xtrm-tools 0.7.3 → 0.7.7

package/.xtrm/skills/optional/architecture-design/prompt-engineering-patterns/scripts/optimize-prompt.py

@@ -0,0 +1,279 @@
+#!/usr/bin/env python3
+"""
+Prompt Optimization Script
+
+Automatically test and optimize prompts using A/B testing and metrics tracking.
+"""
+
+import json
+import time
+from typing import List, Dict, Any
+from dataclasses import dataclass
+from concurrent.futures import ThreadPoolExecutor
+import numpy as np
+
+
+@dataclass
+class TestCase:
+    input: Dict[str, Any]
+    expected_output: str
+    metadata: Dict[str, Any] = None
+
+
+class PromptOptimizer:
+    def __init__(self, llm_client, test_suite: List[TestCase]):
+        self.client = llm_client
+        self.test_suite = test_suite
+        self.results_history = []
+        self.executor = ThreadPoolExecutor()
+
+    def shutdown(self):
+        """Shutdown the thread pool executor."""
+        self.executor.shutdown(wait=True)
+
+    def evaluate_prompt(self, prompt_template: str, test_cases: List[TestCase] = None) -> Dict[str, float]:
+        """Evaluate a prompt template against test cases in parallel."""
+        if test_cases is None:
+            test_cases = self.test_suite
+
+        metrics = {
+            'accuracy': [],
+            'latency': [],
+            'token_count': [],
+            'success_rate': []
+        }
+
+        def process_test_case(test_case):
+            start_time = time.time()
+
+            # Render prompt with test case inputs
+            prompt = prompt_template.format(**test_case.input)
+
+            # Get LLM response
+            response = self.client.complete(prompt)
+
+            # Measure latency
+            latency = time.time() - start_time
+
+            # Calculate individual metrics
+            token_count = len(prompt.split()) + len(response.split())
+            success = 1 if response else 0
+            accuracy = self.calculate_accuracy(response, test_case.expected_output)
+
+            return {
+                'latency': latency,
+                'token_count': token_count,
+                'success_rate': success,
+                'accuracy': accuracy
+            }
+
+        # Run test cases in parallel
+        results = list(self.executor.map(process_test_case, test_cases))
+
+        # Aggregate metrics
+        for result in results:
+            metrics['latency'].append(result['latency'])
+            metrics['token_count'].append(result['token_count'])
+            metrics['success_rate'].append(result['success_rate'])
+            metrics['accuracy'].append(result['accuracy'])
+
+        return {
+            'avg_accuracy': np.mean(metrics['accuracy']),
+            'avg_latency': np.mean(metrics['latency']),
+            'p95_latency': np.percentile(metrics['latency'], 95),
+            'avg_tokens': np.mean(metrics['token_count']),
+            'success_rate': np.mean(metrics['success_rate'])
+        }
+
+    def calculate_accuracy(self, response: str, expected: str) -> float:
+        """Calculate accuracy score between response and expected output."""
+        # Simple exact match
+        if response.strip().lower() == expected.strip().lower():
+            return 1.0
+
+        # Partial match using word overlap
+        response_words = set(response.lower().split())
+        expected_words = set(expected.lower().split())
+
+        if not expected_words:
+            return 0.0
+
+        overlap = len(response_words & expected_words)
+        return overlap / len(expected_words)
+
+    def optimize(self, base_prompt: str, max_iterations: int = 5) -> Dict[str, Any]:
+        """Iteratively optimize a prompt."""
