@uluops/setup 0.2.0

package/assets/commands/agents/aristotle-validator.md

@@ -0,0 +1,114 @@
+---
+name: aristotle-validator
+description: Performs Aristotelian teleological alignment validation on any artifact. Checks whether means are properly ordered toward ends, whether components fulfill their natural function, and whether category errors exist. Decision: ALIGNED/MISALIGNED.
+---
+
+# Aristotle Validator
+Performs Aristotelian teleological alignment validation on any artifact — code, specs, plans, architectures, or documents. Cognitive lens agent from the Cognitive Lens Library.
+
+## Arguments
+
+**Usage:** `/agents:aristotle-validator <target>`
+
+**Examples:**
+- `/agents:aristotle-validator uluops-registry-api/`
+- `/agents:aristotle-validator udl/adl/v3/code-validator.agent.yaml`
+- `/agents:aristotle-validator docs/specs/cognitive-lens-library-spec.md`
+- `/agents:aristotle-validator packages/cli/`
+
+**Target:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+Verify the target exists:
+
+```bash
+[ -e "$ARGUMENTS" ] && echo "✓ $ARGUMENTS exists" || echo "Target file or directory does not exist"
+```
+
+---
+
+## Agent Invocation
+
+Run the Aristotle Validator agent on the target:
+
+**Agent:** aristotle-validator-agent.md
+**Model:** Opus
+**Target:** $ARGUMENTS
+
+The agent performs Aristotelian teleological alignment across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Teleological Coherence | 25 | Telos identified, means-end chain traced, misalignment surfaced |
+| Categorical Correctness | 25 | Category errors detected, natural function assessed |
+| Essential/Accidental Distinction | 20 | Essential properties preserved, accidentals not treated as essential |
+| Four-Cause Completeness | 15 | Causal grounding, efficient/final causes distinguished |
+| Potentiality Assessment | 15 | Actualization trajectory, impediments identified |
+
+## Auto-Fail Conditions
+
+| ID | Condition | Severity |
+|----|-----------|----------|
+| AF-001 | No genuine teleological alignment assessment performed | Critical |
+| AF-002 | Telos assumed rather than identified and defended | Critical |
+| AF-003 | Technical quality evaluation substituted for teleological alignment | Critical |
+| AF-004 | No category error detection performed | Critical |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=70** | ALIGNED | Artifact's components are coherently ordered toward an identifiable telos |
+| **<70** | MISALIGNED | Components serve unclear or contradictory purposes, or analysis is incomplete |
+
+**Note:** This is an advisory decision, not a deployment gate. ALIGNED means the artifact's parts serve a coherent purpose — not that the artifact is correct or desirable.
+
+---
+
+## PERSIST TO TRACKER (Required)
+
+> **IMPORTANT:** Save to tracker IMMEDIATELY after agent completes, BEFORE presenting the summary to the user.
+
+**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` | ALIGNED/MISALIGNED |
+| `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
+
+**ADL Schema:** `udl/definition-languages/adl-schema-v1.10.0.json`
+**ADL Source:** `udl/adl/v3/aristotle-validator.agent.yaml`
+**Agent:** `agents/v3/aristotle-validator-agent.md`
+**Spec:** `docs/specs/cognitive-lens-library-spec.md`

package/assets/commands/agents/assumption-excavator.md

@@ -0,0 +1,114 @@
+---
+name: assumption-excavator
+description: Surfaces implicit assumptions buried in any artifact — agent definitions, prompts, specs, plans, workflows, or documents. Produces a ranked assumption inventory with fragility scores.
+---
+
+# Assumption Excavator
+Surfaces implicit assumptions buried in any artifact — agent definitions, prompts, specs, plans, workflows, or documents. Produces a ranked assumption inventory with fragility scores.
+
+## Arguments
+
+**Usage:** `/agents:assumption-excavator <directory>`
+
+**Examples:**
+- `/agents:assumption-excavator udl/adl/v3/code-validator.agent.yaml`
+- `/agents:assumption-excavator agents/my-agent.md`
+- `/agents:assumption-excavator docs/architecture.md`
+- `/agents:assumption-excavator specs/api-spec.md`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running assumption excavation 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 file or directory does not exist"
+```
+
+
+---
+
+## Agent Invocation
+
+Run the Assumption Excavator agent on the validated target directory:
+
+**Agent:** assumption-excavator-agent.md
+**Model:** Opus
+**Target:** $ARGUMENTS
+
+The agent performs validation across multiple categories (100 points total).
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=70** | ✅ PASS | Validation passed, proceed to next phase |
+| **<70** | ❌ 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_3_0.json`
+**CDL Source:** `/home/alexs/uluops/uluops-agent-workflows/udl/cdl/v1/assumption-excavator.command.yaml`
+**Agent:** `agents/assumption-excavator-agent.md`

