0xray 4.0.11 → 4.0.13

package/dist/skills/hermes-agent/SKILL.md

@@ -1,212 +0,0 @@
----
-name: hermes-agent
-description: Manage 0xRay framework from Hermes Agent via the native xray-hermes plugin. Covers the 4 plugin tools (validate, codex_check, health, hooks), lifecycle hooks, slash commands, bridge architecture, and CLI fallback.
-version: 2.1.0
-author: 0xRay AI
-metadata:
-  hermes:
-    tags: [0xRay, Plugin, Validation, Codex, GitHooks, Bridge]
-    related_skills: []
----
-
-# 0xRay Hermes Plugin (xray-hermes)
-
-Native Hermes plugin providing 0xRay framework integration — quality gates, codex enforcement, git hooks, and full pre/post processing pipeline. Runs via a Node.js bridge to compiled framework components.
-
-## When to Use
-
-- User asks about 0xRay health, validation, or codex checks
-- User wants to install/manage git hooks for automated enforcement
-- User asks about the plugin's tools, hooks, or slash commands
-- User asks about bridge errors or framework not loading
-- User wants to validate files before committing or pushing
-
-## Plugin Architecture
-
-```
-~/.hermes/plugins/xray-hermes/
-├── __init__.py         # Plugin registration, hooks, slash commands
-├── tools.py            # 4 tool handlers (validate, codex_check, health, hooks)
-├── schemas.py          # JSON schemas the LLM sees
-├── bridge.mjs          # Node.js bridge to compiled 0xRay framework
-├── plugin.yaml         # Plugin metadata (name, version, tools, hooks)
-├── types.py            # TypeScript-equivalent type definitions
-├── after-install.md    # Post-install instructions
-└── test_plugin.py      # Tests
-```
-
-**Bridge protocol:** JSON over stdin/stdout to `bridge.mjs` (Node.js). The bridge lazy-loads compiled framework modules from `dist/`:
-- `dist/plugin/quality-gate.js` — codex violation detection
-- `dist/processors/processor-manager.js` — pre/post processor pipeline
-- `dist/state/state-manager.js` — persistent state
-- `dist/core/features-config.js` — feature flags
-
-**Fallback:** When bridge is unavailable, tools fall back to `npx 0xray` CLI commands.
-
-**Config path resolution:** `XRAY_CONFIG_DIR/` > `.xray/` > built-in defaults.
-
-## 4 Tools
-
-### xray_validate
-
-Run pre-commit validation on files. Uses bridge quality gate + processor pipeline, falls back to CLI.
-
-```
-xray_validate(files=["src/my-module.ts"], operation="commit")
-xray_validate(files=["src/auth.ts", "src/auth.test.ts"], operation="modify")
-```
-
-Parameters:
-- `files` (required, array of strings) — file paths to validate
-- `operation` (string) — commit, create, modify, refactor (default: commit)
-
-Returns: pass/fail with per-file results and violations.
-
-### xray_codex_check
-
-Validate code against the 60-term Universal Development Codex. Checks error-handling, type-safety, performance, security, architecture.
-
-```
-xray_codex_check(code="const x: any = foo()", operation="create")
-xray_codex_check(code=snippet, operation="modify", focus_areas=["security", "error-handling"])
-```
-
-Parameters:
-- `code` (string) — code snippet to check. If omitted, returns framework health instead.
-- `operation` (required, string) — create, modify, refactor
-- `focus_areas` (array) — error-handling, type-safety, performance, security, architecture
-
-Returns: violations list with actionable remediation.
-
-### xray_health
-
-Framework health check. Returns version, loaded components, project root.
-
-```
-xray_health()
-```
-
-Returns: framework status, version, component availability, node version.
-
-### xray_hooks
-
-Manage 0xRay git hooks (install, uninstall, list, status).
-
-```
-xray_hooks(action="install")
-xray_hooks(action="status")
-xray_hooks(action="list")
-xray_hooks(action="uninstall", hooks=["pre-commit"])
-```
-
-Parameters:
-- `action` (required, string) — install, uninstall, list, status
-- `hooks` (array) — which hooks to manage (default: all four)
-
-Hooks available: pre-commit, post-commit, pre-push, post-push.
-
-| Hook | Type | What it does |
-|------|------|-------------|
-| `pre-commit` | Blocking | TypeScript check + Codex validation before commit |
-| `post-commit` | Non-blocking | Log archival + cleanup after commit |
-| `pre-push` | Blocking | Full validation suite before push |
-| `post-push` | Non-blocking | Comprehensive monitoring after push |
-
-## 2 Lifecycle Hooks
-
-These fire automatically — no action needed from the user or agent.
