Multi Model Validation

Multi-Model Validation

Version: 3.1.0 Purpose: Patterns for running multiple AI models in parallel via Claudish proxy with dynamic model discovery, session-based workspaces, and performance statistics Status: Production Ready

Overview

Multi-model validation is the practice of running multiple AI models (Grok, Gemini, GPT-5, DeepSeek, etc.) in parallel to validate code, designs, or implementations from different perspectives. This achieves:

• 3-5x speedup via parallel execution (15 minutes → 5 minutes)
• Consensus-based prioritization (issues flagged by all models are CRITICAL)
• Diverse perspectives (different models catch different issues)
• Cost transparency (know before you spend)
• Free model discovery (NEW v3.0) - find high-quality free models from trusted providers
• Performance tracking - identify slow/failing models for future exclusion
• Data-driven recommendations - optimize model shortlist based on historical performance

Key Innovations:

1. Dynamic Model Discovery (NEW v3.0) - Use claudish --top-models and claudish --free to get current available models with pricing
2. Session-Based Workspaces (NEW v3.0) - Each validation session gets a unique directory to prevent conflicts
3. 4-Message Pattern - Ensures true parallel execution by using only Task tool calls in a single message
4. Pattern 7-8 - Statistics collection and data-driven model recommendations

This skill is extracted from the /review command and generalized for use in any multi-model workflow.

Related Skills

CRITICAL: Tracking Protocol Required

Before using any patterns in this skill, ensure you have completed the pre-launch setup from orchestration:model-tracking-protocol.

Launching models without tracking setup = INCOMPLETE validation.

Cross-References:

• orchestration:model-tracking-protocol - MANDATORY tracking templates and protocols (NEW in v0.6.0)
  • Pre-launch checklist (8 required items)
  • Tracking table templates
  • Failure documentation format
  • Results presentation template
• orchestration:quality-gates - Approval gates and severity classification
• orchestration:todowrite-orchestration - Progress tracking during execution
• orchestration:error-recovery - Handling failures and retries

Skill Integration:

This skill (multi-model-validation) defines execution patterns (how to run models in parallel). The model-tracking-protocol skill defines tracking infrastructure (how to collect and present results).

Use both together:

skills: orchestration:multi-model-validation, orchestration:model-tracking-protocol

Core Patterns

Pattern 0: Session Setup and Model Discovery (NEW v3.0)

Purpose: Create isolated session workspace and discover available models dynamically.

Why Session-Based Workspaces:

Using a fixed directory like ai-docs/reviews/ causes problems:

• ❌ Multiple sessions overwrite each other's files
• ❌ Stale data from previous sessions pollutes results
• ❌ Hard to track which files belong to which session

Instead, create a unique session directory for each validation:

# Generate unique session ID
SESSION_ID="review-$(date +%Y%m%d-%H%M%S)-$(head -c 4 /dev/urandom | xxd -p)"
SESSION_DIR="/tmp/${SESSION_ID}"

# Create session workspace
mkdir -p "$SESSION_DIR"

# Export for use by agents
export SESSION_ID SESSION_DIR

echo "Session: $SESSION_ID"
echo "Directory: $SESSION_DIR"

# Example output:
# Session: review-20251212-143052-a3f2
# Directory: /tmp/review-20251212-143052-a3f2

Benefits:

• ✅ Each session is isolated (no cross-contamination)
• ✅ Easy cleanup (rm -rf $SESSION_DIR when done)
• ✅ Session ID can be used for tracking in statistics
• ✅ Parallel sessions don't conflict

Dynamic Model Discovery:

NEVER hardcode model lists. Models change frequently - new ones appear, old ones deprecate, pricing updates. Instead, use claudish to get current available models:

