moflo 4.9.20 → 4.9.22

package/.claude/commands/hooks/post-task.md

@@ -1,112 +0,0 @@
-# hook post-task
-
-Execute post-task cleanup, performance analysis, and memory storage.
-
-## Usage
-
-```bash
-npx claude-flow hook post-task [options]
-```
-
-## Options
-
-- `--task-id, -t <id>` - Task identifier for tracking
-- `--analyze-performance` - Generate performance metrics (default: true)
-- `--store-decisions` - Save task decisions to memory
-- `--export-learnings` - Export neural pattern learnings
-- `--generate-report` - Create task completion report
-
-## Examples
-
-### Basic post-task hook
-
-```bash
-npx claude-flow hook post-task --task-id "auth-implementation"
-```
-
-### With full analysis
-
-```bash
-npx claude-flow hook post-task -t "api-refactor" --analyze-performance --generate-report
-```
-
-### Memory storage
-
-```bash
-npx claude-flow hook post-task -t "bug-fix-123" --store-decisions --export-learnings
-```
-
-### Quick cleanup
-
-```bash
-npx claude-flow hook post-task -t "minor-update" --analyze-performance false
-```
-
-## Features
-
-### Performance Analysis
-
-- Measures execution time
-- Tracks token usage
-- Identifies bottlenecks
-- Suggests optimizations
-
-### Decision Storage
-
-- Saves key decisions made
-- Records implementation choices
-- Stores error resolutions
-- Maintains knowledge base
-
-### Neural Learning
-
-- Exports successful patterns
-- Updates coordination models
-- Improves future performance
-- Trains on task outcomes
-
-### Report Generation
-
-- Creates completion summary
-- Documents changes made
-- Lists files modified
-- Tracks metrics achieved
-
-## Integration
-
-This hook is automatically called by Claude Code when:
-
-- Completing a task
-- Switching to a new task
-- Ending a work session
-- After major milestones
-
-Manual usage in agents:
-
-```bash
-# In agent coordination
-npx claude-flow hook post-task --task-id "your-task-id" --analyze-performance true
-```
-
-## Output
-
-Returns JSON with:
-
-```json
-{
-  "taskId": "auth-implementation",
-  "duration": 1800000,
-  "tokensUsed": 45000,
-  "filesModified": 12,
-  "performanceScore": 0.92,
-  "learningsExported": true,
-  "reportPath": "/reports/task-auth-implementation.md"
-}
-```
-
-## See Also
-
-- `hook pre-task` - Pre-task setup
-- `performance report` - Detailed metrics
-- `memory usage` - Memory management
-- `neural patterns` - Pattern analysis

package/.claude/commands/hooks/pre-edit.md

@@ -1,113 +0,0 @@
-# hook pre-edit
-
-Execute pre-edit validations and agent assignment before file modifications.
-
-## Usage
-
-```bash
-npx claude-flow hook pre-edit [options]
-```
-
-## Options
-
-- `--file, -f <path>` - File path to be edited
-- `--auto-assign-agent` - Automatically assign best agent (default: true)
-- `--validate-syntax` - Pre-validate syntax before edit
-- `--check-conflicts` - Check for merge conflicts
-- `--backup-file` - Create backup before editing
-
-## Examples
-
-### Basic pre-edit hook
-
-```bash
-npx claude-flow hook pre-edit --file "src/auth/login.js"
-```
-
-### With validation
-
-```bash
-npx claude-flow hook pre-edit -f "config/database.js" --validate-syntax
-```
-
-### Manual agent assignment
-
-```bash
-npx claude-flow hook pre-edit -f "api/users.ts" --auto-assign-agent false
-```
-
-### Safe editing with backup
-
-```bash
-npx claude-flow hook pre-edit -f "production.env" --backup-file --check-conflicts
-```
-
-## Features
-
-### Auto Agent Assignment
-
-- Analyzes file type and content
-- Assigns specialist agents
-- TypeScript → TypeScript expert
-- Database → Data specialist
-- Tests → QA engineer
-
-### Syntax Validation
-
-- Pre-checks syntax validity
-- Identifies potential errors
-- Suggests corrections
-- Prevents broken code
-
-### Conflict Detection
-
-- Checks for git conflicts
-- Identifies concurrent edits
-- Warns about stale files
-- Suggests merge strategies
-
-### File Backup
-
-- Creates safety backups
-- Enables quick rollback
-- Tracks edit history
-- Preserves originals
-
-## Integration
-
-This hook is automatically called by Claude Code when:
-
-- Using Edit or MultiEdit tools
-- Before file modifications
-- During refactoring operations
-- When updating critical files
-
-Manual usage in agents:
-
-```bash
-# Before editing files
-npx claude-flow hook pre-edit --file "path/to/file.js" --validate-syntax
-```
-
-## Output
-
-Returns JSON with:
-
-```json
-{
-  "continue": true,
-  "file": "src/auth/login.js",
-  "assignedAgent": "auth-specialist",
-  "syntaxValid": true,
-  "conflicts": false,
-  "backupPath": ".backups/login.js.bak",
-  "warnings": []
-}
-```
-
-## See Also
-
-- `hook post-edit` - Post-edit processing
-- `Edit` - File editing tool
-- `MultiEdit` - Multiple edits tool
-- `agent spawn` - Manual agent creation