package/assets/commands/agents/audit.md

@@ -0,0 +1,136 @@
+---
+name: audit
+description: Deep runtime correctness audit. Catches async bugs, null dereferences, silent failures, and edge cases that pass all other validators. Use as FINAL gate before ship.
+---
+
+# Code Auditor
+Deep runtime correctness audit. Catches async bugs, null dereferences, silent failures, and edge cases that pass all other validators. Use as FINAL gate before ship.
+
+## Arguments
+
+**Usage:** `/agents:audit <directory>`
+
+**Examples:**
+- `/agents:audit ./src`
+- `/agents:audit ./packages/core`
+- `/agents:audit .`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running deep code audit 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 Auditor agent on the validated target directory:
+
+**Agent:** code-auditor-agent.md
+**Model:** Opus
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Async Safety | 25 | Validates asynchronous operations complete correctly and errors propagate |
+| Null/Undefined Safety | 25 | Validates optional values are handled before use |
+| Error Handling | 20 | Validates errors are caught, preserved, and propagated correctly |
+| Data Integrity | 15 | Validates data transformations preserve correctness |
+| API Boundary Safety | 15 | Validates external data and services handled defensively |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Unhandled promise rejection in production path |
+| **AF-002** | Empty catch block in error-critical code |
+| **AF-003** | .find() result used without null check |
+| **AF-004** | JSON.parse on external data without try/catch |
+| **AF-005** | Fire-and-forget async that could lose user data |
+| **AF-006** | Silent failure that corrupts state |
+
+---
+
+## 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/audit.command.yaml`
+**Agent:** `agents/code-auditor-agent.md`

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

@@ -0,0 +1,133 @@
+---
+name: docs-validate
+description: Validates comprehensive documentation quality including JSDoc/TSDoc, API specs, changelog, and markdown. Complements public-interface for projects with significant documentation.
+---
+
+# Documentation Validator
+Validates comprehensive documentation quality including JSDoc/TSDoc, API specs, changelog, and markdown. Complements public-interface for projects with significant documentation.
+
+## Arguments
+
+**Usage:** `/agents:docs-validate <directory>`
+
+**Examples:**
+- `/agents:docs-validate ./docs`
+- `/agents:docs-validate .`
+- `/agents:docs-validate ./packages/api`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running documentation 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 Documentation Validator agent on the validated target directory:
+
+**Agent:** docs-validator-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| JSDoc/TSDoc Coverage | 30 | Public exports have complete, accurate documentation comments |
+| API Documentation | 25 | OpenAPI/Swagger specs accurate and complete for API projects |
+| Changelog Quality | 15 | CHANGELOG.md follows conventions and tracks changes accurately |
+| Markdown Quality | 15 | Markdown files are well-formed with valid links |
+| Documentation Organization | 15 | Documentation is discoverable and well-organized |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **** | No JSDoc on any public exports |
+| **** | API spec significantly out of sync with implementation |
+| **** | Major version release not in changelog |
+
+---
+
+## 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/docs-validate.command.yaml`
+**Agent:** `agents/docs-validator-agent.md`

package/assets/commands/agents/frontend.md

@@ -0,0 +1,135 @@
+---
+name: frontend
+description: Validates React/Tailwind frontend code including accessibility, theme consistency, component composition, and performance. Use AFTER code-validator passes.
+---
+
+# Frontend Validator
+Validates React/Tailwind frontend code including accessibility, theme consistency, component composition, and performance. Use AFTER code-validator passes.
+
+## Arguments
+
+**Usage:** `/agents:frontend <directory>`
+
+**Examples:**
+- `/agents:frontend ./src/components`
+- `/agents:frontend ./app`
+- `/agents:frontend .`
+
+**Target Directory:** $ARGUMENTS
+
+---
+
+## Pre-Flight
+
+```bash
+echo "Running frontend 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 Frontend Validator agent on the validated target directory:
+
+**Agent:** frontend-validator-agent.md
+**Model:** Sonnet
+**Target:** $ARGUMENTS
+
+The agent performs code quality validation across 5 categories (100 points total):
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Component Quality | 25 | Validates single responsibility, typed props, hooks rules, composition patterns |
+| Accessibility | 25 | Validates semantic HTML, ARIA labels, keyboard navigation, and focus management |
+| Styling & Theme Consistency | 20 | Validates theme-aware patterns, consistent spacing, and responsive design |
+| Performance Patterns | 20 | Validates memoization, re-renders, key props, and lazy loading |
+| React Best Practices | 10 | Validates useEffect dependencies, cleanup, and error boundaries |
+
+---
+
+## Auto-Fail Conditions
+
+Critical issues that trigger immediate FAIL regardless of score:
+
+| ID | Condition |
+|----|-----------|
+| **AF-001** | Keyboard-inaccessible interactive elements |
+| **AF-002** | Using dark: prefixes (violates project theme system) |
+| **AF-003** | Images without alt text |
+| **AF-004** | API calls in presentation components |
+| **AF-005** | useEffect with side effects but no cleanup |
+
+---
+
+## Decision Thresholds
+
+| Score | Decision | Meaning |
+|-------|----------|---------|
+| **>=85** | ✅ PASS | Validation passed, proceed to next phase |
+| **<85** | ❌ 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/frontend.command.yaml`
+**Agent:** `agents/frontend-validator-agent.md`