openclaw-node-harness 2.0.0

package/skills/capability-evolver/src/gep/signals.js

@@ -0,0 +1,27 @@
+function extractSignals({ recentSessionTranscript, todayLog, memorySnippet, userSnippet }) {
+  const signals = [];
+  const corpus = [
+    String(recentSessionTranscript || ''),
+    String(todayLog || ''),
+    String(memorySnippet || ''),
+    String(userSnippet || ''),
+  ].join('\n');
+  const lower = corpus.toLowerCase();
+
+  const errorHit = /\[error|error:|exception|fail|failed|iserror":true/.test(lower);
+  if (errorHit) signals.push('log_error');
+  if (lower.includes('memory.md missing')) signals.push('memory_missing');
+  if (lower.includes('user.md missing')) signals.push('user_missing');
+  if (lower.includes('key missing')) signals.push('integration_key_missing');
+  if (lower.includes('no session logs found') || lower.includes('no jsonl files')) signals.push('session_logs_missing');
+  if (lower.includes('pgrep') || lower.includes('ps aux')) signals.push('windows_shell_incompatible');
+  if (lower.includes('path.resolve(__dirname, \'../../')) signals.push('path_outside_workspace');
+
+  // Protocol-specific drift signals
+  if (lower.includes('prompt') && !lower.includes('evolutionevent')) signals.push('protocol_drift');
+
+  return Array.from(new Set(signals));
+}
+
+module.exports = { extractSignals };
+

package/skills/cc-godmode/.clawhub/origin.json

@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "cc-godmode",
+  "installedVersion": "5.11.1",
+  "installedAt": 1770234319653
+}

package/skills/cc-godmode/CHANGELOG.md

@@ -0,0 +1,66 @@
+# Changelog
+
+All notable changes to the CC_GodMode Skill will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [5.11.1] - 2026-02-04
+
+### Added
+- Initial OpenClaw Skill release
+- Complete SKILL.md with all 8 agent specifications
+- Collapsible `<details>` sections for detailed agent docs
+- Quick Start section for immediate usage
+- Dual Quality Gates documentation
+- Workflow diagrams in ASCII art
+- ClawHub publishing workflow
+
+### Features from CC_GodMode v5.11.1
+- **@tester Fail-Safe Reporting**
+  - Graceful degradation chain: Full → Partial → Failure Report
+  - Structured error output (JSON) for programmatic handling
+  - Screenshot-on-failure best practice
+  - MCP Health Check (Pre-Test) instructions
+
+- **@researcher Timeout & Graceful Degradation**
+  - Hard timeout: 30 seconds MAX per task
+  - Partial results format for incomplete research
+  - Memory usage guidelines
+
+- **8 Specialized Agents**
+  - @researcher (haiku) - Knowledge Discovery
+  - @architect (opus) - System Design
+  - @api-guardian (sonnet) - API Lifecycle
+  - @builder (sonnet) - Implementation
+  - @validator (sonnet) - Code Quality
+  - @tester (sonnet) - UX Quality
+  - @scribe (sonnet) - Documentation
+  - @github-manager (haiku) - GitHub Operations
+
+- **Dual Quality Gates**
+  - 40% faster validation with parallel execution
+  - @validator (Code) + @tester (UX) run simultaneously
+  - Decision matrix for result coordination
+
+- **7 Standard Workflows**
+  - New Feature
+  - Bug Fix
+  - API Change
+  - Refactoring
+  - Release
+  - Process Issue
+  - Research Task
+
+### Technical Details
+- YAML frontmatter for ClawHub metadata
+- Version 1:1 mapping with CC_GodMode versions
+- Self-contained documentation (no external dependencies)
+- Context-window optimized with collapsible sections
+
+## [Unreleased]
+
+### Planned
+- Extended workflow customization
+- Domain pack integration
+- Custom agent model selection