package/.claude/commands/hooks/pre-task.md

@@ -1,111 +0,0 @@
-# hook pre-task
-
-Execute pre-task preparations and context loading.
-
-## Usage
-
-```bash
-npx claude-flow hook pre-task [options]
-```
-
-## Options
-
-- `--description, -d <text>` - Task description for context
-- `--auto-spawn-agents` - Automatically spawn required agents (default: true)
-- `--load-memory` - Load relevant memory from previous sessions
-- `--optimize-topology` - Select optimal swarm topology
-- `--estimate-complexity` - Analyze task complexity
-
-## Examples
-
-### Basic pre-task hook
-
-```bash
-npx claude-flow hook pre-task --description "Implement user authentication"
-```
-
-### With memory loading
-
-```bash
-npx claude-flow hook pre-task -d "Continue API development" --load-memory
-```
-
-### Manual agent control
-
-```bash
-npx claude-flow hook pre-task -d "Debug issue #123" --auto-spawn-agents false
-```
-
-### Full optimization
-
-```bash
-npx claude-flow hook pre-task -d "Refactor codebase" --optimize-topology --estimate-complexity
-```
-
-## Features
-
-### Auto Agent Assignment
-
-- Analyzes task requirements
-- Determines needed agent types
-- Spawns agents automatically
-- Configures agent parameters
-
-### Memory Loading
-
-- Retrieves relevant past decisions
-- Loads previous task contexts
-- Restores agent configurations
-- Maintains continuity
-
-### Topology Optimization
-
-- Analyzes task structure
-- Selects best swarm topology
-- Configures communication patterns
-- Optimizes for performance
-
-### Complexity Estimation
-
-- Evaluates task difficulty
-- Estimates time requirements
-- Suggests agent count
-- Identifies dependencies
-
-## Integration
-
-This hook is automatically called by Claude Code when:
-
-- Starting a new task
-- Resuming work after a break
-- Switching between projects
-- Beginning complex operations
-
-Manual usage in agents:
-
-```bash
-# In agent coordination
-npx claude-flow hook pre-task --description "Your task here"
-```
-
-## Output
-
-Returns JSON with:
-
-```json
-{
-  "continue": true,
-  "topology": "hierarchical",
-  "agentsSpawned": 5,
-  "complexity": "medium",
-  "estimatedMinutes": 30,
-  "memoryLoaded": true
-}
-```
-
-## See Also
-
-- `hook post-task` - Post-task cleanup
-- `agent spawn` - Manual agent creation
-- `memory usage` - Memory management
-- `swarm init` - Swarm initialization

