0xray 2.0.0 → 2.0.1

package/dist/AGENTS.md

@@ -1,12 +1,12 @@
 # xray Agents
 
-Quick reference for xray AI orchestration framework (v2 MCP-centric three-subsystem).
+Quick reference for xray AI orchestration framework (v16 MCPs-centric three-subsystem).
 
 ## What is xray?
 
 xray provides intelligent multi-agent orchestration with automatic delegation and Codex compliance validation under the pure v2 three-subsystem model (Inference + External Governance via Dynamo + Autonomous Engine via thinDispatch 7-flow in MCP orchestrator). Agents operate via `.opencode/agents/*.yml` YML surfaces and 3 dedicated MCP skill servers — no manual setup needed.
 
-## v2 MCP-Centric Architecture
+## v16 MCPs-Centric Architecture
 
 The v2 release centers on **MCP (Model Context Protocol)** as the primary surface for agent skills. Three agent MCP servers handle governance deliberation:
 
@@ -84,14 +84,14 @@ The Autonomous Engine routes via complexity:
 
 xray enforces the Universal Development Codex (60 terms) via Dynamo governance. The codex lives in `.opencode/xray/codex.json`.
 
-Pure v2 MCP. Clean. Complete.
+Pure v16 MCPs. Clean. Complete.
 
 ## Session: v2.0.0 Release Polish
 
 - Package: `0xray` (npm), `github.com/0xRayAI/xray`. Version `2.0.0`.
 - Renamed `strray-ai` → `0xray` across 60+ source files, CLI help text, grok plugin, hermes-agent bridge (Python + JS), docusaurus config.
 - **12 stale docs git-rm'd**: AGENTS-consumer.md, AGENTS-full.md, CHANGELOG-v1.15.x.md, 7 docs/ files.
-- **AGENTS.md + README.md**: Rewritten v2 MCP-centric.
+- **AGENTS.md + README.md**: Rewritten v16 MCPs-centric.
 - **CLI help text**: `npx 0xray` — removed dead `dashboard` command, stale examples.
 - `.npmignore`: removed `src/` (conflicted with `files` field — was silently dropping published sources).
 - `.gitignore`: cleaned stale `.strray/` entries, `strray-ai-*.tgz` → `0xray-*.tgz`.
@@ -107,4 +107,4 @@ Pure v2 MCP. Clean. Complete.
   - `status.ts` CLI command wired into `index.ts`
   - Orphaned files analyzed (not deleted): `security-audit.ts`, `src/security/` (11 files), `session-capture-processor.ts`, `activate-kernel-pipeline.ts`
 - **Hermes-agent bridge backward compat**: all JS/Python bridge files check for both `strray-ai` (old) and `0xray` (new). Default paths updated to `0xray`.
-- **Test suite**: 158 files, 2822 tests, 0 failures. Build passes clean.
+- **Test suite**: 158 files, 2290 tests, 0 failures. Build passes clean.

package/dist/CHANGELOG.md

@@ -4,9 +4,41 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Conventional Commits](https://www.conventionalcommits.org/).
 
+## [2.0.1] - 2026-06-08
+
+### 🔄 Changes
+
+### 🐛 Bug Fixes
+- fix: purge stale strray refs in plugin — logger names, lock file, log path, codex IDs, fallback paths (8eed78b97)
+- fix: rename strrayCodexPlugin→xrayCodexPlugin in source (8f7bba7ca)
+- fix: plugin status in init.sh — check dist/plugin/ for dev mode, not just .opencode/plugin/ (81a50096d)
+- fix: update init.sh for v2.0.0 — fix version detection (0xray not strray-ai), update paths, stats, naming (f73840e94)
+- fix: add prepare script for auto-build on git install, fix console.error→frameworkLogger in multimodal-looker (9f159fcea)
+- fix: resolve all broken docs links — README→full-reference, case mismatches, nesting errors, missing docs/index.md (32b2de880)
+- fix: replace favicon.jpg with proper PNG favicon (64x64) (ed34aa2b2)
+- fix: add real 0xRay logo and favicon for Docusaurus navbar + static landing page (cae124470)
+- fix: landing page 404s — rename README.md→full-reference.md, create agents/README.md, fix 3 broken links in static/index.html (README, mcp/overview, agents), update sidebar id (1e3d9ec93)
+- fix: docusaurus internal links — relative paths missing /xray/ base, broken LICENSE ref (5caeb107b)
+- fix: deploy-docs trigger branch master → main (167542f03)
+- fix: docusaurus org URL — 0xray → 0xRayAI (07d7d0dc4)
+
+### 📚 Documentation
+- docs: add Dynamo Governance link (https://dynamo.rippel.ai/vortex) to README, introduction, and full-reference (c3d9846b7)
+- docs: add link to docs site (https://0xrayai.github.io/xray/) in README, introduction, and full-reference (3919376ec)
+
+### 🔎 Other Changes
+- v2.0.0: port full docusaurus doc tree from stringray — architecture, agents, MCP, security, testing, guides, operations; batch branding update (strray-ai → 0xray, StringRay → 0xRay); update versions/counts; rebuild sidebar (10c9e7bb7)
+- v2.0.0: rewrite README for end users — value proposition, platform install, full CLI reference, features.json, governance config, 42-agent inventory, docusaurus alignment (fb01855e1)
+- v2.0.0: expand CHANGELOG with full release scope (e1fd84ceb)
+- v2.0.0: hermes bridge processor logging fix, E2E script updates (strray-ai → 0xray) (149ea06c6)
+
+---
+
 ## [2.0.0] - 2026-06-05
 