# Get top paid models (best value for money)
claudish --top-models

# Example output:
#   google/gemini-3-pro-preview    Google     $7.00/1M   1048K   🔧 🧠 👁️
#   openai/gpt-5.1-codex           Openai     $5.63/1M   400K    🔧 🧠 👁️
#   x-ai/grok-code-fast-1          X-ai       $0.85/1M   256K    🔧 🧠
#   minimax/minimax-m2             Minimax    $0.64/1M   262K    🔧 🧠
#   z-ai/glm-4.6                   Z-ai       $1.07/1M   202K    🔧 🧠
#   qwen/qwen3-vl-235b-a22b-ins... Qwen       $0.70/1M   262K    🔧    👁️

# Get free models from trusted providers
claudish --free

# Example output:
#   google/gemini-2.0-flash-exp:free  Google     FREE      1049K   ✓ · ✓
#   mistralai/devstral-2512:free      Mistralai  FREE      262K    ✓ · ·
#   qwen/qwen3-coder:free             Qwen       FREE      262K    ✓ · ·
#   qwen/qwen3-235b-a22b:free         Qwen       FREE      131K    ✓ ✓ ·
#   openai/gpt-oss-120b:free          Openai     FREE      131K    ✓ ✓ ·

Recommended Free Models for Code Review:

Model Selection Flow:

1. Load Historical Performance (if exists)
   → Read ai-docs/llm-performance.json
   → Get avg speed, quality, success rate per model

2. Discover Available Models
   → Run: claudish --top-models (paid)
   → Run: claudish --free (free tier)

3. Merge with Historical Data
   → Add performance metrics to model list
   → Flag: "⚡ Fast", "🎯 High Quality", "⚠️ Slow", "❌ Unreliable"

4. Present to User (AskUserQuestion)
   → Show: Model | Provider | Price | Avg Speed | Quality
   → Suggest internal reviewer (ALWAYS)
   → Highlight top performers
   → Include 1-2 free models for comparison

5. User Selects Models
   → Minimum: 1 internal + 1 external
   → Recommended: 1 internal + 2-3 external

Interactive Model Selection (AskUserQuestion with multiSelect):

CRITICAL: Use AskUserQuestion tool with multiSelect: true to let users choose models interactively. This provides a better UX than just showing recommendations.

// Use AskUserQuestion to let user select models
AskUserQuestion({
  questions: [{
    question: "Which external models should validate your code? (Internal Claude reviewer always included)",
    header: "Models",
    multiSelect: true,
    options: [
      // Top paid (from claudish --top-models + historical data)
      {
        label: "x-ai/grok-code-fast-1 ⚡",
        description: "$0.85/1M | Quality: 87% | Avg: 42s | Fast + accurate"
      },
      {
        label: "google/gemini-3-pro-preview",
        description: "$7.00/1M | Quality: 91% | Avg: 55s | High accuracy"
      },
      // Free models (from claudish --free)
      {
        label: "qwen/qwen3-coder:free 🆓",
        description: "FREE | Quality: 82% | 262K context | Coding-specialized"
      },
      {
        label: "mistralai/devstral-2512:free 🆓",
        description: "FREE | 262K context | Dev-focused, new model"
      }
    ]
  }]
})

Remember Selection for Session:

Store the user's model selection in the session directory so it persists throughout the validation:

# After user selects models, save to session
save_session_models() {
  local session_dir="$1"
  shift
  local models=("$@")

  # Always include internal reviewer
  echo "claude-embedded" > "$session_dir/selected-models.txt"

  # Add user-selected models
  for model in "${models[@]}"; do
    echo "$model" >> "$session_dir/selected-models.txt"
  done

  echo "Session models saved to $session_dir/selected-models.txt"
}

# Load session models for subsequent operations
load_session_models() {
  local session_dir="$1"
  cat "$session_dir/selected-models.txt"
}

# Usage:
# After AskUserQuestion returns selected models
save_session_models "$SESSION_DIR" "x-ai/grok-code-fast-1" "qwen/qwen3-coder:free"