package/.claude/commands/hooks/session-end.md

@@ -1,118 +0,0 @@
-# hook session-end
-
-Cleanup and persist session state before ending work.
-
-## Usage
-
-```bash
-npx claude-flow hook session-end [options]
-```
-
-## Options
-
-- `--session-id, -s <id>` - Session identifier to end
-- `--save-state` - Save current session state (default: true)
-- `--export-metrics` - Export session metrics
-- `--generate-summary` - Create session summary
-- `--cleanup-temp` - Remove temporary files
-
-## Examples
-
-### Basic session end
-
-```bash
-npx claude-flow hook session-end --session-id "dev-session-2024"
-```
-
-### With full export
-
-```bash
-npx claude-flow hook session-end -s "feature-auth" --export-metrics --generate-summary
-```
-
-### Quick close
-
-```bash
-npx claude-flow hook session-end -s "quick-fix" --save-state false --cleanup-temp
-```
-
-### Complete persistence
-
-```bash
-npx claude-flow hook session-end -s "major-refactor" --save-state --export-metrics --generate-summary
-```
-
-## Features
-
-### State Persistence
-
-- Saves current context
-- Stores open files
-- Preserves task progress
-- Maintains decisions
-
-### Metric Export
-
-- Session duration
-- Commands executed
-- Files modified
-- Tokens consumed
-- Performance data
-
-### Summary Generation
-
-- Work accomplished
-- Key decisions made
-- Problems solved
-- Next steps identified
-
-### Cleanup Operations
-
-- Removes temp files
-- Clears caches
-- Frees resources
-- Optimizes storage
-
-## Integration
-
-This hook is automatically called by Claude Code when:
-
-- Ending a conversation
-- Closing work session
-- Before shutdown
-- Switching contexts
-
-Manual usage in agents:
-
-```bash
-# At session end
-npx claude-flow hook session-end --session-id "your-session" --generate-summary
-```
-
-## Output
-
-Returns JSON with:
-
-```json
-{
-  "sessionId": "dev-session-2024",
-  "duration": 7200000,
-  "saved": true,
-  "metrics": {
-    "commandsRun": 145,
-    "filesModified": 23,
-    "tokensUsed": 85000,
-    "tasksCompleted": 8
-  },
-  "summaryPath": "/sessions/dev-session-2024-summary.md",
-  "cleanedUp": true,
-  "nextSession": "dev-session-2025"
-}
-```
-
-## See Also
-
-- `hook session-start` - Session initialization
-- `hook session-restore` - Session restoration
-- `performance report` - Detailed metrics
-- `memory backup` - State backup

package/.claude/commands/hooks/setup.md

@@ -1,103 +0,0 @@
-# Setting Up ruv-swarm Hooks
-
-## Quick Start
-
-### 1. Initialize with Hooks
-```bash
-npx claude-flow init --hooks
-```
-
-This automatically creates:
-- `.claude/settings.json` with hook configurations
-- Hook command documentation
-- Default hook handlers
-
-### 2. Test Hook Functionality
-```bash
-# Test pre-edit hook
-npx claude-flow hook pre-edit --file test.js
-
-# Test session summary
-npx claude-flow hook session-end --summary
-```
-
-### 3. Customize Hooks
-
-Edit `.claude/settings.json` to customize:
-
-```json
-{
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "^Write$",
-        "hooks": [{
-          "type": "command",
-          "command": "npx claude-flow hook pre-write --file '${tool.params.file_path}'"
-        }]
-      }
-    ]
-  }
-}
-```
-
-## Hook Response Format
-
-Hooks return JSON with:
-- `continue`: Whether to proceed (true/false)
-- `reason`: Explanation for decision
-- `metadata`: Additional context
-
-Example blocking response:
-```json
-{
-  "continue": false,
-  "reason": "Protected file - manual review required",
-  "metadata": {
-    "file": ".env.production",
-    "protection_level": "high"
-  }
-}
-```
-
-## Performance Tips
-- Keep hooks lightweight (< 100ms)
-- Use caching for repeated operations
-- Batch related operations
-- Run non-critical hooks asynchronously
-
-## Debugging Hooks
-```bash
-# Enable debug output
-export CLAUDE_FLOW_DEBUG=true
-
-# Test specific hook
-npx claude-flow hook pre-edit --file app.js --debug
-```
-
-## Common Patterns
-
-### Auto-Format on Save
-Already configured by default for common file types.
-
-### Protected File Detection
-```json
-{
-  "matcher": "^(Write|Edit)$",
-  "hooks": [{
-    "type": "command",
-    "command": "npx claude-flow hook check-protected --file '${tool.params.file_path}'"
-  }]
-}
-```
-
-### Automatic Testing
-```json
-{
-  "matcher": "^Write$",
-  "hooks": [{
-    "type": "command",
-    "command": "test -f '${tool.params.file_path%.js}.test.js' && npm test '${tool.params.file_path%.js}.test.js'"
-  }]
-}
-```