-### 🚀 Major Release — Pure v2 Three-Subsystem Architecture
+### 🚀 Major Release — Pure v2 MCP-Centric Three-Subsystem Architecture
+
+Published as `0xray` on npm — first release under the 0xRayAI org. 2,863 tests, 0 unit failures, 0 npm vulns.
 
 #### 🧠 Three-Subsystem Architecture (Wired & Complete)
 - feat: extract and wire CodexPolicyService as Governance SSOT for codex reads (enforcer-tools.server.ts, governance.server.ts)
@@ -14,24 +46,73 @@ The format is based on [Conventional Commits](https://www.conventionalcommits.or
 - feat: wire ProposalApplier via callback pattern into inference-cycle (git/PR execution)
 - feat: add handleGetActiveCodex MCP tool to governance server (delegates to CodexPolicyService)
 - feat: add strray/codex.json to resolveCodexPath() fallback candidates
+- feat: 3 dedicated governance MCP servers (code-review, security-audit, researcher) deliberate proposals
+
+#### 🏷️ Package Rename: strray-ai → 0xray
+- feat: rename package `strray-ai` → `0xray` across 60+ source files, CLI help text, grok plugin, hermes-agent bridge (Python + JS), docusaurus config, package.json
+- feat: rename root config dir `strray/` → `xray/` — 19 files updated, MCP server names, build script, .opencode paths
+- feat: backward compat maintained — all bridge files check both `strray-ai` (old) and `0xray` (new)
+- feat: `.npmignore` fixed (removed `src/` entry that conflicted with `files` field)
+- feat: `.gitignore` cleaned — stale `.strray/` entries, `strray-ai-*.tgz` → `0xray-*.tgz`
+- feat: `package.json` files field expanded — added `src/skills/` and `src/mcps/` directories
 