-
-### pre_tool_call
-
-Fires before ANY tool executes:
-1. Tracks session stats
-2. Logs tool-start event to `logs/framework/plugin-tool-events.log`
-3. For code-producing tools (write_file, patch, execute_code, write, edit): runs quality gate + pre-processors via bridge
-4. For other tools: nudges when a 0xRay MCP alternative exists (e.g., grep → search_codebase, eslint → xray_lint)
-
-### post_tool_call
-
-Fires after ANY tool returns:
-1. Logs tool-complete event
-2. For code-producing tools: runs post-processors via bridge
-
-### on_session_start (graceful fallback)
-
-Fires when a new session starts. Resets stats and logs to disk. Registration is wrapped in try/except for hosts that don't support it yet.
-
-## Slash Command
-
-```
-/xray status    — Plugin and framework health (calls bridge)
-/xray stats     — Session pipeline statistics
-/xray help      — Show available commands
-/sr status        — Alias
-```
-
-## Session Stats (tracked automatically)
-
-The plugin tracks per-session counters visible via `/xray stats`:
-- total_tool_calls, code_operations, xray_mcp_calls, native_tool_calls
-- quality_gate_runs, quality_gate_blocks
-- pre_processor_runs, post_processor_runs
-- bridge_calls, bridge_errors
-
-## Logging
-
-All logs go to `logs/framework/` in the project root:
-
-| File | Content |
-|------|---------|
-| `activity.log` | All pipeline events (quality gates, processors, nudges, errors) |
-| `plugin-tool-events.log` | Tool start/complete events with durations |
-
-## Quick Decision Guide
-
-| User Says | Tool / Command |
-|----------|---------------|
-| "Is 0xRay working?" | `xray_health()` or `/xray status` |
-| "Check these files before I commit" | `xray_validate(files=[...], operation="commit")` |
-| "Is this code codex compliant?" | `xray_codex_check(code=..., operation="create")` |
-| "Set up git hooks" | `xray_hooks(action="install")` |
-| "What hooks are installed?" | `xray_hooks(action="status")` |
-| "Show session stats" | `/xray stats` |
-| "Why is the bridge failing?" | Check `xray_health()` → if `framework: "not_loaded"`, verify `dist/` symlink |
-
-## Bridge Commands (internal)
-
-These are called by the Python tools via `bridge.mjs`, not directly by the LLM:
-
-| Command | What it does |
-|---------|-------------|
-| `health` | Framework health check |
-| `validate` | Run quality gate on files |
-| `codex-check` | Check code against codex rules |
-| `pre-process` | Quality gate + pre-processors before tool |
-| `post-process` | Post-processors after tool |
-| `hooks` | Git hook management |
-| `stats` | Bridge/framework statistics |
-
-Bridge can be invoked directly for debugging:
-```bash
-echo '{"command":"health"}' | node ~/.hermes/plugins/xray-hermes/bridge.mjs
-node ~/.hermes/plugins/xray-hermes/bridge.mjs health --cwd /path/to/project
-```
-
-## Relationship to MCP Servers
-
-The plugin and MCP servers are complementary:
-- **Plugin tools** = offline-first, always available, lightweight (validate, codex check, health, hooks)
-- **MCP servers** = deeper analysis requiring running Node.js (lint, security scan, architecture assessment, orchestration, codebase search)
-
-The plugin's pre_tool_call hook nudges when an MCP alternative exists (e.g., "use mcp_xray_lint_lint instead of raw eslint"). This is advisory, not blocking.
-
-## Pitfalls
-
-- Plugin requires restart after install/edit: Hermes loads plugins once at session start.
-- Bridge needs `dist/` symlink: The bridge loads compiled `.js` from `dist/` → `node_modules/0xray/dist/`. If the symlink breaks, bridge returns `framework: "not_loaded"`.
-- `xray_codex_check` without `code` param returns health, not a codex check. Pass `code` for actual validation.
-- CLI fallback requires `npx 0xray` in PATH. If bridge fails and CLI isn't available, tools return errors.
-- Quality gate blocks are logged but NOT enforced (advisory). The tool returns violations; the agent decides what to do.
-- Git hooks use symlinks from `.git/hooks/` → `hooks/`. If the `hooks/` directory doesn't exist in the project, `xray_hooks(action="install")` skips those hooks.
-- Project root detection walks up from CWD looking for `node_modules/0xray`, `.xray/features.json`, or `package.json`. Override with `XRAY_PROJECT_ROOT` env var.
-- `logs/framework/` is created automatically. Never breaks the agent if permissions fail.

