moflo 4.8.12 → 4.8.14

package/.claude/commands/stream-chain/run.md

@@ -1,70 +0,0 @@
-# stream-chain run
-
-Execute a custom stream chain with your own prompts.
-
-## Usage
-
-```bash
-claude-flow stream-chain run <prompt1> <prompt2> [...] [options]
-```
-
-Minimum 2 prompts required for chaining.
-
-## Options
-
-- `--verbose` - Show detailed execution information
-- `--timeout <seconds>` - Timeout per step (default: 30)
-- `--debug` - Enable debug mode
-
-## How It Works
-
-Each prompt in the chain receives the complete output from the previous step as context, enabling complex multi-step workflows.
-
-## Examples
-
-### Basic Chain
-```bash
-claude-flow stream-chain run \
-  "Write a function" \
-  "Add tests for it"
-```
-
-### Complex Workflow
-```bash
-claude-flow stream-chain run \
-  "Analyze the authentication system" \
-  "Identify security vulnerabilities" \
-  "Propose fixes with priority levels" \
-  "Implement the critical fixes" \
-  "Generate tests for the fixes"
-```
-
-### With Options
-```bash
-claude-flow stream-chain run \
-  "Complex analysis task" \
-  "Detailed implementation" \
-  --timeout 60 \
-  --verbose
-```
-
-## Context Preservation
-
-The output from each step is injected into the next prompt:
-
-```
-Step 1: "Write a sorting function"
-Output: [function code]
-
-Step 2 receives: "Previous step output:
-[function code]
-
-Next step: Optimize for performance"
-```
-
-## Best Practices
-
-1. **Clear Instructions**: Make each prompt specific
-2. **Logical Flow**: Order prompts in logical sequence
-3. **Appropriate Timeouts**: Increase for complex tasks
-4. **Verification**: Add verification steps in chain

package/.claude/commands/training/README.md

@@ -1,9 +0,0 @@
-# Training Commands
-
-Commands for training operations in Claude Flow.
-
-## Available Commands
-
-- [neural-train](./neural-train.md)
-- [pattern-learn](./pattern-learn.md)
-- [model-update](./model-update.md)

package/.claude/commands/training/model-update.md

@@ -1,25 +0,0 @@
-# model-update
-
-Update neural models with new data.
-
-## Usage
-```bash
-npx claude-flow training model-update [options]
-```
-
-## Options
-- `--model <name>` - Model to update
-- `--incremental` - Incremental update
-- `--validate` - Validate after update
-
-## Examples
-```bash
-# Update all models
-npx claude-flow training model-update
-
-# Specific model
-npx claude-flow training model-update --model agent-selector
-
-# Incremental with validation
-npx claude-flow training model-update --incremental --validate
-```

package/.claude/commands/training/neural-patterns.md

@@ -1,74 +0,0 @@
-# Neural Pattern Training
-
-## Purpose
-Continuously improve coordination through neural network learning.
-
-## How Training Works
-
-### 1. Automatic Learning
-Every successful operation trains the neural networks:
-- Edit patterns for different file types
-- Search strategies that find results faster
-- Task decomposition approaches
-- Agent coordination patterns
-
-### 2. Manual Training
-```
-Tool: mcp__moflo__neural_train
-Parameters: {
-  "pattern_type": "coordination",
-  "training_data": "successful task patterns",
-  "epochs": 50
-}
-```
-
-### 3. Pattern Types
-
-**Cognitive Patterns:**
-- Convergent: Focused problem-solving
-- Divergent: Creative exploration
-- Lateral: Alternative approaches
-- Systems: Holistic thinking
-- Critical: Analytical evaluation
-- Abstract: High-level design
-
-### 4. Improvement Tracking
-```
-Tool: mcp__moflo__neural_status
-Result: {
-  "patterns": {
-    "convergent": 0.92,
-    "divergent": 0.87,
-    "lateral": 0.85
-  },
-  "improvement": "5.3% since last session",
-  "confidence": 0.89
-}
-```
-
-## Pattern Analysis
-```
-Tool: mcp__moflo__neural_patterns
-Parameters: {
-  "action": "analyze",
-  "operation": "recent_edits"
-}
-```
-
-## Benefits
-- 🧠 Learns your coding style
-- 📈 Improves with each use
-- 🎯 Better task predictions
-- ⚡ Faster coordination
-
-## CLI Usage
-```bash
-# Train neural patterns via CLI
-npx claude-flow neural train --type coordination --epochs 50
-
-# Check neural status
-npx claude-flow neural status
-
-# Analyze patterns
-npx claude-flow neural patterns --analyze
-```

