@uluops/setup 0.2.0

package/assets/commands/agents/mcp-validate.md

@@ -0,0 +1,136 @@
+---
+name: mcp-validate
+description: Validate Model Context Protocol (MCP) server implementation. Validates tools, resources, prompts, transport, and security.
+---
+
+# MCP Validator
+Validate Model Context Protocol (MCP) server implementation. Validates tools, resources, prompts, transport, and security.
+
+## Arguments
+
+**Usage:** `/agents:mcp-validate <directory>`
+
+**Examples:**
+- `/agents:mcp-validate ./servers/my-mcp`
+- `/agents:mcp-validate ./mcp-tools`
+- `/agents:mcp-validate .`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running MCP validation on $ARGUMENTS..."
+echo "======================================="
+```
+
+Verify the target directory exists:
+
+```bash
+test -d "$ARGUMENTS" && echo "✓ Directory exists: $ARGUMENTS" || echo "ERROR: Directory '$ARGUMENTS' not found"
+```
+
+Enter and confirm location:
+
+```bash
+cd "$ARGUMENTS" && pwd
+```
+
+Check path exists:
+
+```bash
+[ -e "$ARGUMENTS" ] && echo "✓ $ARGUMENTS exists" || echo "Target directory does not exist"
+```
+
+
+---
+
+## Agent Invocation
+
+Run the MCP Validator agent on the validated target directory:
+
+**Agent:** mcp-validator-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Tools Implementation | 25 | Tool definitions, schemas, descriptions, error handling |
+| Resources Implementation | 20 | Resource URIs, templates, MIME types, subscriptions |
+| Prompts Implementation | 15 | Prompt templates, arguments, usage patterns |
+| Transport & Protocol | 20 | JSON-RPC, initialization, capabilities, versioning |
+| Security & Best Practices | 20 | Input validation, authorization, error handling |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Missing JSON-RPC message handling |
+| **AF-002** | No capability declaration in server initialization |
+| **AF-003** | Tools without inputSchema definitions |
+| **AF-004** | Hardcoded secrets in tool implementations |
+| **AF-005** | No error handling for tool execution failures |
+| **AF-006** | Direct eval() or exec() of user-provided input |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=80** | ✅ PASS | Validation passed, proceed to next phase |
+| **<80** | ❌ FAIL | Validation failed, fix issues before proceeding |
+
+**Note:** Any critical issue triggers FAIL regardless of score.
+
+---
+
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user. The workflow is not complete until results are persisted.
+**1. Get token metrics from buffer:**
+```bash
+agent-metrics buffer list --since 5m -f tracker
+```
+
+**2. Save to tracker (DO THIS FIRST):**
+
+mcp__uluops-tracker__save_features_list
+
+**3. Verify saved:** Compare `json.summary.total_issues` with saved count.
+
+**4. THEN present summary to user.**
+
+### Field Mappings
+
+**From JSON OUTPUT to Tracker:**
+| Source | Tracker Field | Notes |
+|--------|---------------|-------|
+| `json.result.score` | `validators[].score` | Total score |
+| `json.result.decision` | `validators[].status` | PASS/FAIL |
+| `buffer.model` | `validators[].model` | From agent-metrics buffer |
+| `buffer.tokens.input_tokens` | `input_tokens` | Raw input tokens |
+| `buffer.tokens.output_tokens` | `output_tokens` | Output tokens |
+| `buffer.tokens.cache_creation_tokens` | `cache_creation_tokens` | Cache creation |
+| `buffer.tokens.cache_read_tokens` | `cache_read_tokens` | Cache reads |
+| `buffer.tokens.total_effective_tokens` | `total_effective_tokens` | Effective total |
+| `json.categories[].findings[].issues[]` | `recommendations[]` | Flatten nested structure |
+
+**Note:** `json` = agent's JSON OUTPUT, `buffer` = `agent-metrics buffer list -f tracker`
+
+---
+
+## Source
+
+**CDL Schema:** `udl/definition-languages/cdl-schema-v1.1.0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/mcp-validate.command.yaml`
+**Agent:** `agents/mcp-validator-agent.md`

