specific instructions
+**If Task agent fails task:**
+- Dispatch fix Task agent with specific instructions
 - Don't try to fix manually (context pollution)
 
 ## Integration
 
 **Required workflow skills:**
 - **superpowers:writing-plans** - Creates the plan this skill executes
-- **superpowers:requesting-code-review** - Code review template for reviewer subagents
+- **superpowers:requesting-code-review** - Code review template for reviewer Task agents
 - **superpowers:finishing-a-development-branch** - Complete development after all tasks
 
-**Subagents should use:**
-- **superpowers:test-driven-development** - Subagents follow TDD for each task
+**Task agents should use:**
+- **superpowers:test-driven-development** - Task agents follow TDD for each task
 
 **Alternative workflow:**
 - **superpowers:executing-plans** - Use for parallel session instead of same-session execution

package/merged-commands/tdd-workflows-tdd-cycle.md

@@ -42,13 +42,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 1: Test Specification and Design
 
 ### 1. Requirements Analysis
-- Use Task tool with subagent_type="comprehensive-review::architect-review"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Analyze requirements for: $ARGUMENTS. Define acceptance criteria, identify edge cases, and create test scenarios. Output a comprehensive test specification."
 - Output: Test specification, acceptance criteria, edge case matrix
 - Validation: Ensure all requirements have corresponding test scenarios
 
 ### 2. Test Architecture Design
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Design test architecture for: $ARGUMENTS based on test specification. Define test structure, fixtures, mocks, and test data strategy. Ensure testability and maintainability."
 - Output: Test architecture, fixture design, mock strategy
 - Validation: Architecture supports isolated, fast, reliable tests
@@ -56,13 +56,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 2: RED - Write Failing Tests
 
 ### 3. Write Unit Tests (Failing)
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Write FAILING unit tests for: $ARGUMENTS. Tests must fail initially. Include edge cases, error scenarios, and happy paths. DO NOT implement production code."
 - Output: Failing unit tests, test documentation
 - **CRITICAL**: Verify all tests fail with expected error messages
 
 ### 4. Verify Test Failure
-- Use Task tool with subagent_type="tdd-workflows::code-reviewer"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Verify that all tests for: $ARGUMENTS are failing correctly. Ensure failures are for the right reasons (missing implementation, not test errors). Confirm no false positives."
 - Output: Test failure verification report
 - **GATE**: Do not proceed until all tests fail appropriately
@@ -70,13 +70,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 3: GREEN - Make Tests Pass
 
 ### 5. Minimal Implementation
-- Use Task tool with subagent_type="backend-development::backend-architect"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement MINIMAL code to make tests pass for: $ARGUMENTS. Focus only on making tests green. Do not add extra features or optimizations. Keep it simple."
 - Output: Minimal working implementation
 - Constraint: No code beyond what's needed to pass tests
 
 ### 6. Verify Test Success
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Run all tests for: $ARGUMENTS and verify they pass. Check test coverage metrics. Ensure no tests were accidentally broken."
 - Output: Test execution report, coverage metrics
 - **GATE**: All tests must pass before proceeding
@@ -84,13 +84,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 4: REFACTOR - Improve Code Quality
 
 ### 7. Code Refactoring
-- Use Task tool with subagent_type="tdd-workflows::code-reviewer"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Refactor implementation for: $ARGUMENTS while keeping tests green. Apply SOLID principles, remove duplication, improve naming, and optimize performance. Run tests after each refactoring."
 - Output: Refactored code, refactoring report
 - Constraint: Tests must remain green throughout
 
 ### 8. Test Refactoring
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Refactor tests for: $ARGUMENTS. Remove test duplication, improve test names, extract common fixtures, and enhance test readability. Ensure tests still provide same coverage."
 - Output: Refactored tests, improved test structure
 - Validation: Coverage metrics unchanged or improved
@@ -98,13 +98,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 5: Integration and System Tests
 
 ### 9. Write Integration Tests (Failing First)
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Write FAILING integration tests for: $ARGUMENTS. Test component interactions, API contracts, and data flow. Tests must fail initially."
 - Output: Failing integration tests
 - Validation: Tests fail due to missing integration logic
 