package/.claude/commands/training/neural-train.md

@@ -1,25 +0,0 @@
-# neural-train
-
-Train neural patterns from operations.
-
-## Usage
-```bash
-npx claude-flow training neural-train [options]
-```
-
-## Options
-- `--data <source>` - Training data source
-- `--model <name>` - Target model
-- `--epochs <n>` - Training epochs
-
-## Examples
-```bash
-# Train from recent ops
-npx claude-flow training neural-train --data recent
-
-# Specific model
-npx claude-flow training neural-train --model task-predictor
-
-# Custom epochs
-npx claude-flow training neural-train --epochs 100
-```

package/.claude/commands/training/pattern-learn.md

@@ -1,25 +0,0 @@
-# pattern-learn
-
-Learn patterns from successful operations.
-
-## Usage
-```bash
-npx claude-flow training pattern-learn [options]
-```
-
-## Options
-- `--source <type>` - Pattern source
-- `--threshold <score>` - Success threshold
-- `--save <name>` - Save pattern set
-
-## Examples
-```bash
-# Learn from all ops
-npx claude-flow training pattern-learn
-
-# High success only
-npx claude-flow training pattern-learn --threshold 0.9
-
-# Save patterns
-npx claude-flow training pattern-learn --save optimal-patterns
-```

package/.claude/commands/training/specialization.md

@@ -1,63 +0,0 @@
-# Agent Specialization Training
-
-## Purpose
-Train agents to become experts in specific domains for better performance.
-
-## Specialization Areas
-
-### 1. By File Type
-Agents automatically specialize based on file extensions:
-- **.js/.ts**: Modern JavaScript patterns
-- **.py**: Pythonic idioms
-- **.go**: Go best practices
-- **.rs**: Rust safety patterns
-
-### 2. By Task Type
-```
-Tool: mcp__moflo__agent_spawn
-Parameters: {
-  "type": "coder",
-  "capabilities": ["react", "typescript", "testing"],
-  "name": "React Specialist"
-}
-```
-
-### 3. Training Process
-The system trains through:
-- Successful edit operations
-- Code review patterns
-- Error fix approaches
-- Performance optimizations
-
-### 4. Specialization Benefits
-```
-# Check agent specializations
-Tool: mcp__moflo__agent_list
-Parameters: {"swarmId": "current"}
-
-Result shows expertise levels:
-{
-  "agents": [
-    {
-      "id": "coder-123",
-      "specializations": {
-        "javascript": 0.95,
-        "react": 0.88,
-        "testing": 0.82
-      }
-    }
-  ]
-}
-```
-
-## Continuous Improvement
-Agents share learnings across sessions for cumulative expertise!
-
-## CLI Usage
-```bash
-# Train agent specialization via CLI
-npx claude-flow train agent --type coder --capabilities "react,typescript"
-
-# Check specializations
-npx claude-flow agent list --specializations
-```