package/.claude/commands/simplify.md

@@ -1,101 +0,0 @@
----
-description: Review changed code for reuse, quality, and efficiency, then fix any issues found. Sizes review effort to the diff and routes the cheapest model that fits.
----
-
-# /simplify — Adaptive Gate-Compliant Code Review
-
-Review changed code for reuse, quality, and efficiency. **Effort scales with diff size; model is routed for cost.** A 5-line comment trim does not get 3 Opus agents.
-
-## Phase 0: Gate prerequisites
-
-These satisfy the memory-first and task-create-first gates. Always do them before any Agent spawn.
-
-1. **Memory search** — `mcp__moflo__memory_search — query: "code quality patterns", namespace: "patterns"`
-2. **Task create** — `TaskCreate — subject: "🔍 [Reviewer] Simplify changed code"`
-
-## Phase 1: Identify the diff
-
-```bash
-git diff HEAD          # working tree
-git diff main...HEAD   # committed since branch base
-```
-
-Treat the union as the diff. Note whether `/simplify` already ran on this branch in this session — if so, you are in a **validation pass** (Phase 4 below).
-
-## Phase 2: Classify the diff
-
-Pick the smallest tier the diff genuinely fits.
-
-| Tier | Trigger | Action |
-|------|---------|--------|
-| **TRIVIAL** | ≤10 net LOC, single file, comments/formatting/local renames only | Self-review, zero agents |
-| **SMALL** | ≤200 net LOC, ≤2 files, no API/dependency change | **One agent** (default for most diffs, including critical surface) |
-| **NORMAL** | ≥3 files, OR >200 LOC, OR public API change, OR new/removed dependency, OR cross-cutting refactor | Three parallel agents |
-
-Critical-surface files (launcher, hooks, MCP wiring) raise the *care* of the agent prompt — sharper checklist, blast-radius framing — they do **not** automatically escalate to NORMAL. Risk-weighted ≠ headcount-weighted.
-
-## Phase 3: Use the classifier's model (skip for TRIVIAL)
-
-The classifier returns the right model for the tier — no separate router call needed:
-
-- `sonnet` (default) — real logic edits, single agent or 3-agent fan-out.
-- `haiku` — mostly-relocation diffs (mechanical moves; pattern-matching beats deep reasoning).
-- `opus` — never returned. Code review is breadth-bound, not depth-bound; sonnet 3-way IS the high-effort tier.
-
-Pass the classifier's `model` field verbatim to Agent's `model` parameter. If you fell back to prose rules in Phase 2 (no classifier), default to `sonnet`.
-
-## Phase 4: Validation pass (re-run after fixes from a prior simplify)
-
-If `/simplify` already ran on this branch in this session AND the only edits since are fixes the prior pass surfaced, **default to TRIVIAL self-review** regardless of LOC count. The fan-out happened; the fix is small relative to the already-reviewed diff.
-
-Escalate one tier (self-review → SMALL agent) only if the fix introduced a new file, a new exported symbol, a new dependency, or a control-flow change not covered by the original findings. Never escalate a validation pass to NORMAL.
-
-## Phase 5: Run the appropriate review
-
-### TRIVIAL
-Print one confirmation line (`simplify: TRIVIAL — N LOC, 1 file — stamped`) and exit. **Do not** walk the three-category check; the classifier already concluded the diff is below the review-value threshold. Budget: <5 seconds, no Agent.
-
-### Validation pass
-Run the three category checks against the post-fix diff in one pass. Most are clean — confirm and exit. Budget: ~30 seconds, no Agent.
-
-### SMALL — one agent
-```
-Agent — {
-  subagent_type: "reviewer",
-  model: "<sonnet (or haiku for trivial-formatting tier from router)>",