# Later in the session, retrieve the selection
MODELS=$(load_session_models "$SESSION_DIR")

Session Model Memory Structure:

$SESSION_DIR/
├── selected-models.txt    # User's model selection (persists for session)
├── code-context.md        # Code being reviewed
├── claude-review.md       # Internal review
├── grok-review.md         # External review (if selected)
├── qwen-coder-review.md   # External review (if selected)
└── consolidated-review.md # Final consolidated review

Why Remember the Selection:

1. Re-runs: If validation needs to be re-run, use same models
2. Consistency: All phases of validation use identical model set
3. Audit trail: Know which models produced which results
4. Cost tracking: Accurate cost attribution per session

Always Include Internal Reviewer:

BEST PRACTICE: Always run internal Claude reviewer alongside external models.

Why?
✓ FREE (embedded Claude, no API costs)
✓ Fast baseline (usually fastest)
✓ Provides comparison point
✓ Works even if ALL external models fail
✓ Consistent behavior (same model every time)

The internal reviewer should NEVER be optional - it's your safety net.

Pattern 1: The 4-Message Pattern (MANDATORY)

This pattern is CRITICAL for achieving true parallel execution with multiple AI models.

Why This Pattern Exists:

Claude Code executes tools sequentially by default when different tool types are mixed in the same message. To achieve true parallelism, you MUST:

1. Use ONLY one tool type per message
2. Ensure all Task calls are in a single message
3. Separate preparation (Bash) from execution (Task) from presentation

The Pattern:

Message 1: Preparation (Bash Only)
  - Create workspace directories
  - Validate inputs (check if claudish installed)
  - Write context files (code to review, design reference, etc.)
  - NO Task calls
  - NO TodoWrite calls

Message 2: Parallel Execution (Task Only)
  - Launch ALL AI models in SINGLE message
  - ONLY Task tool calls
  - Separate each Task with --- delimiter
  - Each Task is independent (no dependencies)
  - All execute simultaneously

Message 3: Auto-Consolidation (Task Only)
  - Automatically triggered when N ≥ 2 models complete
  - Launch consolidation agent
  - Pass all review file paths
  - Apply consensus analysis

Message 4: Present Results
  - Show user prioritized issues
  - Include consensus levels (unanimous, strong, majority)
  - Link to detailed reports
  - Cost summary (if applicable)

Example: 5-Model Parallel Code Review

Message 1: Preparation (Session Setup + Model Discovery)
  # Create unique session workspace
  Bash: SESSION_ID="review-$(date +%Y%m%d-%H%M%S)-$(head -c 4 /dev/urandom | xxd -p)"
  Bash: SESSION_DIR="/tmp/${SESSION_ID}" && mkdir -p "$SESSION_DIR"
  Bash: git diff > "$SESSION_DIR/code-context.md"

  # Discover available models
  Bash: claudish --top-models  # See paid options
  Bash: claudish --free        # See free options

  # User selects models via AskUserQuestion (see Pattern 0)

Message 2: Parallel Execution (ONLY Task calls - single message)
  Task: senior-code-reviewer
    Prompt: "Review $SESSION_DIR/code-context.md for security issues.
             Write detailed review to $SESSION_DIR/claude-review.md
             Return only brief summary."
  ---
  Task: codex-code-reviewer PROXY_MODE: x-ai/grok-code-fast-1
    Prompt: "Review $SESSION_DIR/code-context.md for security issues.
             Write detailed review to $SESSION_DIR/grok-review.md
             Return only brief summary."
  ---
  Task: codex-code-reviewer PROXY_MODE: qwen/qwen3-coder:free
    Prompt: "Review $SESSION_DIR/code-context.md for security issues.
             Write detailed review to $SESSION_DIR/qwen-coder-review.md
             Return only brief summary."
  ---
  Task: codex-code-reviewer PROXY_MODE: openai/gpt-5.1-codex
    Prompt: "Review $SESSION_DIR/code-context.md for security issues.
             Write detailed review to $SESSION_DIR/gpt5-review.md
             Return only brief summary."
  ---
  Task: codex-code-reviewer PROXY_MODE: mistralai/devstral-2512:free
    Prompt: "Review $SESSION_DIR/code-context.md for security issues.
             Write detailed review to $SESSION_DIR/devstral-review.md
             Return only brief summary."