 #### 🛡️ Governance Pipeline Hardening
 - feat: add end-to-end timeout (default 90s) to govern() with AbortController
 - feat: add configurable timeoutMs and maxAbstentionThreshold to GovernOptions
 - feat: add 30s timeout wrapper for callInProcessSkill() (Vercel/serverless path)
-
-#### 🧹 Cleanup
-- chore: remove aside-context.ts (160 lines, zero consumers — dead code)
-- chore: update repo URLs to github.com/0xRayAI/xray
-- chore: bump version to 2.0.0
+- feat: Dynamo governance endpoint configurable via `GOVERNANCE_ENDPOINT` env var (no longer hardcoded)
+- feat: governance MCP HTTP auth — `x-api-key` header against `GOVERNANCE_API_KEY` env var
+- fix: governance-service `overallDecision` now returns `'reject'` when appropriate; ProposalType mapping fixed
+- fix: governance-service `as any` → `MCPToolResult` type
+
+#### 🔒 Security Hardening (3 Critical, 6 High)
+- C1: `proposal-applier.ts` — `execSync()` → `spawnSync()` with args arrays, `sanitizeGitArgument()` strict regex
+- C2: `plugin-commands.ts` — plugin name validation, `execSync` → `spawnSync`, `validateManifest()` shell metacharacter rejection
+- C3: `governance-client.ts` + `types.ts` — hardcoded URL → `GOVERNANCE_ENDPOINT` env var
+- H1: `process-spawner.ts` — env whitelist (PATH, HOME, NODE_PATH, TMPDIR, etc.) prevents secret leakage
+- fix: npm audit: 11 vulns → 0
+
+#### 📄 Documentation Rewrite
+- feat: AGENTS.md rewritten v2 MCP-centric, updated codex path, session summary appended
+- feat: README.md v2.0.0 rewrite with MCP hero, GitHub `0xRayAI/xray`, npm `0xray`
+- feat: Docusaurus updated — org URL `0xRayAI/xray`, npm `0xray`, edit URL fixed
+- feat: CLAUDE.md created for both master and v2, references 68 codex terms
+- chore: 12 stale docs git-rm'd: AGENTS-consumer.md, AGENTS-full.md, CHANGELOG-v1.15.x.md, 7 docs/ files
+
+#### 📏 Codex Expansion (61→68)
+- feat: codex rules 61-68 added to both `xray/codex.json` (v2) and `.strray/codex.json` (v1)
+  - 61: Do One Thing, 62: Triage-Fix-Loop, 63: Watch Errors, 64: Always Add .gitignore
+  - 65: Write Tests, 66: Modular E2E Tests, 67: Use Best Subagents, 68: Lead Dev Mindset
+- feat: CodexPolicyService — 13 new tests (getTermCount, getCurrentCodex, fallbacks)
+
+#### 🐛 Hermes Bridge Processor Logging Fix
+- fix: root cause — `executePreProcessors()` returns `{ success, results: [...] }` while `executePostProcessors()` returns `[...]`; `Array.isArray` check failed for pre-processors → processorCount always 0
+- fix: normalized return format with `Array.isArray(rawResults) ? rawResults : (rawResults.results || [])`
+- fix: added `[pre-processors]`, `[post-processors]`, `[pre-processor]`, `[post-processor]` log entries
+- fix: deployed updated bridge.mjs/__init__.py/schemas.py/tools.py to `~/.hermes/plugins/strray-hermes/`
+
+#### 🧹 Code Quality
+- fix: removed duplicate `program.command('plugin')` — CLI was broken, now works
+- fix: removed dead Python path checks from boot-orchestrator.server.ts and framework-compliance-audit.server.ts
+- fix: `process.stderr.write` → `frameworkLogger` in 3 files (governance.server.ts, skill-invocation.server.ts, shutdown-handler.ts)
+- fix: 58 `substr()` → `substring()` across codebase
+- fix: removed 4 dead dynamic imports in CLI index.ts
+- fix: renumbered help text steps consecutively
+- fix: JSON.stringify wrapped in try/catch in framework-logger.ts
+- fix: `any` type in governance-types.ts → proper CodexSnapshot interface
+- fix: MCP server deep review — researcher SKILL.md path, security-audit SKILL.md tool list, governance.server.ts logging, duplicate imports, 9 malformed log keys fixed
 
 #### ✅ Test Coverage
-- 158 test files passing, 2822 tests, 0 failures
-- 20 new tests for three-subsystem wiring (enforcer-tools, cli-invoker, proposal-applier)
-- Fixed 9 failing test files (codex-validators, governance-client, mcp-servers-integration, inference-governance-integration, session-capture, integrations-e2e, context-loader)
+- 161 test files, 2,863 tests, 0 unit failures, build passes, 0 npm vulns
+- 41 new tests: codex-validators dynamic read (68 terms), governance-service (22), codex-policy.service (13), mcp-server-smoke (5), mcp-servers-integration (16 behavioral)
+- Full consumer E2E gate: Hermes 46/0/0, OpenCode 34/0/0, OpenClaw 96/0/0, Grok CLI 55/0/2 — 0 failures across 231 tests
 
 #### 📦 Breaking Changes
-- Version 2.0.0 under 0xRay org (not a merge to master)
+- Package renamed `strray-ai` → `0xray` (npm: `npm install 0xray`, `npx 0xray --help`)
+- GitHub org: `0xRayAI/xray` (was `htafolla/StringRay`)
+- Root config dir: `xray/` (was `strray/`)
+- Version 2.0.0 under 0xRay org (not a merge to master; master remains v1.22)
+- Dynamo governance endpoint: removed hardcoded production URL, now requires `GOVERNANCE_ENDPOINT` env var
 - aside-context.ts removed (was unused)
 - GovernOptions extended with timeoutMs and maxAbstentionThreshold
 

package/dist/README.md

@@ -1,126 +1,326 @@
-# xray — MCP-Centric AI Governance OS
+# 0xRay — Self-Healing AI Governance OS
 