package/dist/skills/inference-improve/SKILL.md

@@ -1,97 +0,0 @@
----
-source: framework
-name: inference-improve
-description: Autonomous inference improvement through collaborative agent analysis
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [inference, improvement, autonomous, learning]
-capabilities:
-  - analyze_inference_patterns
-  - improve_routing
-  - collaborative_analysis
-dependencies: []
----
-
-# Inference Improvement Skill
-
-## Purpose
-
-Coordinates a collaborative agent workflow to improve routing inference by analyzing logs, reflections, and reports.
-
-## Trigger Phrases
-
-- "improve inference"
-- "analyze routing patterns"
-- "autonomous improvement"
-- "learn from logs"
-- "coalesce insights"
-
-## Agent Workflow
-
-### Phase 1: Data Gathering (Researcher)
-```
-@researcher gather all recent logs, reflections, and reports
-- Read logs/framework/activity.log
-- Read logs/framework/routing-outcomes.json  
-- Read docs/reflections/*.md
-- Read logs/reports/session-*.md
-- Read logs/reports/job-*.md
-```
-
-### Phase 2: Pattern Analysis (Code-Analyzer)
-```
-@code-analyzer analyze gathered data
-- Identify routing success/failure patterns
-- Detect weak keyword matches
-- Find confidence distribution issues
-- Locate emerging patterns
-```
-
-### Phase 3: Design Improvements (Architect)
-```
-@architect design routing improvements
-- Propose new keyword mappings
-- Suggest confidence adjustments
-- Recommend complexity thresholds
-- Design new routing patterns
-```
-
-### Phase 4: Review & Refine (Code-Reviewer)
-```
-@code-reviewer review proposed changes
-- Validate quality of proposals
-- Refine suggestions
-- Ensure no regressions
-- Prioritize changes
-```
-
-### Phase 5: Validate & Apply (Enforcer)
-```
-@enforcer validate and apply changes
-- Codex compliance check
-- Verify changes are safe
-- Apply to routing-mappings.json
-- Log improvements
-```
-
-## Output
-
-Produces actionable improvements:
-1. Updated `routing-mappings.json`
-2. New insights report
-3. Confidence adjustments
-4. Pattern additions/removals
-
-## Configuration
-
-```json
-{
-  "inference_improvement": {
-    "enabled": true,
-    "autonomous": true,
-    "interval_hours": 24,
-    "min_confidence": 0.7
-  }
-}
-```

package/dist/skills/lint/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: lint
-description: Code linting and static analysis
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [quality, lint]
-capabilities:
-  - analyze_code
-  - find_issues
-  - suggest_fixes
-dependencies: []
-
-mcp:
-  lint:
-    command: node
-    args: [node_modules/0xray/dist/mcps/lint.server.js]
----
-
-# Lint Skill
-
-Code linting and static analysis.
-
-## Tools Available
-
-- **code_linting**: Code linting
-- **static_analysis**: Static analysis
-- **quality_checks**: Quality checks
-
-## Usage
-
-This skill provides quality capabilities for lint functionality.
-
-## Integration
-
-Activated when quality capabilities are requested through the skills system.

package/dist/skills/log-monitor/SKILL.md

@@ -1,44 +0,0 @@
----
-source: framework
-name: log-monitor
-description: Log analysis, pattern detection, and alerting
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [monitoring, logging, alerting, observability]
-capabilities:
-  - analyze_logs
-  - detect_patterns
-  - send_alerts
-dependencies: []
-
-mcp:
-  log-monitor:
-    command: node
-    args: [node_modules/0xray/dist/mcps/knowledge-skills/log-monitor.server.js]
----
-
-# Log Monitor Skill
-
-Log analysis, pattern detection, and alerting system.
-
-## Tools Available
-
-- **analyze_logs**: Analyze log entries to identify patterns and errors
-- **detect_patterns**: Detect specific patterns in logs using regex
-- **alert_on_issues**: Generate alerts based on log analysis thresholds
-- **correlate_events**: Correlate log entries across sources
-- **generate_report**: Generate comprehensive log analysis reports
-
-## Usage
-
-This skill provides logging capabilities for:
-- Real-time log monitoring
-- Error pattern detection
-- Anomaly detection
-- Security threat identification
-- Performance issue identification
-
-## Integration
-
-Activated when log analysis or monitoring capabilities are requested.