  All 5 models execute simultaneously (5x parallelism!)

Message 3: Auto-Consolidation
  (Automatically triggered - don't wait for user to request)

  Task: senior-code-reviewer
    Prompt: "Consolidate 5 code reviews from:
             - $SESSION_DIR/claude-review.md
             - $SESSION_DIR/grok-review.md
             - $SESSION_DIR/qwen-coder-review.md
             - $SESSION_DIR/gpt5-review.md
             - $SESSION_DIR/devstral-review.md

             Apply consensus analysis:
             - Issues flagged by ALL 5 → UNANIMOUS (VERY HIGH confidence)
             - Issues flagged by 4 → STRONG (HIGH confidence)
             - Issues flagged by 3 → MAJORITY (MEDIUM confidence)
             - Issues flagged by 1-2 → DIVERGENT (LOW confidence)

             Prioritize by consensus level and severity.
             Write to $SESSION_DIR/consolidated-review.md"

Message 4: Present Results + Update Statistics
  # Track performance for each model (see Pattern 7)
  track_model_performance "claude-embedded" "success" 32 8 95
  track_model_performance "x-ai/grok-code-fast-1" "success" 45 6 87
  track_model_performance "qwen/qwen3-coder:free" "success" 52 5 82
  track_model_performance "openai/gpt-5.1-codex" "success" 68 7 89
  track_model_performance "mistralai/devstral-2512:free" "success" 48 5 84

  # Record session summary
  record_session_stats 5 5 0 68 245 3.6

  "Multi-model code review complete! 5 AI models analyzed your code.
   Session: $SESSION_ID

   Top 5 Issues (Prioritized by Consensus):
   1. [UNANIMOUS] Missing input validation on POST /api/users
   2. [UNANIMOUS] SQL injection risk in search endpoint
   3. [STRONG] Weak password hashing (bcrypt rounds too low)
   4. [MAJORITY] Missing rate limiting on authentication endpoints
   5. [MAJORITY] Insufficient error handling in payment flow

   Model Performance (this session):
   | Model                          | Time | Issues | Quality | Cost   |
   |--------------------------------|------|--------|---------|--------|
   | claude-embedded                | 32s  | 8      | 95%     | FREE   |
   | x-ai/grok-code-fast-1          | 45s  | 6      | 87%     | $0.002 |
   | qwen/qwen3-coder:free          | 52s  | 5      | 82%     | FREE   |
   | openai/gpt-5.1-codex           | 68s  | 7      | 89%     | $0.015 |
   | mistralai/devstral-2512:free   | 48s  | 5      | 84%     | FREE   |

   Parallel Speedup: 3.6x (245s sequential → 68s parallel)

   See $SESSION_DIR/consolidated-review.md for complete analysis.
   Performance logged to ai-docs/llm-performance.json"

Performance Impact:

• Sequential execution: 5 models × 3 min = 15 minutes
• Parallel execution: max(model times) ≈ 5 minutes
• Speedup: 3x with perfect parallelism

Pattern 2: Parallel Execution Architecture

Single Message, Multiple Tasks:

The key to parallel execution is putting ALL Task calls in a single message with the --- delimiter:

✅ CORRECT - Parallel Execution:

Task: agent1
  Prompt: "Task 1 instructions"
---
Task: agent2
  Prompt: "Task 2 instructions"
---
Task: agent3
  Prompt: "Task 3 instructions"

All 3 execute simultaneously.