-  prompt: "FIRST ACTION: Run mcp__moflo__memory_search with query 'code review patterns' and namespace 'patterns' to satisfy the memory-first gate. THEN review this diff for reuse, quality, and efficiency. <diff inline>. Flag specific issues as file:line + 1-line description. Max 5 file reads. Under 200 words. Skip cosmetic style. Don't suggest cross-cutting refactors of code outside this diff."
-}
-```
-
-For critical-surface files, prepend a 1-line risk note (e.g., "This is `bin/session-start-launcher.mjs` — runs in every consumer's session-start hot path; cross-platform + blast-radius matter."). One careful agent, not three.
-
-### NORMAL — three parallel agents
-Launch three agents in a single message, each at the routed model (typically sonnet). Each agent gets the SMALL-tier tool-budget cap.
-
-- **Agent 1 (Reuse):** existing helpers/utilities that should be used; duplicated patterns; functions re-implementing something already in the codebase.
-- **Agent 2 (Quality):** redundant state, parameter sprawl, copy-paste with variation, leaky abstractions, stringly-typed code, nested conditionals 3+ levels, unnecessary comments.
-- **Agent 3 (Efficiency):** unnecessary work, missed concurrency, hot-path bloat, recurring no-op updates, TOCTOU existence checks, unbounded structures, over-broad reads.
-
-Each agent prompt must start with `FIRST ACTION: mcp__moflo__memory_search ... namespace: "patterns"` — subagents must satisfy the memory-first gate independently before Glob/Grep/Read.
-
-## Phase 6: Fix or skip
-
-Aggregate findings. Fix each issue directly that's worth fixing. False positives or out-of-scope: note and skip without arguing.
-
-If fixes were made, re-run tests to confirm nothing broke. If tests fail after a fix, revert it.
-
-After fixes: the next `/simplify` invocation is a **validation pass** (Phase 4). Bundle related fixes into one batch so a single validation pass covers them — don't re-fan-out for cosmetic micro-corrections.
-
-## Phase 7: Optional — record routing outcome
-
-If you spawned an agent, feed back the outcome so the router learns:
-
-```
-mcp__moflo__hooks_model-outcome — { task: "...", model: "<chosen>", outcome: "success" | "failure" | "escalated" }
-```
-
-`escalated` only when a real miss happened that a higher tier would have caught — never used to retroactively justify opus.
-
-## Briefly summarize
-
-End with one or two sentences: which tier ran, which model, what was fixed (or "clean — no changes"). No headers, no bullets.

package/.claude/commands/sparc/analyzer.md

@@ -1,42 +0,0 @@
-# SPARC Analyzer Mode
-
-## Purpose
-Deep code and data analysis with batch processing capabilities.
-
-## Activation
-
-### Option 1: Using MCP Tools (Preferred in Claude Code)
-
-### Option 2: Using NPX CLI (Fallback when MCP not available)
-```bash
-# Use when running from terminal or MCP tools unavailable
-npx claude-flow sparc run analyzer "analyze codebase performance"
-
-# For alpha features
-npx claude-flow@alpha sparc run analyzer "analyze codebase performance"
-```
-
-### Option 3: Local Installation
-```bash
-# If claude-flow is installed locally
-./claude-flow sparc run analyzer "analyze codebase performance"
-```
-
-## Core Capabilities
-- Code analysis with parallel file processing
-- Data pattern recognition
-- Performance profiling
-- Memory usage analysis
-- Dependency mapping
-
-## Batch Operations
-- Parallel file analysis using concurrent Read operations
-- Batch pattern matching with Grep tool
-- Simultaneous metric collection
-- Aggregated reporting
-
-## Output Format
-- Detailed analysis reports
-- Performance metrics
-- Improvement recommendations
-- Visualizations when applicable