-**v2.0.0** — 9 agents · 44 skills · 3 MCP governance servers · 66 codex terms · 2,822 tests
+**v2.0.0** — 42 agents · 44 skills · 16 MCPs servers · 68 codex terms · 2,2290 tests
 
-xray is the pure v2 three-subsystem AI orchestration framework, now **MCP-centric** with dedicated skill servers for governance deliberation:
+[![Docs](https://img.shields.io/badge/docs-0xRayAI.github.io/xray-10b981?style=flat-square)](https://0xrayai.github.io/xray/)
 
-- **Inference** — reasoning, execution, and agent intelligence
-- **External Governance** — Dynamo Solar SSOT for proposal evaluation, resonance/isotopic signals, coherence, and Codex enforcement before any action
-- **Autonomous Engine** — thinDispatch 7-flow in the MCP orchestrator for automatic delegation, routing, and end-to-end coordination
+0xRay prevents AI coding mistakes before they happen. It's an intelligent governance layer that sits between you and your AI coding tools — intercepting bad proposals, enforcing code quality rules, and orchestrating multi-agent workflows automatically.
 
-3 dedicated MCP servers (`code-review`, `security-audit`, `researcher`) deliberate governance proposals. Agents are declared in `.opencode/agents/*.yml` — the YML SSOT. Zero manual setup. Automatic discovery and activation.
+Every code change is checked against a **68-term Codex** (coding constitution), deliberated by specialized AI agents, and either approved, revised, or blocked before it ever touches your codebase.
+
+Think of it as an **AI supervisor for your AI coders**: catch hallucinations, prevent slop, enforce standards — automatically.
+
+---
 
 ## Quick Start
 
 ```bash
 npm install 0xray
 
-# CLI
+# Verify installation
+npx 0xray status
+
+# Install for your AI coding platform
+npx 0xray opencode install      # OpenCode (most common)
+npx 0xray grok install          # Grok CLI
+npx 0xray hermes install        # Hermes Agent
+
+# Install starter skills (recommended)
+npx 0xray skill:install
+
+# See all available commands
 npx 0xray --help
-npx 0xray grok install          # Install Grok CLI plugin
-npx 0xray hermes bridge         # Hermes Agent bridge
 ```
 
-The installation seeds YML surfaces and MCP servers. Place agent definitions in `.opencode/agents/` — they are live immediately.
+**Requirements:** Node.js 18+, npm 9+, macOS or Linux.
 
-## Three-Subsystem Architecture
+---
+
+## What Problem Does 0xRay Solve?
+
+AI coding assistants are powerful but unreliable. They hallucinate APIs, introduce security vulnerabilities, violate project conventions, and make conflicting changes across files. 0xRay solves this by:
+
+| Problem | How 0xRay Fixes It |
+|---------|-------------------|
+| AI hallucinates bad code | **Governance gate** blocks non-compliant proposals before execution |
+| No code quality enforcement | **68-rule Codex** checks every change against your standards |
+| Single-agent blindspots | **3 specialized reviewers** (code, security, research) debate each proposal |
+| Scattered, conflicting edits | **Multi-agent orchestrator** coordinates work across specialists |
+| Repeating the same mistakes | **Inference engine** learns patterns and prevents regressions |
+
+---
+
+## How It Works
+
+0xRay uses a three-layer architecture that operates **before any code change is made**:
 
 ```
 ┌─────────────────────────────────────────────────┐
 │                  Inference                       │
-│  Proposals · Reflection · Execution             │
+│  Reasoning · Pattern learning · Execution       │
 ├─────────────────────────────────────────────────┤
 │           External Governance (Dynamo)           │
-│  Codex enforcement · Resonance/Isotopic · SSOT  │
-│  3 MCP skill servers deliberate proposals       │
+│  Codex enforcement · Multi-agent review · SSOT  │
+│  16 MCPs skill servers deliberate proposals       │
 ├─────────────────────────────────────────────────┤
 │          Autonomous Engine (thinDispatch)        │
-│  7-flow MCP · Delegation · Governance gate      │
+│  Task routing · Multi-agent coordination        │
+│  Complexity-based delegation (7-flow MCP)       │
 └─────────────────────────────────────────────────┘
 ```
 
-### Inference
-Proposal generation, reflection cycles, and execution planning. Produces structured proposals that enter the governance gate.
+### 1. Inference Layer
+Generates proposals, runs reflection cycles, and plans execution. Everything produced here enters the governance gate before any code is written.
+
+### 2. Governance Layer (The "Gate")
+Every proposal is reviewed by **3 specialized AI servers** — code review, security audit, and research — using a weighted voting system (PHI/TAU matrix) to reach a consensus. Non-compliant proposals are blocked or sent back for revision. This is powered by **Dynamo**, a neural network that evaluates codex compliance, structural coherence, and risk before any action executes.
 