Anti-Pattern: Sequential Execution

❌ WRONG - Sequential Execution:

Message 1:
  Task: agent1

Message 2:
  Task: agent2

Message 3:
  Task: agent3

Each task waits for previous to complete (3x slower).

Independent Tasks Requirement:

Each Task must be independent (no dependencies):

✅ CORRECT - Independent:
  Task: review code for security
  Task: review code for performance
  Task: review code for style

  All can run simultaneously (same input, different perspectives).

❌ WRONG - Dependent:
  Task: implement feature
  Task: write tests for feature (depends on implementation)
  Task: review implementation (depends on tests)

  Must run sequentially (each needs previous output).

Unique Output Files:

Each Task MUST write to a unique output file within the session directory:

✅ CORRECT - Unique Files in Session Directory:
  Task: reviewer1 → $SESSION_DIR/claude-review.md
  Task: reviewer2 → $SESSION_DIR/grok-review.md
  Task: reviewer3 → $SESSION_DIR/qwen-coder-review.md

❌ WRONG - Shared File:
  Task: reviewer1 → $SESSION_DIR/review.md
  Task: reviewer2 → $SESSION_DIR/review.md (overwrites reviewer1!)
  Task: reviewer3 → $SESSION_DIR/review.md (overwrites reviewer2!)

❌ WRONG - Fixed Directory (not session-based):
  Task: reviewer1 → ai-docs/reviews/claude-review.md  # May conflict with other sessions!

Wait for All Before Consolidation:

Do NOT consolidate until ALL tasks complete:

✅ CORRECT - Wait for All:
  Launch: Task1, Task2, Task3, Task4 (parallel)
  Wait: All 4 complete
  Check: results.filter(r => r.status === 'fulfilled').length
  If >= 2: Proceed with consolidation
  If < 2: Offer retry or abort

❌ WRONG - Premature Consolidation:
  Launch: Task1, Task2, Task3, Task4
  After 30s: Task1, Task2 done
  Consolidate: Only Task1 + Task2 (Task3, Task4 still running!)

Pattern 3: Proxy Mode Implementation

PROXY_MODE Directive:

External AI models are invoked via the PROXY_MODE directive in agent prompts:

Task: codex-code-reviewer PROXY_MODE: x-ai/grok-code-fast-1
  Prompt: "Review code for security issues..."

Agent Behavior:

When an agent sees PROXY_MODE, it:

1. Detects PROXY_MODE directive in incoming prompt
2. Extracts model name (e.g., "x-ai/grok-code-fast-1")
3. Extracts actual task (everything after PROXY_MODE line)
4. Constructs claudish command:
   printf '%s' "AGENT_PROMPT" | claudish --model x-ai/grok-code-fast-1 --stdin --quiet --auto-approve
5. Executes SYNCHRONOUSLY (blocking, waits for full response)
6. Captures full output
7. Writes detailed results to file (ai-docs/grok-review.md)
8. Returns BRIEF summary only (2-5 sentences)

Critical: Blocking Execution

External model calls MUST be synchronous (blocking) so the agent waits for completion:

✅ CORRECT - Blocking (Synchronous):
  RESULT=$(printf '%s' "$PROMPT" | claudish --model grok --stdin --quiet --auto-approve)
  echo "$RESULT" > ai-docs/grok-review.md
  echo "Grok review complete. See ai-docs/grok-review.md"

❌ WRONG - Background (Asynchronous):
  printf '%s' "$PROMPT" | claudish --model grok --stdin --quiet --auto-approve &
  echo "Grok review started..."  # Agent returns immediately, review not done!