package/assets/commands/agents/optimize.md

@@ -0,0 +1,133 @@
+---
+name: optimize
+description: Run Optimizer agent on a project/directory. Analyzes structure, performance, bundle hygiene, and maintainability. Reports only - does not auto-apply changes.
+---
+
+# Code Optimizer
+Run Optimizer agent on a project/directory. Analyzes structure, performance, bundle hygiene, and maintainability. Reports only - does not auto-apply changes.
+
+## Arguments
+
+**Usage:** `/agents:optimize <directory>`
+
+**Examples:**
+- `/agents:optimize ./src`
+- `/agents:optimize ./packages/api`
+- `/agents:optimize .`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running code optimization analysis on $ARGUMENTS..."
+echo "==================================================="
+```
+
+Verify the target directory exists:
+
+```bash
+test -d "$ARGUMENTS" && echo "✓ Directory exists: $ARGUMENTS" || echo "ERROR: Directory '$ARGUMENTS' not found"
+```
+
+Enter and confirm location:
+
+```bash
+cd "$ARGUMENTS" && pwd
+```
+
+Check path exists:
+
+```bash
+[ -e "$ARGUMENTS" ] && echo "✓ $ARGUMENTS exists" || echo "Target directory does not exist"
+```
+
+
+---
+
+## Agent Invocation
+
+Run the Code Optimizer agent on the validated target directory:
+
+**Agent:** code-optimizer-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 4 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Structure & Duplication | 30 | Code organization, DRY principles, module responsibilities |
+| Performance & Hot Paths | 25 | Async patterns, allocations, request handling, retry logic |
+| Bundle & Dependencies | 20 | Unused code removal, dependency hygiene, tree-shaking |
+| Readability & Maintainability | 25 | Naming, function size, comments, types, code style |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Recommended refactor would change public API signatures |
+| **AF-002** | Refactor requires modifying tests to pass |
+| **AF-003** | Performance optimization trades correctness for speed |
+| **AF-004** | Unsafe memory patterns or race conditions introduced |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=80** | ✅ PASS | Validation passed, proceed to next phase |
+| **<80** | ❌ FAIL | Validation failed, fix issues before proceeding |
+
+**Note:** Any critical issue triggers FAIL regardless of score.
+
+---
+
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user. The workflow is not complete until results are persisted.
+**1. Get token metrics from buffer:**
+```bash
+agent-metrics buffer list --since 5m -f tracker
+```
+
+**2. Save to tracker (DO THIS FIRST):**
+
+mcp__uluops-tracker__save_features_list
+
+**3. Verify saved:** Compare `json.summary.total_issues` with saved count.
+
+**4. THEN present summary to user.**
+
+### Field Mappings
+
+**From JSON OUTPUT to Tracker:**
+| Source | Tracker Field | Notes |
+|--------|---------------|-------|
+| `json.result.score` | `validators[].score` | Total score |
+| `json.result.decision` | `validators[].status` | PASS/FAIL |
+| `buffer.model` | `validators[].model` | From agent-metrics buffer |
+| `buffer.tokens.input_tokens` | `input_tokens` | Raw input tokens |
+| `buffer.tokens.output_tokens` | `output_tokens` | Output tokens |
+| `buffer.tokens.cache_creation_tokens` | `cache_creation_tokens` | Cache creation |
+| `buffer.tokens.cache_read_tokens` | `cache_read_tokens` | Cache reads |
+| `buffer.tokens.total_effective_tokens` | `total_effective_tokens` | Effective total |
+| `json.categories[].findings[].issues[]` | `recommendations[]` | Flatten nested structure |
+
+**Note:** `json` = agent's JSON OUTPUT, `buffer` = `agent-metrics buffer list -f tracker`
+
+---
+
+## Source
+
+**CDL Schema:** `udl/definition-languages/cdl-schema-v1.1.0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/optimize.command.yaml`
+**Agent:** `agents/code-optimizer-agent.md`