package/.claude/commands/truth/start.md

@@ -1,143 +0,0 @@
-# 📊 Truth Command
-
-View truth scores and reliability metrics for your codebase and agent tasks.
-
-## Overview
-
-The `truth` command provides comprehensive insights into code quality, agent performance, and verification metrics.
-
-## Usage
-
-```bash
-claude-flow truth [options]
-```
-
-## Options
-
-- `--format <type>` - Output format: table (default), json, csv, html
-- `--period <time>` - Time period: 1h, 24h, 7d, 30d
-- `--agent <name>` - Filter by specific agent
-- `--threshold <0-1>` - Show only scores below threshold
-- `--export <file>` - Export metrics to file
-- `--watch` - Real-time monitoring mode
-
-## Metrics Displayed
-
-### Truth Scores
-- **Overall Score**: Aggregate truth score (0.0-1.0)
-- **File Scores**: Individual file truth ratings
-- **Agent Scores**: Per-agent reliability metrics
-- **Task Scores**: Task completion quality
-
-### Trends
-- **Improvement Rate**: Quality trend over time
-- **Regression Detection**: Identifies declining scores
-- **Agent Learning**: Shows agent improvement curves
-
-### Statistics
-- **Mean Score**: Average truth score
-- **Median Score**: Middle value of scores
-- **Standard Deviation**: Score consistency
-- **Confidence Interval**: Statistical reliability
-
-## Examples
-
-### Basic Usage
-```bash
-# View current truth scores
-claude-flow truth
-
-# View scores for last 7 days
-claude-flow truth --period 7d
-
-# Export to HTML report
-claude-flow truth --export report.html --format html
-```
-
-### Advanced Analysis
-```bash
-# Monitor real-time scores
-claude-flow truth --watch
-
-# Find problematic files
-claude-flow truth --threshold 0.8
-
-# Agent-specific metrics
-claude-flow truth --agent coder --period 24h
-
-# JSON for processing
-claude-flow truth --format json | jq '.overall_score'
-```
-
-## Dashboard View
-
-```
-📊 Truth Metrics Dashboard
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-Overall Truth Score: 0.947 ✅
-Trend: ↗️ +2.3% (7d)
-
-Top Performers:
-  verification-agent   0.982 ⭐
-  code-analyzer       0.971 ⭐
-  test-generator      0.958 ✅
-
-Needs Attention:
-  refactor-agent      0.821 ⚠️
-  docs-generator      0.794 ⚠️
-
-Recent Tasks:
-  task-456  0.991 ✅  "Implement auth"
-  task-455  0.967 ✅  "Add tests"
-  task-454  0.743 ❌  "Refactor API"
-```
-
-## Integration
-
-### With CI/CD
-```yaml
-# GitHub Actions example
-- name: Check Truth Scores
-  run: |
-    claude-flow truth --format json > truth.json
-    score=$(jq '.overall_score' truth.json)
-    if (( $(echo "$score < 0.95" | bc -l) )); then
-      echo "Truth score too low: $score"
-      exit 1
-    fi
-```
-
-### With Monitoring
-```bash
-# Send to monitoring system
-claude-flow truth --format json | \
-  curl -X POST https://metrics.example.com/api/truth \
-  -H "Content-Type: application/json" \
-  -d @-
-```
-
-## Configuration
-
-Set truth display preferences in `.claude-flow/config.json`:
-
-```json
-{
-  "truth": {
-    "defaultFormat": "table",
-    "defaultPeriod": "24h",
-    "warningThreshold": 0.85,
-    "criticalThreshold": 0.75,
-    "autoExport": {
-      "enabled": true,
-      "path": ".claude-flow/metrics/truth-daily.json"
-    }
-  }
-}
-```
-
-## Related Commands
-
-- `verify` - Run verification checks
-- `pair` - Collaborative development with truth tracking
-- `report` - Generate detailed reports

package/.claude/commands/verify/check.md

@@ -1,50 +0,0 @@
-# verify check
-
-Run verification checks on code, tasks, or agent outputs.
-
-## Usage
-
-```bash
-claude-flow verify check [options]
-```
-
-## Options
-
-- `--file <path>` - Verify specific file
-- `--task <id>` - Verify task output
-- `--directory <path>` - Verify entire directory
-- `--threshold <0-1>` - Override default threshold (0.95)
-- `--auto-fix` - Attempt automatic fixes
-- `--json` - Output results as JSON
-- `--verbose` - Show detailed verification steps
-
-## Examples
-
-```bash
-# Basic file verification
-claude-flow verify check --file src/app.js
-
-# Verify with higher threshold
-claude-flow verify check --file src/critical.js --threshold 0.99
-
-# Verify and auto-fix issues
-claude-flow verify check --directory src/ --auto-fix
-
-# Get JSON output for CI/CD
-claude-flow verify check --json > verification.json
-```
-
-## Truth Scoring
-
-The check command evaluates:
-- Code correctness
-- Best practices adherence
-- Security vulnerabilities
-- Performance implications
-- Documentation completeness
-
-## Exit Codes
-
-- `0` - Verification passed
-- `1` - Verification failed
-- `2` - Error during verification