+        current_prompt = base_prompt
+        best_prompt = base_prompt
+        best_score = 0
+        current_metrics = None
+
+        for iteration in range(max_iterations):
+            print(f"\nIteration {iteration + 1}/{max_iterations}")
+
+            # Evaluate current prompt
+            # Bolt Optimization: Avoid re-evaluating if we already have metrics from previous iteration
+            if current_metrics:
+                metrics = current_metrics
+            else:
+                metrics = self.evaluate_prompt(current_prompt)
+
+            print(f"Accuracy: {metrics['avg_accuracy']:.2f}, Latency: {metrics['avg_latency']:.2f}s")
+
+            # Track results
+            self.results_history.append({
+                'iteration': iteration,
+                'prompt': current_prompt,
+                'metrics': metrics
+            })
+
+            # Update best if improved
+            if metrics['avg_accuracy'] > best_score:
+                best_score = metrics['avg_accuracy']
+                best_prompt = current_prompt
+
+            # Stop if good enough
+            if metrics['avg_accuracy'] > 0.95:
+                print("Achieved target accuracy!")
+                break
+
+            # Generate variations for next iteration
+            variations = self.generate_variations(current_prompt, metrics)
+
+            # Test variations and pick best
+            best_variation = current_prompt
+            best_variation_score = metrics['avg_accuracy']
+            best_variation_metrics = metrics
+
+            for variation in variations:
+                var_metrics = self.evaluate_prompt(variation)
+                if var_metrics['avg_accuracy'] > best_variation_score:
+                    best_variation_score = var_metrics['avg_accuracy']
+                    best_variation = variation
+                    best_variation_metrics = var_metrics
+
+            current_prompt = best_variation
+            current_metrics = best_variation_metrics
+
+        return {
+            'best_prompt': best_prompt,
+            'best_score': best_score,
+            'history': self.results_history
+        }
+
+    def generate_variations(self, prompt: str, current_metrics: Dict) -> List[str]:
+        """Generate prompt variations to test."""
+        variations = []
+
+        # Variation 1: Add explicit format instruction
+        variations.append(prompt + "\n\nProvide your answer in a clear, concise format.")
+
+        # Variation 2: Add step-by-step instruction
+        variations.append("Let's solve this step by step.\n\n" + prompt)
+
+        # Variation 3: Add verification step
+        variations.append(prompt + "\n\nVerify your answer before responding.")
+
+        # Variation 4: Make more concise
+        concise = self.make_concise(prompt)
+        if concise != prompt:
+            variations.append(concise)
+
+        # Variation 5: Add examples (if none present)
+        if "example" not in prompt.lower():
+            variations.append(self.add_examples(prompt))
+
+        return variations[:3]  # Return top 3 variations
+
+    def make_concise(self, prompt: str) -> str:
+        """Remove redundant words to make prompt more concise."""
+        replacements = [
+            ("in order to", "to"),
+            ("due to the fact that", "because"),
+            ("at this point in time", "now"),
+            ("in the event that", "if"),
+        ]
+
+        result = prompt
+        for old, new in replacements:
+            result = result.replace(old, new)
+
+        return result
+
+    def add_examples(self, prompt: str) -> str:
+        """Add example section to prompt."""
+        return f"""{prompt}
+
+Example:
+Input: Sample input
+Output: Sample output
+"""
+
+    def compare_prompts(self, prompt_a: str, prompt_b: str) -> Dict[str, Any]:
+        """A/B test two prompts."""
+        print("Testing Prompt A...")
+        metrics_a = self.evaluate_prompt(prompt_a)
+
+        print("Testing Prompt B...")
+        metrics_b = self.evaluate_prompt(prompt_b)
+
+        return {
+            'prompt_a_metrics': metrics_a,
+            'prompt_b_metrics': metrics_b,
+            'winner': 'A' if metrics_a['avg_accuracy'] > metrics_b['avg_accuracy'] else 'B',
+            'improvement': abs(metrics_a['avg_accuracy'] - metrics_b['avg_accuracy'])
+        }
+
+    def export_results(self, filename: str):
+        """Export optimization results to JSON."""