package/assets/commands/agents/pattern-analyzer.md

@@ -0,0 +1,126 @@
+---
+name: pattern-analyzer
+description: Analyzes ecosystem-wide patterns across all agents, commands, and workflows. Detects conventions, identifies inconsistencies, and learns from validation failures.
+---
+
+# Pattern Analyzer
+Analyzes ecosystem-wide patterns across all agents, commands, and workflows. Detects conventions, identifies inconsistencies, and learns from validation failures.
+
+## Arguments
+
+**Usage:** `/agents:pattern-analyzer <directory>`
+
+**Examples:**
+- `/agents:pattern-analyzer agents/`
+- `/agents:pattern-analyzer commands/`
+- `/agents:pattern-analyzer .`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running pattern analysis..."
+echo "==========================="
+```
+
+Verify the target directory exists:
+
+```bash
+test -d "$ARGUMENTS" && echo "✓ Directory exists: $ARGUMENTS" || echo "ERROR: Directory '$ARGUMENTS' not found"
+```
+
+Enter and confirm location:
+
+```bash
+cd "$ARGUMENTS" && pwd
+```
+
+
+---
+
+## Agent Invocation
+
+Run the Pattern Analyzer agent on the validated target directory:
+
+**Agent:** prompt-pattern-analyzer-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 4 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Convention Extraction | 25 | Identifies scoring frameworks, decision keywords, thresholds, and structural patterns |
+| Consistency Analysis | 30 | Measures terminology variance, flags outliers, quantifies drift |
+| Evolution Opportunities | 25 | Identifies redundancy, refactoring opportunities, and emerging best practices |
+| Failure Pattern Learning | 20 | Analyzes historical audit scores and extracts common failure modes |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Fewer than 5 agents in ecosystem |
+| **AF-002** | No agents discovered at expected paths |
+| **AF-003** | High variance prevents pattern extraction |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=75** | ✅ PASS | Validation passed, proceed to next phase |
+| **<75** | ❌ FAIL | Validation failed, fix issues before proceeding |
+
+**Note:** Any critical issue triggers FAIL regardless of score.
+
+---
+
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user. The workflow is not complete until results are persisted.
+**1. Get token metrics from buffer:**
+```bash
+agent-metrics buffer list --since 5m -f tracker
+```
+
+**2. Save to tracker (DO THIS FIRST):**
+
+mcp__uluops-tracker__save_features_list
+
+**3. Verify saved:** Compare `json.summary.total_issues` with saved count.
+
+**4. THEN present summary to user.**
+
+### Field Mappings
+
+**From JSON OUTPUT to Tracker:**
+| Source | Tracker Field | Notes |
+|--------|---------------|-------|
+| `json.result.score` | `validators[].score` | Total score |
+| `json.result.decision` | `validators[].status` | PASS/FAIL |
+| `buffer.model` | `validators[].model` | From agent-metrics buffer |
+| `buffer.tokens.input_tokens` | `input_tokens` | Raw input tokens |
+| `buffer.tokens.output_tokens` | `output_tokens` | Output tokens |
+| `buffer.tokens.cache_creation_tokens` | `cache_creation_tokens` | Cache creation |
+| `buffer.tokens.cache_read_tokens` | `cache_read_tokens` | Cache reads |
+| `buffer.tokens.total_effective_tokens` | `total_effective_tokens` | Effective total |
+| `json.categories[].findings[].issues[]` | `recommendations[]` | Flatten nested structure |
+
+**Note:** `json` = agent's JSON OUTPUT, `buffer` = `agent-metrics buffer list -f tracker`
+
+---
+
+## Source
+
+**CDL Schema:** `udl/definition-languages/cdl-schema-v1.1.0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/pattern-analyzer.command.yaml`
+**Agent:** `agents/prompt-pattern-analyzer-agent.md`