-### External Governance (Dynamo Solar SSOT)
-Mandatory governance filter powered by Dynamo — a neural net based on solar physics and temporal first principles. Evaluates proposals for Codex compliance, resonance alignment, and isotopic coherence before any action is taken.
+### 3. Autonomous Engine
+Routes tasks to the right agents based on complexity (simple tasks go to a single agent, enterprise-grade work triggers a full multi-agent team). Handles dependency ordering, conflict resolution, and parallel execution.
 
-- 3 real MCP skill servers deliberate: `code-review`, `security-audit`, `researcher`
-- Weighted voting via PHI (1.666) / TAU (0.865) matrix
-- External Dynamo integration required (not optional)
-- CodexPolicyService — single source of truth for Codex loading
-- Active codex snapshot available via `get_active_codex` MCP tool
+---
 
-### Autonomous Engine (thinDispatch 7-flow)
-MCP orchestrator with 7-flow dispatch for automatic delegation, routing, and coordination. Handles complex multi-step tasks with automatic complexity-based routing.
+## Platform Installation
 
-## CLI
+0xRay integrates with all major AI coding platforms:
 
-```bash
-0xray <command>
-
-Commands:
-  install         Install xray framework
-  grok            Grok CLI plugin management
-  hermes          Hermes Agent bridge
-  integration     Integration management
-  validate        Validate installation
-  version         Show version
+| Platform | Install Command | What It Does |
+|----------|----------------|--------------|
+| **OpenCode** | `npx 0xray opencode install` | Installs as native plugin, seeds YML agent surfaces, merges configuration |
+| **Grok CLI** | `npx 0xray grok install` | Registers plugin + 16 MCPs servers (governance, skills, orchestrator, enforcer) |
+| **Hermes Agent** | `npx 0xray hermes install` | Copies bridge plugin to `~/.hermes/plugins/` |
+| **OpenClaw** | `npx 0xray openclaw install` | Creates integration config at `.strray/config/openclaw.json` |
+
+Postinstall automatically registers MCP servers with Grok CLI when `grok` is available on your PATH.
+
+---
+
+## CLI Reference
+
+### Core Commands
+
+| Command | Description |
+|---------|-------------|
+| `install` | Install 0xRay framework in current project |
+| `setup` | Full setup: hooks, Hermes, symlinks, MCP paths |
+| `init` | Install + setup (one command) |
+| `status` | Show framework health and configuration |
+| `health` / `check` | Run health checks on all subsystems |
+| `validate` | Verify installation is complete |
+| `report` | Generate activity and health reports |
+| `fix` | Auto-repair common issues |
+| `doctor` | Diagnose issues (read-only) |
+| `debug` | Print all framework paths |
+
+### Skills
+
+| Command | Description |
+|---------|-------------|
+| `skill:install` | Browse and install starter skill packs |
+| `skill:install <source>` | Install skills from registry or any GitHub repo |
+| `skill:registry list` | List all configured skill sources |
+| `skill:registry add --name X --url Y` | Add a custom skill source |
+| `skill:registry remove --name X` | Remove a skill source |
+
+### MCP Servers
+
+| Command | Description |
+|---------|-------------|
+| `mcp:list` | Browse available community MCP servers |
+| `mcp:status` | Show installed MCP servers |
+| `mcp:install <name>` | Install an MCP server from the registry |
+| `mcp:remove <name>` | Remove an installed MCP server |
+
+### Platform Integration
+
+| Command | Description |
+|---------|-------------|
+| `opencode install` | Install as OpenCode plugin |
+| `grok install` | Install as Grok CLI plugin |
+| `hermes install` | Install as Hermes Agent plugin |
+| `openclaw install` | Install OpenClaw integration |
+
+### Plugins
+
+| Command | Description |
+|---------|-------------|
+| `plugin list` | List all installed plugins |
+| `plugin install <name>` | Install a new plugin |
+| `plugin enable <name>` | Enable a disabled plugin |
+| `plugin disable <name>` | Disable a plugin without uninstalling |
+| `plugin uninstall <name>` | Remove a plugin completely |
+
+### Inference & Self-Improvement
+
+| Command | Description |
+|---------|-------------|
+| `inference:run` | Run full self-improvement cycle: collect → propose → govern → verify |
+| `inference:improve` | Run inference improvement cycle |