package/.claude/commands/verify/start.md

@@ -1,128 +0,0 @@
-# 🔍 Verification Commands
-
-Truth verification system for ensuring code quality and correctness with a 0.95 accuracy threshold.
-
-## Overview
-
-The verification system provides real-time truth checking and validation for all agent tasks, ensuring high-quality outputs and automatic rollback on failures.
-
-## Subcommands
-
-### `verify check`
-Run verification checks on current code or agent outputs.
-
-```bash
-claude-flow verify check --file src/app.js
-claude-flow verify check --task "task-123"
-claude-flow verify check --threshold 0.98
-```
-
-### `verify rollback`
-Automatically rollback changes that fail verification.
-
-```bash
-claude-flow verify rollback --to-commit abc123
-claude-flow verify rollback --last-good
-claude-flow verify rollback --interactive
-```
-
-### `verify report`
-Generate verification reports and metrics.
-
-```bash
-claude-flow verify report --format json
-claude-flow verify report --export metrics.html
-claude-flow verify report --period 7d
-```
-
-### `verify dashboard`
-Launch interactive verification dashboard.
-
-```bash
-claude-flow verify dashboard
-claude-flow verify dashboard --port 3000
-claude-flow verify dashboard --export
-```
-
-## Configuration
-
-Default threshold: **0.95** (95% accuracy required)
-
-Configure in `.claude-flow/config.json`:
-```json
-{
-  "verification": {
-    "threshold": 0.95,
-    "autoRollback": true,
-    "gitIntegration": true,
-    "hooks": {
-      "preCommit": true,
-      "preTask": true,
-      "postEdit": true
-    }
-  }
-}
-```
-
-## Integration
-
-### With Swarm Commands
-```bash
-claude-flow swarm --verify --threshold 0.98
-claude-flow hive-mind --verify
-```
-
-### With Training Pipeline
-```bash
-claude-flow train --verify --rollback-on-fail
-```
-
-### With Pair Programming
-```bash
-claude-flow pair --verify --real-time
-```
-
-## Metrics
-
-- **Truth Score**: 0.0 to 1.0 (higher is better)
-- **Confidence Level**: Statistical confidence in verification
-- **Rollback Rate**: Percentage of changes rolled back
-- **Quality Improvement**: Trend over time
-
-## Examples
-
-### Basic Verification
-```bash
-# Verify current directory
-claude-flow verify check
-
-# Verify with custom threshold
-claude-flow verify check --threshold 0.99
-
-# Verify and auto-fix
-claude-flow verify check --auto-fix
-```
-
-### Advanced Workflows
-```bash
-# Continuous verification during development
-claude-flow verify watch --directory src/
-
-# Batch verification
-claude-flow verify batch --files "*.js" --parallel
-
-# Integration testing
-claude-flow verify integration --test-suite full
-```
-
-## Performance
-
-- Verification latency: <100ms for most checks
-- Rollback time: <1s for git-based rollback
-- Dashboard refresh: Real-time via WebSocket
-
-## Related Commands
-
-- `truth` - View truth scores and metrics
-- `pair` - Collaborative development with verification
-- `train` - Training with verification feedback

package/.claude/helpers/gate-hook.mjs

@@ -1,50 +0,0 @@
-#!/usr/bin/env node
-import { execSync } from 'child_process';
-import { resolve } from 'path';
-
-var command = process.argv[2];
-if (!command) process.exit(0);
-
-// Read stdin JSON from Claude Code
-var stdinData = '';
-try {
-  stdinData = await new Promise(function(res) {
-    var data = '';
-    var timeout = setTimeout(function() { res(data); }, 500);
-    process.stdin.setEncoding('utf-8');
-    process.stdin.on('data', function(chunk) { data += chunk; });
-    process.stdin.on('end', function() { clearTimeout(timeout); res(data); });
-    process.stdin.on('error', function() { clearTimeout(timeout); res(''); });
-    if (process.stdin.isTTY) { clearTimeout(timeout); res(''); }
-  });
-} catch (e) { /* no stdin */ }
-
-var hookContext = {};
-try { if (stdinData.trim()) hookContext = JSON.parse(stdinData); } catch (e) {}
-
-// Pass tool info as env vars for gate.cjs
-var env = Object.assign({}, process.env);
-if (hookContext.tool_name) env.TOOL_NAME = hookContext.tool_name;
-if (hookContext.tool_input && typeof hookContext.tool_input === 'object') {
-  Object.keys(hookContext.tool_input).forEach(function(key) {
-    if (typeof hookContext.tool_input[key] === 'string') {
-      env['TOOL_INPUT_' + key] = hookContext.tool_input[key];
-    }
-  });
-}
-
-// Run gate.cjs with the enriched environment
-var projectDir = (env.CLAUDE_PROJECT_DIR || process.cwd()).replace(/^\/([a-z])\//i, '$1:/');
-var gateScript = resolve(projectDir, '.claude/helpers/gate.cjs');
-try {
-  var output = execSync('node "' + gateScript + '" ' + command, {
-    env: env, encoding: 'utf-8', timeout: 5000, stdio: ['pipe', 'pipe', 'pipe']
-  });
-  if (output.trim()) process.stdout.write(output);
-  process.exit(0);
-} catch (err) {
-  // gate.cjs exit(2) = block, exit(1) = also block attempt — translate both to exit(2)
-  if (err.stderr) process.stderr.write(err.stderr);
-  if (err.stdout) process.stderr.write(err.stdout);
-  process.exit(err.status === 2 || err.status === 1 ? 2 : 0);
-}