package/assets/commands/agents/prompt-quality.md

@@ -0,0 +1,134 @@
+---
+name: prompt-quality
+description: Validates prompts against prompt engineering best practices for clarity, context, structure, and effectiveness.
+---
+
+# Prompt Quality Validator
+Validates prompts against prompt engineering best practices for clarity, context, structure, and effectiveness.
+
+## Arguments
+
+**Usage:** `/agents:prompt-quality <directory>`
+
+**Examples:**
+- `/agents:prompt-quality agents/my-agent.md`
+- `/agents:prompt-quality commands/my-cmd.md`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running prompt quality validation on $ARGUMENTS..."
+echo "=================================================="
+```
+
+Verify the target directory exists:
+
+```bash
+test -d "$ARGUMENTS" && echo "✓ Directory exists: $ARGUMENTS" || echo "ERROR: Directory '$ARGUMENTS' not found"
+```
+
+Enter and confirm location:
+
+```bash
+cd "$ARGUMENTS" && pwd
+```
+
+Check file exists:
+
+```bash
+[ -f "$ARGUMENTS" ] && echo "✓ $ARGUMENTS found" || echo "Target file does not exist"
+```
+
+
+---
+
+## Agent Invocation
+
+Run the Prompt Quality Validator agent on the validated target directory:
+
+**Agent:** prompt-quality-validator-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Clarity & Specificity | 25 | Validates task definition, scope, format, vagueness, and examples |
+| Context & Background | 20 | Validates context sufficiency, audience, constraints, and role assignment |
+| Structure & Organization | 20 | Validates section headers, step decomposition, formatting, and modularity |
+| Effectiveness Techniques | 20 | Validates few-shot examples, chain-of-thought, error prevention, and edge cases |
+| Quality Assurance | 15 | Validates success criteria, testability, and instruction consistency |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Missing task definition/mission |
+| **AF-002** | No output format specification |
+| **AF-003** | Conflicting instructions detected |
+| **AF-004** | More than 3 vague qualifiers in directives |
+| **AF-005** | Complex pattern with zero examples |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=75** | ✅ PASS | Validation passed, proceed to next phase |
+| **<75** | ❌ FAIL | Validation failed, fix issues before proceeding |
+
+**Note:** Any critical issue triggers FAIL regardless of score.
+
+---
+
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user. The workflow is not complete until results are persisted.
+**1. Get token metrics from buffer:**
+```bash
+agent-metrics buffer list --since 5m -f tracker
+```
+
+**2. Save to tracker (DO THIS FIRST):**
+
+mcp__uluops-tracker__save_features_list
+
+**3. Verify saved:** Compare `json.summary.total_issues` with saved count.
+
+**4. THEN present summary to user.**
+
+### Field Mappings
+
+**From JSON OUTPUT to Tracker:**
+| Source | Tracker Field | Notes |
+|--------|---------------|-------|
+| `json.result.score` | `validators[].score` | Total score |
+| `json.result.decision` | `validators[].status` | PASS/FAIL |
+| `buffer.model` | `validators[].model` | From agent-metrics buffer |
+| `buffer.tokens.input_tokens` | `input_tokens` | Raw input tokens |
+| `buffer.tokens.output_tokens` | `output_tokens` | Output tokens |
+| `buffer.tokens.cache_creation_tokens` | `cache_creation_tokens` | Cache creation |
+| `buffer.tokens.cache_read_tokens` | `cache_read_tokens` | Cache reads |
+| `buffer.tokens.total_effective_tokens` | `total_effective_tokens` | Effective total |
+| `json.categories[].findings[].issues[]` | `recommendations[]` | Flatten nested structure |
+
+**Note:** `json` = agent's JSON OUTPUT, `buffer` = `agent-metrics buffer list -f tracker`
+
+---
+
+## Source
+
+**CDL Schema:** `udl/definition-languages/cdl-schema-v1.1.0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/prompt-quality.command.yaml`
+**Agent:** `agents/prompt-quality-validator-agent.md`