package/skills/cc-godmode/README.md

@@ -0,0 +1,293 @@
+# 🚀 OpenClaw GodMode Skill
+
+> **Self-Orchestrating Multi-Agent Development Workflows for Claude Code**
+>
+> *You say WHAT, the AI decides HOW.*
+
+[![ClawHub](https://img.shields.io/badge/ClawHub-cc--godmode-blue)](https://clawhub.ai/skills/cc-godmode)
+[![Version](https://img.shields.io/badge/version-5.11.1-green)](./CHANGELOG.md)
+[![License](https://img.shields.io/badge/license-MIT-blue)](./LICENSE)
+[![OpenClaw](https://img.shields.io/badge/OpenClaw-compatible-orange)](https://openclaw.ai)
+[![Claude Code](https://img.shields.io/badge/Claude_Code-required-purple)](https://claude.ai/code)
+
+---
+
+## ⚠️ Important: Requirements
+
+### 🔧 Claude Code Required
+This skill **requires [Claude Code](https://claude.ai/code)** (Anthropic's CLI agent). It will not work with the web interface or API alone.
+
+### 💳 Paid Account Recommended
+GodMode spawns multiple sub-agents that consume tokens quickly. We **strongly recommend**:
+
+| Plan | Recommendation |
+|------|----------------|
+| Free | ❌ Not recommended (tokens exhaust very quickly) |
+| Pro ($20/mo) | ✅ Good for smaller projects |
+| **Max ($200/mo)** | ⭐ **Recommended** for heavy use |
+
+The multi-agent orchestration is powerful but token-intensive. With a free account, you'll hit limits within minutes.
+
+---
+
+## 🔀 Two Versions of GodMode
+
+### This Repo: OpenClaw GodMode Skill
+**Optimized for [OpenClaw](https://openclaw.ai)** — the AI agent framework that extends Claude Code with messaging, cron jobs, and more.
+
+- 📦 Installable via ClawHub
+- 🔗 Integrates with OpenClaw's skill system
+- 💬 Works with Telegram, WhatsApp, Discord channels
+- ⏰ Can be triggered via cron jobs
+
+### Original: [ClawdBot-GodMode](https://github.com/cubetribe/ClawdBot-GodMode)
+**The standalone CLAUDE.md version** — perfect for server administration from your local machine.
+
+- 🖥️ Ideal for managing VPS and remote servers
+- 🔧 Great for administering machines running OpenClaw
+- 📝 Documentation-first approach with excellent versioning
+- 🚀 Battle-tested on multiple production servers
+
+**Both repos are valuable** — choose based on your use case:
+- Running OpenClaw? → Use this skill
+- Managing servers via Claude Code locally? → Use the [original GodMode](https://github.com/cubetribe/ClawdBot-GodMode)
+
+---
+
+## ✨ What is GodMode?
+
+GodMode transforms your **Claude Code** agent into a **multi-agent development orchestrator**. Instead of manually managing every step of development, you simply describe what you want — and a team of specialized AI agents figures out how to build it.
+
+This isn't just another coding assistant. It's a complete **autonomous development workflow** that has been battle-tested over multiple weeks in real-world production projects.
+
+### 🎯 The Magic
+
+```
+You: "Add user authentication with JWT and refresh tokens"
+
+GodMode: *spawns @researcher to evaluate best practices*
+         *@architect designs the system*
+         *@builder implements it*
+         *@validator + @tester run quality checks in parallel*
+         *@scribe updates documentation*
+         
+Result: Production-ready feature with tests, docs, and proper architecture.
+```
+
+---
+
+## 🤖 Meet the Team
+
+GodMode orchestrates **8 specialized agents**, each with a specific role:
+
+| Agent | Role | What They Do |
+|-------|------|--------------|
+| 🔬 **@researcher** | Knowledge Discovery | Web research, tech evaluation, best practices |
+| 🏗️ **@architect** | System Design | Architecture decisions, ADRs, system design |
+| 🛡️ **@api-guardian** | API Lifecycle | Breaking change detection, versioning |
+| 👷 **@builder** | Implementation | Code writing, refactoring |
+| ✅ **@validator** | Code Quality | TypeScript, linting, security checks |
+| 🧪 **@tester** | UX Quality | E2E tests, visual regression, a11y |
+| 📝 **@scribe** | Documentation | Changelog, README, API docs |
+| 🐙 **@github-manager** | GitHub Ops | Issues, PRs, releases, CI/CD |
+
+---
+
+## 📦 Installation
+
+### Via ClawHub (Recommended)
+
+```bash
+clawdhub install cc-godmode
+```
+
+### Manual Installation
+
+```bash
+# Clone this repository
+git clone https://github.com/cubetribe/openclaw-godmode-skill.git
+
+# Copy to your OpenClaw skills directory
+cp -r openclaw-godmode-skill ~/.openclaw/skills/cc-godmode
+
+# Or for Clawdbot:
+cp -r openclaw-godmode-skill ~/.clawdbot/skills/cc-godmode
+
+# Verify installation
+ls ~/.openclaw/skills/cc-godmode/SKILL.md
+```
+
+---
+
+## 🎮 Usage
+
+Once installed, just describe what you want in natural language:
+
+### New Feature
+```
+New Feature: Add user authentication with JWT
+```
+
+### Bug Fix
+```
+Bug Fix: Login form validation not working
+```
+
+### API Change
+```
+API Change: Add email field to User type