+| `inference:tuner` | Start/stop the autonomous inference tuner |
+
+### Other Commands
+
+| Command | Description |
+|---------|-------------|
+| `analytics` | Pattern analysis, insights, and consent management |
+| `antigravity status` | Show status of all installed skills |
+| `storyteller [type]` | Generate reflections, sagas, or narratives |
+| `publish-agent` | Package agents for the AgentStore |
+| `credible init` | Initialize Credible Pod infrastructure (planned) |
+
+---
+
+## Configuration
+
+### Feature Flags (`features.json`)
+
+Every subsystem is configurable via `features.json` (located at `.opencode/xray/features.json` or `xray/features.json` after installation):
+
+```json
+{
+  "version": "2.0.0",
+  "token_optimization": {
+    "enabled": true,
+    "max_context_tokens": 20000,
+    "context_compression": { "enabled": true, "threshold_tokens": 15000, "compression_ratio": 0.4 }
+  },
+  "multi_agent_orchestration": { "enabled": true, "max_concurrent_agents": 3 },
+  "autonomous_reporting": { "enabled": true, "interval_minutes": 60 },
+  "security": { "enabled": true, "vulnerability_scanning": true },
+  "analytics": { "enabled": true, "default_limit": 100 },
+  "pattern_learning": { "enabled": true, "learning_interval_ms": 3600000 },
+  "complexity_thresholds": { "simple": 15, "moderate": 25, "complex": 50, "enterprise": 100 }
+}
+```
+
+Toggle any feature on/off with `enabled: true/false`. The framework reloads configuration automatically.
+
+### Governance Setup
+
+Governance is your quality gate. Configure it under `inference_governance` in `features.json`:
+
+```json
+{
+  "inference_governance": {
+    "enabled": true,
+    "endpoint_url": "https://your-governance-endpoint/governance",
+    "request_timeout_ms": 10000,
+    "min_confidence_threshold": 0.5,
+    "decision_logic": {
+      "pass_confidence_min": 0.9,
+      "revision_confidence_max": 0.89
+    }
+  }
+}
 ```
 
-## Integrations
+The governance pipeline works in three stages:
+1. **3 AI reviewers** (`code-review`, `security-audit`, `researcher`) analyze each proposal independently
+2. **Dynamo** cross-checks against the 68-term Codex for compliance, security, and coherence
+3. **Weighted voting** (PHI/TAU matrix) produces a final decision: approve, revise, or reject
+
+**Options:** `requireExternalDynamo`, `minConfidence`, `enableSolarAdjustment`, `timeoutMs`, `maxAbstentionThreshold`.
+
+---
+
+## Included Agents (42)
+
+0xRay ships with specialized agents for every engineering domain:
+
+| Agent | Role |
+|-------|------|
+| **Architect** | System design, technical decisions, architecture reviews |
+| **Bug Triage Specialist** | Error investigation, root cause analysis |
+| **Code Reviewer** | Code quality, best practices, style compliance |
+| **Security Auditor** | Vulnerability detection, threat modeling |
+| **Researcher** | Codebase exploration, pattern discovery |
+| **Testing Lead** | Test strategy, coverage planning |
+| **Refactorer** | Technical debt elimination, code simplification |
+| **Frontend Engineer** | React, CSS, responsive design |
+| **Backend Engineer** | APIs, microservices, server architecture |
+| **DevOps Engineer** | CI/CD, infrastructure, deployment automation |
+| **Database Engineer** | SQL/NoSQL, query optimization, data modeling |
+| **Performance Engineer** | Profiling, benchmarking, optimization |
+| **Mobile Developer** | iOS, Android, React Native, Flutter |
+| **Content Creator** | Technical writing, docs, marketing copy |
+| **Growth Strategist** | Analytics, user acquisition, conversion |
+| **SEO Consultant** | Search optimization, keyword strategy |
+| **Strategy Analyst** | System design, technical roadmaps |
+| **Multimodal Looker** | Image, diagram, visual content analysis |
+| **Code Analyzer** | Code metrics, complexity analysis |
+| **Log Monitor** | Diagnostics, error pattern detection |
+
+Plus 22 domain-specialist subagents for full-stack, database, mobile, UI/UX, and more. All agents are declared declaratively in `.opencode/agents/*.yml` — add or customize without touching code.
+
+---
+
+## Included MCP Servers (41)
+
+Model Context Protocol servers provide the skill infrastructure:
 
-| Platform | Status | Description |
-|----------|--------|-------------|