package/assets/commands/agents/prompt-validate.md

@@ -0,0 +1,135 @@
+---
+name: prompt-validate
+description: Validates AI agent prompts for quality and consistency before deployment. Run before adding new agents to the project.
+---
+
+# Prompt Validator
+Validates AI agent prompts for quality and consistency before deployment. Run before adding new agents to the project.
+
+## Arguments
+
+**Usage:** `/agents:prompt-validate <directory>`
+
+**Examples:**
+- `/agents:prompt-validate agents/my-agent.md`
+- `/agents:prompt-validate vdl/my-validator.yaml`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running prompt validation on $ARGUMENTS..."
+echo "=========================================="
+```
+
+Verify the target directory exists:
+
+```bash
+test -d "$ARGUMENTS" && echo "✓ Directory exists: $ARGUMENTS" || echo "ERROR: Directory '$ARGUMENTS' not found"
+```
+
+Enter and confirm location:
+
+```bash
+cd "$ARGUMENTS" && pwd
+```
+
+Check file exists:
+
+```bash
+[ -f "$ARGUMENTS" ] && echo "✓ $ARGUMENTS found" || echo "Target file does not exist"
+```
+
+
+---
+
+## Agent Invocation
+
+Run the Prompt Validator agent on the validated target directory:
+
+**Agent:** prompt-engineer-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Clarity & Specificity | 25 | Mission is unambiguous, success criteria explicit, output format clear |
+| Structure & Organization | 20 | Logical flow, consistent formatting, and information hierarchy |
+| Completeness | 25 | Edge cases, fallbacks, error handling, examples, and constraints |
+| Effectiveness | 20 | Scoring is actionable, criteria measurable, output usable |
+| Consistency | 10 | Adherence to project conventions and terminology |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Undefined or vague mission statement |
+| **AF-002** | No output format specification |
+| **AF-003** | Conflicting instructions in different sections |
+| **AF-004** | Subjective-only decision criteria |
+| **AF-005** | Missing error/edge case handling |
+| **AF-006** | Scoring points that cannot be objectively verified |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=75** | ✅ PASS | Validation passed, proceed to next phase |
+| **<75** | ❌ FAIL | Validation failed, fix issues before proceeding |
+
+**Note:** Any critical issue triggers FAIL regardless of score.
+
+---
+
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user. The workflow is not complete until results are persisted.
+**1. Get token metrics from buffer:**
+```bash
+agent-metrics buffer list --since 5m -f tracker
+```
+
+**2. Save to tracker (DO THIS FIRST):**
+
+mcp__uluops-tracker__save_features_list
+
+**3. Verify saved:** Compare `json.summary.total_issues` with saved count.
+
+**4. THEN present summary to user.**
+
+### Field Mappings
+
+**From JSON OUTPUT to Tracker:**
+| Source | Tracker Field | Notes |
+|--------|---------------|-------|
+| `json.result.score` | `validators[].score` | Total score |
+| `json.result.decision` | `validators[].status` | PASS/FAIL |
+| `buffer.model` | `validators[].model` | From agent-metrics buffer |
+| `buffer.tokens.input_tokens` | `input_tokens` | Raw input tokens |
+| `buffer.tokens.output_tokens` | `output_tokens` | Output tokens |
+| `buffer.tokens.cache_creation_tokens` | `cache_creation_tokens` | Cache creation |
+| `buffer.tokens.cache_read_tokens` | `cache_read_tokens` | Cache reads |
+| `buffer.tokens.total_effective_tokens` | `total_effective_tokens` | Effective total |
+| `json.categories[].findings[].issues[]` | `recommendations[]` | Flatten nested structure |
+
+**Note:** `json` = agent's JSON OUTPUT, `buffer` = `agent-metrics buffer list -f tracker`
+
+---
+
+## Source
+
+**CDL Schema:** `udl/definition-languages/cdl-schema-v1.1.0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/prompt-validate.command.yaml`
+**Agent:** `agents/prompt-engineer-agent.md`