+```
+
+### Research Task
+```
+Research: Best practices for React state management 2025
+```
+
+### Release
+```
+Prepare Release
+```
+
+---
+
+## 🔄 Workflows
+
+GodMode automatically selects the right workflow based on your request:
+
+### 🆕 New Feature (Full Pipeline)
+```
+You → @researcher* → @architect → @builder → [@validator + @tester] → @scribe
+                                                   (parallel)
+```
+
+### 🐛 Bug Fix (Quick)
+```
+You → @builder → [@validator + @tester] → done
+```
+
+### ⚠️ API Change (Critical Path)
+```
+You → @architect → @api-guardian → @builder → [@validator + @tester] → @scribe
+```
+
+### 🔬 Research Only
+```
+You → @researcher → Report
+```
+
+*Agents marked with `*` are optional and context-dependent*
+
+---
+
+## 🏆 Why GodMode?
+
+### Battle-Tested
+This system has been developed and refined over **multiple weeks** of intensive real-world testing. It's not theoretical — it's proven to work on production projects.
+
+### True Autonomy
+Unlike simple prompt chains, GodMode agents make intelligent decisions about:
+- Which agents to involve
+- When to parallelize tasks
+- How to handle failures and edge cases
+- What quality gates to apply
+
+### Documentation-First
+Every change is documented. Every decision is recorded. The versioning and documentation workflow is **extremely reliable** — crucial for maintaining production systems.
+
+### Dual Quality Gates
+Every feature passes through **two independent quality checks** running in parallel — because catching bugs early saves hours of debugging later.
+
+---
+
+## ⚙️ Requirements
+
+### Required
+- **[Claude Code](https://claude.ai/code)** — Anthropic's CLI agent
+- **Paid Claude Account** — Pro ($20) or Max ($200) recommended
+
+### Required MCP Servers
+- `playwright` — For @tester E2E testing
+- `github` — For @github-manager operations
+
+### Optional (Enhanced Features)
+- `lighthouse` — Performance audits
+- `a11y` — Accessibility testing
+- `memory` — Context persistence across sessions
+
+Check your MCP status:
+```bash
+openclaw mcp list
+# or
+claude mcp list
+```
+
+---
+
+## 🔒 Security
+
+This skill is **documentation-only** and contains no executable code:
+
+- ✅ No bash scripts that run automatically
+- ✅ No external API calls from the skill itself
+- ✅ No file modifications without explicit agent action
+- ✅ Full source transparency — read every line
+- ✅ MIT licensed
+
+All orchestration happens through your existing Claude Code agent using standard tool calls.
+
+---
+
+## 📚 Documentation
+
+| Document | Description |
+|----------|-------------|
+| [SKILL.md](./SKILL.md) | Main skill documentation (loaded by OpenClaw) |
+| [docs/WORKFLOWS.md](./docs/WORKFLOWS.md) | Detailed workflow documentation |
+| [docs/AGENTS.md](./docs/AGENTS.md) | Complete agent specifications |
+| [docs/TROUBLESHOOTING.md](./docs/TROUBLESHOOTING.md) | FAQ and problem solving |
+| [docs/MIGRATION.md](./docs/MIGRATION.md) | Migrating from CLAUDE.md |
+
+---
+
+## 🔗 Links
+
+- **Original GodMode:** [ClawdBot-GodMode](https://github.com/cubetribe/ClawdBot-GodMode) — Standalone version for server administration
+- **OpenClaw:** [openclaw.ai](https://openclaw.ai) — The AI agent framework
+- **ClawHub:** [clawhub.ai](https://clawhub.ai) — Skill marketplace
+- **Claude Code:** [claude.ai/code](https://claude.ai/code) — Anthropic's CLI agent
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome! This project is open source and we'd love your help making it even better.
+
+1. Fork this repository
+2. Create a feature branch: `git checkout -b feature/my-feature`
+3. Make your changes
+4. Test locally by copying to your skills directory
+5. Submit a pull request
+
+---
+
+## 📄 License
+
+MIT License — see [LICENSE](./LICENSE)
+
+---
+
+## 💬 A Note from the Creator
+
+> I've been working on GodMode for weeks, testing it on real projects, refining the agent interactions, and optimizing the workflows. The results have been **sensational** — tasks that used to take hours now complete in minutes with higher quality.
+>
+> I use the original GodMode daily to manage multiple VPS and production servers. The documentation-first approach and reliable versioning make it a dream for server administration. This OpenClaw version brings the same power to the OpenClaw ecosystem.
+>
+> I'm sharing this with the open-source community because I believe this approach to AI-assisted development is the future. Try it, break it, improve it, and let's build something amazing together.
+>
+> **Pro tip:** Get the Max plan ($200/mo) if you're serious about multi-agent workflows. The token headroom makes all the difference.
+>
+> — Dennis @ [cubetribe](https://github.com/cubetribe)
+
+---
+
+**Built with 🚀 by humans and Claude Code working together**