package/dist/skills/mobile-developer/SKILL.md

@@ -1,42 +0,0 @@
----
-source: framework
-name: mobile-developer
-description: "Mobile developer for iOS (Swift/SwiftUI), Android (Kotlin/Compose), React Native, and Flutter"
-category: mobile
----
-
-# Mobile Developer Skill
-
-Mobile developer for native and cross-platform app development. Platform-native, user-experience focused, performance-conscious.
-
-## Platform Guidelines
-
-**iOS:** SwiftUI for new projects, UIKit for complex animations, MVVM/Coordinator pattern, Dynamic Type, Dark Mode, Core Data/SwiftData
-
-**Android:** Jetpack Compose, Material Design 3, MVVM + Hilt/Koin, Room, SDK 34 (min 24)
-
-**React Native:** Expo, React Navigation, TypeScript, optimize bundle size, test on both platforms
-
-**Flutter:** Riverpod/BLoC, Material Design 3, platform channels for native features
-
-## Performance Targets
-
-- Cold launch < 2s
-- Memory < 150MB
-- Battery efficient (minimal background work)
-- Lazy loading and image caching
-
-## Security
-
-- Keychain/Keystore for sensitive data
-- HTTPS only
-- OAuth 2.0 / PKCE
-- Anti-reverse-engineering (code obfuscation)
-- Input validation on all user data
-
-## Mobile UX
-
-- Follow platform conventions
-- Pull-to-refresh, loading states, empty states
-- Offline handling with sync
-- Gesture support (swipe, pinch)

package/dist/skills/model-health-check/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: model-health-check
-description: AI model health monitoring and diagnostics
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [monitoring, model, health, check]
-capabilities:
-  - monitor_health
-  - diagnose_issues
-  - provide_metrics
-dependencies: []
-
-mcp:
-  model-health-check:
-    command: node
-    args: [node_modules/0xray/dist/mcps/model-health-check.server.js]
----
-
-# Model Health Check Skill
-
-AI model health monitoring and diagnostics.
-
-## Tools Available
-
-- **model_monitoring**: Model monitoring
-- **health_diagnostics**: Health diagnostics
-- **performance_tracking**: Performance tracking
-
-## Usage
-
-This skill provides monitoring capabilities for model health check functionality.
-
-## Integration
-
-Activated when monitoring capabilities are requested through the skills system.

package/dist/skills/multimodal-looker/SKILL.md

@@ -1,45 +0,0 @@
----
-source: framework
-name: multimodal-looker
-description: Visual content analysis for diagrams, screenshots, and UI mockups
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [visual, diagrams, screenshots, accessibility, ui-analysis]
-capabilities:
-  - analyze_visual
-  - process_diagrams
-  - extract_information
-dependencies: []
-
-mcp:
-  multimodal-looker:
-    command: node
-    args: [node_modules/0xray/dist/mcps/knowledge-skills/multimodal-looker.server.js]
----
-
-# Multimodal Looker Skill
-
-Visual content analysis for diagrams, screenshots, and UI mockups.
-
-## Tools Available
-
-- **analyze_diagram**: Analyze flowcharts, sequence diagrams, architecture diagrams
-- **analyze_screenshot**: Identify UI components and layout patterns
-- **generate_ui_spec**: Generate UI specification from mockups
-- **extract_design_tokens**: Extract colors, typography, spacing
-- **accessibility_audit**: Perform WCAG accessibility audit
-- **compare_visuals**: Compare visual elements for differences
-
-## Usage
-
-This skill provides visual analysis capabilities for:
-- Diagram understanding and extraction
-- UI mockup analysis
-- Design token extraction
-- Accessibility compliance checking
-- Visual regression testing
-
-## Integration
-
-Activated when visual analysis or UI understanding capabilities are requested.