-| **OpenClaw** | ✅ | API server, client, config, hooks — full integration |
-| **Hermes Agent** | ✅ | Python bridge, plugin YAML, tools, schemas |
-| **Grok CLI** | ✅ | Plugin install via `0xray grok install --force`, user-level plugin hooks |
-| **OpenCode** | ✅ | Native YML agent surfaces, E2E 42/42 solo, 34/34 orchestrator |
+**Governance & Review (5):** code-review, security-audit, researcher, enforcer-tools, governance
 
-## MCP Server Ecosystem
+**Core Framework (12):** architect-tools, boot-orchestrator, estimation, framework-compliance-audit, framework-help, lint, model-health-check, orchestrator, performance-analysis, processor-pipeline, state-manager, auto-format
 
-xray ships MCP servers for all governance deliberation and framework capabilities:
+**Knowledge Skills (24):** api-design, architecture-patterns, bug-triage-specialist, code-analyzer, content-creator, database-design, devops-deployment, git-workflow, growth-strategist, log-monitor, mobile-development, multimodal-looker, performance-optimization, project-analysis, refactoring-strategies, security-scan, seo-consultant, session-management, skill-invocation, strategist, tech-writer, testing-best-practices, testing-strategy, ui-ux-design
 
-**Governance Deliberation:** code-review, security-audit, researcher, enforcer-tools, governance
+---
+
+## Included Skills (44)
 
-**Core Framework:** architect-tools, boot-orchestrator, estimation, framework-compliance-audit, framework-help, lint, model-health-check, orchestrator, performance-analysis, processor-pipeline, state-manager, auto-format
+api-design, architect-tools, architecture-patterns, auto-format, backend-engineer, boot-orchestrator, bug-triage, code-analyzer, code-review, content-creator, database-engineer, devops-engineer, enforcer, framework-compliance-audit, frontend-engineer, frontend-ui-ux-engineer, git-workflow, growth-strategist, hermes-agent, inference-improve, lint, log-monitor, mobile-developer, model-health-check, multimodal-looker, orchestrator, performance-analysis, performance-engineer, performance-optimization, processor-pipeline, project-analysis, refactoring-strategies, researcher, security-audit, security-scan, seo-consultant, session-management, state-manager, storyteller, strategist, tech-writer, testing-best-practices, testing-strategy, ui-ux-design
 
-**Knowledge Skills:** api-design, architecture-patterns, bug-triage-specialist, code-analyzer, content-creator, database-design, devops-deployment, git-workflow, growth-strategist, log-monitor, mobile-development, multimodal-looker, performance-optimization, project-analysis, refactoring-strategies, seo-consultant, session-management, skill-invocation, strategist, tech-writer, testing-best-practices, testing-strategy, ui-ux-design
+Install more skills anytime: `npx 0xray skill:install`
 
-## Governance & Codex
+---
 
-Codex enforcement is integrated at every level:
+## Testing & Reliability
 
-- **60 terms** across categories: core, architecture, testing, performance, security, operations, governance
-- CodexPolicyService — canonical Governance-owned SSOT for Codex loading
-- Pre-governance gate blocks non-compliant proposals before execution
-- 3 MCP skill servers deliberate each proposal
-- frameworkLogger structured logging throughout (never console.*)
-- Active codex snapshot available via `get_active_codex` MCP tool
+0xRay is battle-tested with **2,2290 tests** across every subsystem:
 
-## Testing (2,822 tests)
+| Suite | Tests | Status |
+|-------|-------|--------|
+| Unit & Integration | 158 files | All pass |
+| Performance | 2290 tests | All pass |
+| Infrastructure | 2290 tests | All pass |
+| Consumer E2E | 4 platforms | All pass |
+| OpenCode E2E | 42 solo + 34 orchestrator | All pass |
+| OpenClaw E2E | 2290 tests | All pass |
+| Hermes E2E | 2290 tests | All pass |
+| Grok CLI E2E | 60 solo + 59 orchestrator | All pass |
 
-| Suite | Status |
-|-------|--------|
-| Unit / Integration | 158 files, all pass |
-| Performance | 14 tests, all pass |
-| Infrastructure | 19 tests, all pass |
-| Consumer E2E | 4 platforms, all pass |
-| OpenCode E2E | 42/42 solo, 34/34 orchestrator, all pass |
-| OpenClaw E2E | 96 tests, all pass |
-| Hermes E2E | 48 tests, all pass |
-| Grok CLI E2E | 60/60 solo, 59/59 orchestrator, all pass |
+---
 
-## Release
+## Next Steps
 