package/skills/cc-godmode/SKILL.md

@@ -0,0 +1,242 @@
+---
+name: cc-godmode
+description: "Self-orchestrating multi-agent development workflows with 8 specialized agents (researcher, architect, builder, validator, tester, scribe, etc.). Use for complex features, bug fixes, API changes, or releases that need a full dev pipeline."
+triggers:
+  - "orchestrate development workflow"
+  - "multi-agent development"
+  - "new feature workflow"
+  - "cc godmode"
+  - "full dev pipeline"
+negative_triggers:
+  - "single file edit"
+  - "simple code change"
+  - "quick one-line fix"
+  - "just run tests"
+metadata:
+  clawdbot:
+    emoji: "🚀"
+    author: "CC_GodMode Team"
+    version: "5.11.1"
+    tags:
+      - orchestration
+      - multi-agent
+      - development
+      - workflow
+      - claude-code
+      - automation
+    repository: "https://github.com/clawdbot/cc-godmode-skill"
+    license: "MIT"
+    tools:
+      - Read
+      - Write
+      - Edit
+      - Bash
+      - Glob
+      - Grep
+      - WebSearch
+      - WebFetch
+---
+
+# CC_GodMode 🚀
+
+> **Self-Orchestrating Development Workflows - You say WHAT, the AI decides HOW.**
+
+You are the **Orchestrator** for CC_GodMode - a multi-agent system that automatically delegates and orchestrates development workflows. You plan, coordinate, and delegate. You NEVER implement yourself.
+
+---
+
+## Quick Start
+
+**Commands you can use:**
+
+| Command | What happens |
+|---------|--------------|
+| `New Feature: [X]` | Full workflow: research → design → implement → test → document |
+| `Bug Fix: [X]` | Quick fix: implement → validate → test |
+| `API Change: [X]` | Safe API change with consumer analysis |
+| `Research: [X]` | Investigate technologies/best practices |
+| `Process Issue #X` | Load and process a GitHub issue |
+| `Prepare Release` | Document and publish release |
+
+---
+
+## Your Subagents
+
+You have 8 specialized agents. Call them via the Task tool with `subagent_type`:
+
+| Agent | Role | Model | Key Tools |
+|-------|------|-------|-----------|
+| `@researcher` | Knowledge Discovery | haiku | WebSearch, WebFetch |
+| `@architect` | System Design | opus | Read, Grep, Glob |
+| `@api-guardian` | API Lifecycle | sonnet | Grep, Bash (git diff) |
+| `@builder` | Implementation | sonnet | Read, Write, Edit, Bash |
+| `@validator` | Code Quality Gate | sonnet | Bash (tsc, tests) |
+| `@tester` | UX Quality Gate | sonnet | Playwright, Lighthouse |
+| `@scribe` | Documentation | sonnet | Read, Write, Edit |
+| `@github-manager` | GitHub Ops | haiku | GitHub MCP, Bash (gh) |
+
+---
+
+## Standard Workflows
+
+### 1. New Feature (Full Workflow)
+```
+                                          ┌──▶ @validator ──┐
+User ──▶ (@researcher)* ──▶ @architect ──▶ @builder              ├──▶ @scribe
+                                          └──▶ @tester   ──┘
+                                               (PARALLEL)
+```
+*@researcher is optional - use when new tech research is needed
+
+### 2. Bug Fix (Quick)
+```
+                ┌──▶ @validator ──┐
+User ──▶ @builder                  ├──▶ (done)
+                └──▶ @tester   ──┘
+```
+
+### 3. API Change (Critical!)
+```
+                                                              ┌──▶ @validator ──┐
+User ──▶ (@researcher)* ──▶ @architect ──▶ @api-guardian ──▶ @builder              ├──▶ @scribe
+                                                              └──▶ @tester   ──┘
+```
+**@api-guardian is MANDATORY for API changes!**
+
+### 4. Refactoring
+```
+                            ┌──▶ @validator ──┐
+User ──▶ @architect ──▶ @builder              ├──▶ (done)
+                            └──▶ @tester   ──┘
+```
+
+### 5. Release
+```
+User ──▶ @scribe ──▶ @github-manager
+```
+
+### 6. Process Issue
+```
+User: "Process Issue #X" → @github-manager loads → Orchestrator analyzes → Appropriate workflow
+```
+
+### 7. Research Task
+```
+User: "Research [topic]" → @researcher → Report with findings + sources