 ### 10. Implement Integration
-- Use Task tool with subagent_type="backend-development::backend-architect"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement integration code for: $ARGUMENTS to make integration tests pass. Focus on component interaction and data flow."
 - Output: Integration implementation
 - Validation: All integration tests pass
@@ -112,13 +112,13 @@ Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-g
 ## Phase 6: Continuous Improvement Cycle
 
 ### 11. Performance and Edge Case Tests
-- Use Task tool with subagent_type="unit-testing::test-automator"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Add performance tests and additional edge case tests for: $ARGUMENTS. Include stress tests, boundary tests, and error recovery tests."
 - Output: Extended test suite
 - Metric: Increased test coverage and scenario coverage
 
 ### 12. Final Code Review
-- Use Task tool with subagent_type="comprehensive-review::architect-review"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Perform comprehensive review of: $ARGUMENTS. Verify TDD process was followed, check code quality, test quality, and coverage. Suggest improvements."
 - Output: Review report, improvement suggestions
 - Action: Implement critical suggestions while maintaining green tests

package/merged-commands/tdd-workflows-tdd-red.md

@@ -35,7 +35,7 @@ Write comprehensive failing tests following TDD red phase principles.
 
 ## Role
 
-Generate failing tests using Task tool with subagent_type="unit-testing::test-automator".
+Generate failing tests using Task tool with subagent_type="general-purpose".
 
 ## Prompt Template
 

package/merged-commands/tdd-workflows-tdd-refactor.md

@@ -28,7 +28,7 @@ Refactor code with confidence using comprehensive test safety net:
 
 ## Usage
 
-Use Task tool with subagent_type="tdd-orchestrator" to perform safe refactoring.
+Use Task tool with subagent_type="general-purpose" to perform safe refactoring.
 
 Prompt: "Refactor this code while keeping all tests green: $ARGUMENTS. Apply TDD refactor phase:
 

package/merged-commands/test/fast.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡ Quick Test — Fast testing for specific scope
+description: Quick Test — Fast testing for specific scope
 version: "1.0"
 category: validation
 execution-mode: execute
@@ -13,48 +13,37 @@ execution-mode: execute
 
 ---
 
-## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
-
-**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
-1. ORCHESTRATION-LAWS.md  
-2. ADAPTIVE-EXECUTION.md  
-3. EXECUTION-PROTOCOL.md  
-
-**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
+## Execution
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## 🔀 TIERED EXECUTION
-
-| Tier | When | Action |
-|------|------|--------|
-| **TIER 1** | runSubagent EXISTS | Invoke sub-agent (MANDATORY) |
-| **TIER 2** | Tool MISSING | EMBODY agent file (FALLBACK) |
+## Phase 1: TEST EXECUTION
 
----
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `tester` |
+| **Goal** | Run focused tests |
+| **Exit** | Tests run, results recorded |
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+### Delegation
 
-One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what’s happening (announce before doing).
+> Task(subagent_type="general-purpose", prompt="You are a tester. Run focused tests for the given scope. Exit when tests are run and results are recorded.", description="tester: Run focused tests")
 
 ---
 
-## 🎭 Phase 1: TEST EXECUTION
-
-| Agent | `tester` |
-|-------|----------|
-| Goal | Run focused tests |
-| Exit | Tests run, results recorded |
+## Phase 2: QUICK ANALYSIS (IF FAILURES)
 
----
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `debugger` |
+| **Trigger** | If failures exist |
+| **Goal** | Quick failure analysis |
+| **Exit** | Root causes identified |
 
-## 🎭 Phase 2: QUICK ANALYSIS (IF FAILURES)
+### Delegation
 
-| Agent | `debugger` |
-|-------|------------|
-| Trigger | If failures exist |
-| Goal | Quick failure analysis |
-| Exit | Root causes identified |
+> Task(subagent_type="general-purpose", prompt="You are a debugger. Perform quick failure analysis on test failures. Exit when root causes are identified.", description="debugger: Quick failure analysis")
 
 ---
 
@@ -71,5 +60,5 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present results with:
 
-1. ✅ **Pass** — Tests green
-2. 🔧 **Fix** → `/fix:fast`
+1. **Pass** — Tests green
+2. **Fix** → `/fix:fast`