+        with open(filename, 'w') as f:
+            json.dump(self.results_history, f, indent=2)
+
+
+def main():
+    # Example usage
+    test_suite = [
+        TestCase(
+            input={'text': 'This movie was amazing!'},
+            expected_output='Positive'
+        ),
+        TestCase(
+            input={'text': 'Worst purchase ever.'},
+            expected_output='Negative'
+        ),
+        TestCase(
+            input={'text': 'It was okay, nothing special.'},
+            expected_output='Neutral'
+        )
+    ]
+
+    # Mock LLM client for demonstration
+    class MockLLMClient:
+        def complete(self, prompt):
+            # Simulate LLM response
+            if 'amazing' in prompt:
+                return 'Positive'
+            elif 'worst' in prompt.lower():
+                return 'Negative'
+            else:
+                return 'Neutral'
+
+    optimizer = PromptOptimizer(MockLLMClient(), test_suite)
+
+    try:
+        base_prompt = "Classify the sentiment of: {text}\nSentiment:"
+
+        results = optimizer.optimize(base_prompt)
+
+        print("\n" + "="*50)
+        print("Optimization Complete!")
+        print(f"Best Accuracy: {results['best_score']:.2f}")
+        print(f"Best Prompt:\n{results['best_prompt']}")
+
+        optimizer.export_results('optimization_results.json')
+    finally:
+        optimizer.shutdown()
+
+
+if __name__ == '__main__':
+    main()

package/.xtrm/skills/optional/architecture-design/subagent-driven-development/SKILL.md

@@ -0,0 +1,277 @@
+---
+name: subagent-driven-development
+description: Use when executing implementation plans with independent tasks in the current session
+---
+
+# Subagent-Driven Development
+
+Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
+
+**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
+
+**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Have implementation plan?" [shape=diamond];
+    "Tasks mostly independent?" [shape=diamond];
+    "Stay in this session?" [shape=diamond];
+    "subagent-driven-development" [shape=box];
+    "executing-plans" [shape=box];
+    "Manual execution or brainstorm first" [shape=box];
+
+    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
+    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
+    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
+    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
+    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
+    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
+}
+```
+
+**vs. Executing Plans (parallel session):**
+- Same session (no context switch)
+- Fresh subagent 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)
+
+## The Process
+
+```dot
+digraph process {
+    rankdir=TB;
+
+    subgraph cluster_per_task {
+        label="Per Task";
+        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
+        "Implementer subagent 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];
+        "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];
+    "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"];
+    "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";
+}
+```
+
+## Model Selection
+
+Use the least powerful model that can handle each role to conserve cost and increase speed.
+
+**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
+
+**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
+
+**Architecture, design, and review tasks**: use the most capable available model.
+
+**Task complexity signals:**
+- Touches 1-2 files with a complete spec → cheap model
+- Touches multiple files with integration concerns → standard model
+- Requires design judgment or broad codebase understanding → most capable model
+
+## Handling Implementer Status
+
+Implementer subagents report one of four statuses. Handle each appropriately:
+
+**DONE:** Proceed to spec compliance review.
+
+**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
+
+**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
+
+**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
+1. If it's a context problem, provide more context and re-dispatch with the same model
+2. If the task requires more reasoning, re-dispatch with a more capable model
+3. If the task is too large, break it into smaller pieces
+4. If the plan itself is wrong, escalate to the human
+
+**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
+
+## 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
+
+## Example Workflow
+
+```
+You: I'm using Subagent-Driven Development to execute this plan.
+
+[Read plan file once: docs/superpowers/plans/feature-plan.md]
+[Extract all 5 tasks with full text and context]
+[Create TodoWrite with all tasks]
+
+Task 1: Hook installation script
+
+[Get Task 1 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: "Before I begin - should the hook be installed at user or system level?"
+
+You: "User level (~/.config/superpowers/hooks/)"
+
+Implementer: "Got it. Implementing now..."