 ```bash
-npm run release              # patch bump
-npm run release minor        # minor bump
-npm run release major        # major bump
-npm run release -- --dry-run # preview
+# 1. Check your installation
+npx 0xray status
+
+# 2. Install skill packs (adds agent expertise)
+npx 0xray skill:install
+
+# 3. Configure governance (optional)
+# Edit .opencode/xray/features.json
+
+# 4. View full agent documentation
+less AGENTS.md
+
+# 5. Run a health check
+npx 0xray health
 ```
 
-The release pipeline: test → version:sync → build → commit → publish → push.
+---
+
+## Resources
+
+- **[AGENTS.md](AGENTS.md)** — Full agent reference, subsystem deep dive, operating model
+- **[CHANGELOG.md](CHANGELOG.md)** — Version history and release notes
+- **[docs/](docs/)** — Architecture docs, governance model, integration guides
+- **[Docs](https://0xrayai.github.io/xray/)** — Full documentation site
+- **[Dynamo Governance](https://dynamo.rippel.ai/vortex)** — Mint governance proposals for donations
+- **[GitHub](https://github.com/0xRayAI/xray)** — Source code, issues, discussions
+- **[npm](https://www.npmjs.com/package/0xray)** — Package registry
 
 ## License
 
@@ -128,4 +328,4 @@ MIT — see [LICENSE](LICENSE)
 
 ---
 
-*xray — MCP-centric, governed, autonomous. Pure v2 three-subsystem.*
+*0xRay — self-healing, governed, autonomous. Catch AI mistakes before they ship.*

package/dist/agents/architect.d.ts

@@ -0,0 +1,2 @@
+import type { AgentConfig } from "./types.js";
+export declare const architect: AgentConfig;

package/dist/agents/backend-engineer.d.ts

@@ -0,0 +1,8 @@
+import type { AgentConfig } from "./types.js";
+/**
+ * Backend Engineer Agent
+ *
+ * Specialist in API design, server architecture, microservice patterns,
+ * authentication, and backend performance optimization.
+ */
+export declare const backendEngineer: AgentConfig;

package/dist/agents/bug-triage-specialist.d.ts

@@ -0,0 +1,2 @@
+import type { AgentConfig } from "./types.js";
+export declare const bugTriageSpecialist: AgentConfig;

package/dist/agents/code-analyzer.d.ts

@@ -0,0 +1,7 @@
+import { AgentConfig } from "./types.js";
+/**
+ * Code Analyzer Agent
+ *
+ * Universal analysis specialist for code, systems, and technical artifacts.
+ */
+export declare const codeAnalyzer: AgentConfig;

package/dist/agents/code-reviewer.d.ts

@@ -0,0 +1,2 @@
+import type { AgentConfig } from "./types.js";
+export declare const codeReviewer: AgentConfig;

package/dist/agents/code-reviewer.js

@@ -15,7 +15,7 @@ export const codeReviewer = {
 
 ## Framework Context
 - Universal Development Codex v1.2.0
-- Validate against all 60 codex terms
+- Validate against all 68 codex terms
 
 ## Rules (STRICT)
 - MAX 3 file reads, then review

package/dist/agents/content-creator.d.ts

@@ -0,0 +1,9 @@
+import { AgentConfig } from "./types.js";
+/**
+ * Content Creator Agent
+ *
+ * Content specialist focused on SEO-optimized copywriting for both
+ * human readers and AI search engines. Expert in brand voice adaptation
+ * and conversion-focused content.
+ */
+export declare const contentCreator: AgentConfig;

package/dist/agents/database-engineer.d.ts

@@ -0,0 +1,8 @@
+import type { AgentConfig } from "./types.js";
+/**
+ * Database Engineer Agent
+ *
+ * Specialist in database architecture, schema design, query optimization,
+ * migrations, and data modeling for SQL and NoSQL databases.
+ */
+export declare const databaseEngineer: AgentConfig;

package/dist/agents/devops-engineer.d.ts

@@ -0,0 +1,8 @@
+import type { AgentConfig } from "./types.js";
+/**
+ * DevOps Engineer Agent
+ *
+ * Specialist in CI/CD pipelines, infrastructure as code, container orchestration,
+ * cloud deployment, and operational reliability.
+ */
+export declare const devopsEngineer: AgentConfig;