+```
+
+---
+
+## The 10 Golden Rules
+
+1. **Version-First** - Determine target version BEFORE any work starts
+2. **@researcher for Unknown Tech** - Use when new technologies need evaluation
+3. **@architect is the Gate** - No feature starts without architecture decision
+4. **@api-guardian is MANDATORY for API changes** - No exceptions
+5. **Dual Quality Gates** - @validator (Code) AND @tester (UX) must BOTH be green
+6. **@tester MUST create Screenshots** - Every page at 3 viewports (mobile, tablet, desktop)
+7. **Use Task Tool** - Call agents via Task tool with `subagent_type`
+8. **No Skipping** - Every agent in the workflow must be executed
+9. **Reports in reports/vX.X.X/** - All agents save reports under version folder
+10. **NEVER git push without permission** - Applies to ALL agents!
+
+---
+
+## Dual Quality Gates
+
+After @builder completes, BOTH gates run **in parallel** for 40% faster validation:
+
+```
+@builder
+    │
+    ├────────────────────┐
+    ▼                    ▼
+@validator           @tester
+(Code Quality)     (UX Quality)
+    │                    │
+    └────────┬───────────┘
+             │
+        SYNC POINT
+             │
+    ┌────────┴────────┐
+    │                 │
+BOTH APPROVED     ANY BLOCKED
+    │                 │
+    ▼                 ▼
+@scribe          @builder (fix)
+```
+
+**Decision Matrix:**
+
+| @validator | @tester | Action |
+|------------|---------|--------|
+| ✅ APPROVED | ✅ APPROVED | → @scribe |
+| ✅ APPROVED | 🔴 BLOCKED | → @builder (tester concerns) |
+| 🔴 BLOCKED | ✅ APPROVED | → @builder (code concerns) |
+| 🔴 BLOCKED | 🔴 BLOCKED | → @builder (merged feedback) |
+
+### Gate 1: @validator (Code Quality)
+- TypeScript compiles (`tsc --noEmit`)
+- Unit tests pass
+- No security issues
+- All consumers updated (for API changes)
+
+### Gate 2: @tester (UX Quality)
+- E2E tests pass
+- Screenshots at 3 viewports
+- A11y compliant (WCAG 2.1 AA)
+- Core Web Vitals OK (LCP, CLS, INP, FCP)
+
+---
+
+## Critical Paths (API Changes)
+
+Changes in these paths **MUST** go through @api-guardian: `src/api/**`, `backend/routes/**`, `shared/types/**`, `types/`, `*.d.ts`, `openapi.yaml`/`openapi.json`, `schema.graphql`
+
+## Reports Structure
+
+All agent reports saved to `reports/v[VERSION]/` as `00-researcher-report.md` through `06-scribe-report.md`.
+
+## Handoff Matrix
+
+| Agent | Receives from | Passes to |
+|-------|---------------|-----------|
+| @researcher | User/Orchestrator | @architect |
+| @architect | User/@researcher | @api-guardian or @builder |
+| @api-guardian | @architect | @builder |
+| @builder | @architect/@api-guardian | @validator AND @tester (PARALLEL) |
+| @validator | @builder | SYNC POINT |
+| @tester | @builder | SYNC POINT |
+| @scribe | Both gates approved | @github-manager (for release) |
+| @github-manager | @scribe/User | Done |
+
+## Pre-Push Requirements
+
+Before ANY push: (1) VERSION file updated, (2) CHANGELOG.md updated, (3) README.md updated if user-facing, (4) never push same version twice. Versioning: MAJOR=breaking, MINOR=features, PATCH=fixes.
+
+---
+
+## Detailed Agent Specifications
+
+See [references/agents.md](references/agents.md) for full agent specifications (roles, tools, output formats, and models for all 8 agents).
+
+---
+
+## Version
+
+**CC_GodMode v5.11.1** | MCP: `playwright` (req), `github` (req), `lighthouse` (opt), `a11y` (opt), `memory` (opt)
+
+---
+
+## Start
+
+When the user makes a request:
+
+1. **Analyze** the request type (Feature/Bug/API/Refactor/Issue)
+2. **Determine version** → Read VERSION file, decide increment
+3. **Create report folder** → `mkdir -p reports/vX.X.X/`
+4. **Announce version** → "Working on vX.X.X - [description]"
+5. **Check** MCP server availability
+6. **Select** the appropriate workflow
+7. **Activate** agents → All reports saved to `reports/vX.X.X/`
+8. **Complete** → @scribe updates VERSION + CHANGELOG