+[Later] Implementer:
+  - Implemented install-hook command
+  - Added tests, 5/5 passing
+  - Self-review: Found I missed --force flag, added it
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra
+
+[Get git SHAs, dispatch code quality reviewer]
+Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
+
+[Mark Task 1 complete]
+
+Task 2: Recovery modes
+
+[Get Task 2 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: [No questions, proceeds]
+Implementer:
+  - Added verify/repair modes
+  - 8/8 tests passing
+  - Self-review: All good
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ❌ Issues:
+  - Missing: Progress reporting (spec says "report every 100 items")
+  - Extra: Added --json flag (not requested)
+
+[Implementer fixes issues]
+Implementer: Removed --json flag, added progress reporting
+
+[Spec reviewer reviews again]
+Spec reviewer: ✅ Spec compliant now
+
+[Dispatch code quality reviewer]
+Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
+
+[Implementer fixes]
+Implementer: Extracted PROGRESS_INTERVAL constant
+
+[Code reviewer reviews again]
+Code reviewer: ✅ Approved
+
+[Mark Task 2 complete]
+
+...
+
+[After all tasks]
+[Dispatch final code-reviewer]
+Final reviewer: All requirements met, ready to merge
+
+Done!
+```
+
+## Advantages
+
+**vs. Manual execution:**
+- Subagents follow TDD naturally
+- Fresh context per task (no confusion)
+- Parallel-safe (subagents don't interfere)
+- Subagent can ask questions (before AND during work)
+
+**vs. Executing Plans:**
+- Same session (no handoff)
+- Continuous progress (no waiting)
+- Review checkpoints automatic
+
+**Efficiency gains:**
+- No file reading overhead (controller provides full text)
+- Controller curates exactly what context is needed
+- Subagent gets complete information upfront
+- Questions surfaced before work begins (not after)
+
+**Quality gates:**
+- Self-review catches issues before handoff
+- Two-stage review: spec compliance, then code quality
+- Review loops ensure fixes actually work
+- Spec compliance prevents over/under-building
+- Code quality ensures implementation is well-built
+
+**Cost:**
+- More subagent 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)
+
+## Red Flags
+
+**Never:**
+- Start implementation on main/master branch without explicit user consent
+- 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)
+- 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:**
+- Answer clearly and completely
+- Provide additional context if needed
+- Don't rush them into implementation
+
+**If reviewer finds issues:**
+- Implementer (same subagent) fixes them
+- Reviewer reviews again
+- Repeat until approved
+- Don't skip the re-review
+
+**If subagent fails task:**
+- Dispatch fix subagent with specific instructions
+- Don't try to fix manually (context pollution)
+
+## Integration
+
+**Required workflow skills:**
+- **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting
+- **superpowers:writing-plans** - Creates the plan this skill executes
+- **superpowers:requesting-code-review** - Code review template for reviewer subagents
+- **superpowers:finishing-a-development-branch** - Complete development after all tasks
+
+**Subagents should use:**
+- **superpowers:test-driven-development** - Subagents follow TDD for each task
+
+**Alternative workflow:**
+- **superpowers:executing-plans** - Use for parallel session instead of same-session execution

package/.xtrm/skills/optional/architecture-design/subagent-driven-development/code-quality-reviewer-prompt.md

@@ -0,0 +1,26 @@
+# Code Quality Reviewer Prompt Template
+
+Use this template when dispatching a code quality reviewer subagent.
+
+**Purpose:** Verify implementation is well-built (clean, tested, maintainable)
+
+**Only dispatch after spec compliance review passes.**
+
+```
+Task tool (superpowers:code-reviewer):
+  Use template at requesting-code-review/code-reviewer.md
+
+  WHAT_WAS_IMPLEMENTED: [from implementer's report]
+  PLAN_OR_REQUIREMENTS: Task N from [plan-file]
+  BASE_SHA: [commit before task]
+  HEAD_SHA: [current commit]
+  DESCRIPTION: [task summary]
+```
+
+**In addition to standard code quality concerns, the reviewer should check:**
+- Does each file have one clear responsibility with a well-defined interface?
+- Are units decomposed so they can be understood and tested independently?
+- Is the implementation following the file structure from the plan?
+- Did this implementation create new files that are already large, or significantly grow existing files? (Don't flag pre-existing file sizes — focus on what this change contributed.)