package/dist/skills/orchestrator/SKILL.md

@@ -1,61 +0,0 @@
----
-source: framework
-name: orchestrator
-description: Multi-agent workflow coordination, lead-dev operating model (codex 67-68), and task delegation. Default when suit is worn — no keywords required.
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [orchestration, orchestrator, lead-dev]
-capabilities:
-  - coordinate_agents
-  - delegate_tasks
-  - manage_workflow
-dependencies: []
-
-mcp:
-  orchestrator:
-    command: node
-    args: [node_modules/0xray/dist/mcps/orchestrator.server.js]
----
-
-# Orchestrator Skill — includes lead-dev operating model
-
-When `multi_agent_orchestration.lead_dev_mode` is true in `features.json` (default when suit is worn), this is the **default OS behavior** — not a separate skill or MCP.
-
-## Seven rules (codex 67–68)
-
-1. Phased plan + detailed todos; assign best subagent; monitor output
-2. Lead dev loops test→fix until green; no permission pings
-3. Per-suite test triage after major changes; full suite last
-4. Lead stays main thread; subagents execute; update todos
-5. Read all console and test output; triage fix rerun
-6. Never defer errors as "pre-existing" — add todo and resolve
-7. Resolve all errors before phase completion
-
-## MCP loop (one tool surface — no autonomy-intake)
-
-| Step | MCP tool | Notes |
-|------|----------|-------|
-| **Intake + classify** | `analyze-complexity` | Pass `tasks` array; persists `.xray/state/lead-dev-plan.json` when mode is on |
-| Delegate (consult) | `orchestrate-task` | Invokes MCP consult skills (code-review, researcher, security-audit, etc.) |
-| Delegate (implement) | **host `Task` / `spawn_subagent`** | `orchestrate-task` **defers** backend-engineer, frontend-engineer, bug-triage — lead must spawn |
-| Monitor | `get-orchestration-status` | Lead updates todos |
-| Major work | researcher + architect-tools + code-review | Auto-listed in plan when complexity > threshold |
-
-## Subagent routing
-
-| Task | Subagent |
-|------|----------|
-| Phasing | strategist |
-| Architecture | architect-tools |
-| Research | researcher |
-| Implementation | backend-engineer / frontend-engineer |
-| Test failures | bug-triage |
-| Review | code-review |
-
-## Hooks (rewired, not new MCPs)
-
-- **SessionStart** → `session-start.js` boots lead_dev_mode
-- **PreToolUse** → hints `per_suite_triage_required` on full `npm test`
-
-Config: `features.json` → `multi_agent_orchestration.lead_dev_mode`

package/dist/skills/performance-analysis/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: performance-analysis
-description: System performance analysis and optimization
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [performance, performance, analysis]
-capabilities:
-  - analyze_performance
-  - identify_bottlenecks
-  - optimize_code
-dependencies: []
-
-mcp:
-  performance-analysis:
-    command: node
-    args: [node_modules/0xray/dist/mcps/performance-analysis.server.js]
----
-
-# Performance Analysis Skill
-
-System performance analysis and optimization.
-
-## Tools Available
-
-- **performance_analysis**: Performance analysis
-- **optimization_recommendations**: Optimization recommendations
-- **metrics_tracking**: Metrics tracking
-
-## Usage
-
-This skill provides performance capabilities for performance analysis functionality.
-
-## Integration
-
-Activated when performance capabilities are requested through the skills system.

package/dist/skills/performance-engineer/SKILL.md

@@ -1,41 +0,0 @@
----
-source: framework
-name: performance-engineer
-description: "Performance engineer for profiling, benchmarking, load testing, and optimization"
-category: performance
----
-
-# Performance Engineer Skill
-
-Performance optimization specialist. Data-driven, systematic, results-oriented approach.
-
-## Performance Metrics
-
-**Frontend:** LCP < 2.5s, INP < 200ms, CLS < 0.1, FCP < 1.8s, TTFB < 800ms
-**Backend:** < 200ms p95, < 500ms p99, error rate < 0.1%, availability 99.9%
-**Database:** query < 100ms OLTP, connection pool < 80%, index hit ratio > 95%
-
-## Profiling Strategy
-
-1. Identify symptoms
-2. Measure baseline
-3. Profile hotspots
-4. Optimize
-5. Verify improvement
-6. Monitor regression
-
-## Optimization Priority
-
-1. Algorithm improvements
-2. Caching strategy
-3. Database queries
-4. Code-level optimization
-5. Hardware/infrastructure
-
-## Load Testing
-
-- Use realistic data volumes
-- Test at peak + 20%
-- Warm up before measuring
-- Run multiple iterations
-- Monitor infrastructure during tests

package/dist/skills/performance-optimization/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: performance-optimization
-description: Application performance optimization and tuning
-author: Xray Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [performance, performance, optimization]
-capabilities:
-  - optimize_performance
-  - tune_application
-  - improve_efficiency
-dependencies: []
-
-mcp:
-  performance-optimization:
-    command: node
-    args: [node_modules/0xray/dist/mcps/knowledge-skills/performance-optimization.server.js]
----
-
-# Performance Optimization Skill
-
-Application performance optimization and tuning.
-
-## Tools Available
-
-- **performance_tuning**: Performance tuning
-- **optimization_strategies**: Optimization strategies
-- **performance_monitoring**: Performance monitoring
-
-## Usage
-
-This skill provides performance capabilities for performance optimization functionality.
-
-## Integration
-
-Activated when performance capabilities are requested through the skills system.