+
+**Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment

package/.xtrm/skills/optional/architecture-design/subagent-driven-development/implementer-prompt.md

@@ -0,0 +1,113 @@
+# Implementer Subagent Prompt Template
+
+Use this template when dispatching an implementer subagent.
+
+```
+Task tool (general-purpose):
+  description: "Implement Task N: [task name]"
+  prompt: |
+    You are implementing Task N: [task name]
+
+    ## Task Description
+
+    [FULL TEXT of task from plan - paste it here, don't make subagent read file]
+
+    ## Context
+
+    [Scene-setting: where this fits, dependencies, architectural context]
+
+    ## Before You Begin
+
+    If you have questions about:
+    - The requirements or acceptance criteria
+    - The approach or implementation strategy
+    - Dependencies or assumptions
+    - Anything unclear in the task description
+
+    **Ask them now.** Raise any concerns before starting work.
+
+    ## Your Job
+
+    Once you're clear on requirements:
+    1. Implement exactly what the task specifies
+    2. Write tests (following TDD if task says to)
+    3. Verify implementation works
+    4. Commit your work
+    5. Self-review (see below)
+    6. Report back
+
+    Work from: [directory]
+
+    **While you work:** If you encounter something unexpected or unclear, **ask questions**.
+    It's always OK to pause and clarify. Don't guess or make assumptions.
+
+    ## Code Organization
+
+    You reason best about code you can hold in context at once, and your edits are more
+    reliable when files are focused. Keep this in mind:
+    - Follow the file structure defined in the plan
+    - Each file should have one clear responsibility with a well-defined interface
+    - If a file you're creating is growing beyond the plan's intent, stop and report
+      it as DONE_WITH_CONCERNS — don't split files on your own without plan guidance
+    - If an existing file you're modifying is already large or tangled, work carefully
+      and note it as a concern in your report
+    - In existing codebases, follow established patterns. Improve code you're touching
+      the way a good developer would, but don't restructure things outside your task.
+
+    ## When You're in Over Your Head
+
+    It is always OK to stop and say "this is too hard for me." Bad work is worse than
+    no work. You will not be penalized for escalating.
+
+    **STOP and escalate when:**
+    - The task requires architectural decisions with multiple valid approaches
+    - You need to understand code beyond what was provided and can't find clarity
+    - You feel uncertain about whether your approach is correct
+    - The task involves restructuring existing code in ways the plan didn't anticipate
+    - You've been reading file after file trying to understand the system without progress
+
+    **How to escalate:** Report back with status BLOCKED or NEEDS_CONTEXT. Describe
+    specifically what you're stuck on, what you've tried, and what kind of help you need.
+    The controller can provide more context, re-dispatch with a more capable model,
+    or break the task into smaller pieces.
+
+    ## Before Reporting Back: Self-Review
+
+    Review your work with fresh eyes. Ask yourself:
+
+    **Completeness:**
+    - Did I fully implement everything in the spec?
+    - Did I miss any requirements?
+    - Are there edge cases I didn't handle?
+
+    **Quality:**
+    - Is this my best work?
+    - Are names clear and accurate (match what things do, not how they work)?
+    - Is the code clean and maintainable?
+
+    **Discipline:**
+    - Did I avoid overbuilding (YAGNI)?
+    - Did I only build what was requested?
+    - Did I follow existing patterns in the codebase?
+
+    **Testing:**
+    - Do tests actually verify behavior (not just mock behavior)?
+    - Did I follow TDD if required?
+    - Are tests comprehensive?
+
+    If you find issues during self-review, fix them now before reporting.
+
+    ## Report Format
+
+    When done, report:
+    - **Status:** DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
+    - What you implemented (or what you attempted, if blocked)
+    - What you tested and test results
+    - Files changed
+    - Self-review findings (if any)
+    - Any issues or concerns
+
+    Use DONE_WITH_CONCERNS if you completed the work but have doubts about correctness.
+    Use BLOCKED if you cannot complete the task. Use NEEDS_CONTEXT if you need
+    information that wasn't provided. Never silently produce work you're unsure about.
+```