Why Blocking Matters:

If agents return before external models complete, the orchestrator will:

• Think all reviews are done (they're not)
• Try to consolidate partial results (missing data)
• Present incomplete results to user (bad experience)

Output Strategy:

Agents write full detailed output to file and return brief summary only:

Full Output (ai-docs/grok-review.md):
  "# Code Review by Grok

   ## Security Issues

   ### CRITICAL: SQL Injection in User Search
   The search endpoint constructs SQL queries using string concatenation...
   [500 more lines of detailed analysis]"

Brief Summary (returned to orchestrator):
  "Grok review complete. Found 3 CRITICAL, 5 HIGH, 12 MEDIUM issues.
   See ai-docs/grok-review.md for details."

Why Brief Summaries:

• Orchestrator doesn't need full 500-line review in context
• Full review is in file for consolidation agent
• Keeps orchestrator context clean (context efficiency)

Auto-Approve Flag:

Use --auto-approve flag to prevent interactive prompts:

✅ CORRECT - Auto-Approve:
  claudish --model grok --stdin --quiet --auto-approve

❌ WRONG - Interactive (blocks waiting for user input):
  claudish --model grok --stdin --quiet
  # Waits for user to approve costs... but this is inside an agent!

PROXY_MODE-Enabled Agents Reference

CRITICAL: Only these agents support PROXY_MODE. Using other agents (like general-purpose) will NOT work correctly.

Supported Agents by Plugin

agentdev plugin (3 agents)

frontend plugin (8 agents)

seo plugin (5 agents)

Total: 18 PROXY_MODE-enabled agents

How to Check if an Agent Supports PROXY_MODE

Look for <proxy_mode_support> in the agent's definition file:

grep -l "proxy_mode_support" plugins/*/agents/*.md

Common Mistakes

Correct Pattern Example

// ✅ CORRECT: Use PROXY_MODE-enabled agent with directive
Task({
  subagent_type: "agentdev:reviewer",
  description: "Grok design review",
  run_in_background: true,
  prompt: `PROXY_MODE: x-ai/grok-code-fast-1

Review the design plan at ai-docs/feature-design.md

Focus on:
1. Completeness
2. Missing considerations
3. Potential issues
4. Implementation risks`
})

// ❌ WRONG: Using general-purpose and instructing to run claudish
Task({
  subagent_type: "general-purpose",
  description: "Grok design review",
  prompt: `Review using Grok via claudish:
  npx claudish --model x-ai/grok-code-fast-1 ...`
})

Pattern 4: Cost Estimation and Transparency

Input/Output Token Separation:

Provide separate estimates for input and output tokens:

Cost Estimation for Multi-Model Review:

Input Tokens (per model):
  - Code context: 500 lines × 1.5 = 750 tokens
  - Review instructions: 200 tokens
  - Total input per model: ~1000 tokens
  - Total input (5 models): 5,000 tokens

Output Tokens (per model):
  - Expected output: 2,000 - 4,000 tokens
  - Total output (5 models): 10,000 - 20,000 tokens

Cost Calculation (example rates):
  - Input: 5,000 tokens × $0.0001/1k = $0.0005
  - Output: 15,000 tokens × $0.0005/1k = $0.0075 (3-5x more expensive)
  - Total: $0.0080 (range: $0.0055 - $0.0105)

User Approval Gate:
  "Multi-model review will cost approximately $0.008 ($0.005 - $0.010).
   Proceed? (Yes/No)"

Input Token Estimation Formula:

Input Tokens = (Code Lines × 1.5) + Instruction Tokens

Why 1.5x multiplier?
  - Code lines: ~1 token per line (average)
  - Context overhead: +50% (imports, comments, whitespace)

Example:
  500 lines of code → 500 × 1.5 = 750 tokens
  + 200 instruction tokens = 950 tokens total input

Output Token Estimation Formula:

Output Tokens = Base Estimate + Complexity Factor

Base Estimates by Task Type:
  - Code review: 2,000 - 4,000 tokens
  - Design validation: 1,000 - 2,000 tokens
  - Architecture planning: 3,000 - 6,000 tokens
  - Bug investigation: 2,000 - 5,000 tokens

Complexity Factors:
  - Simple (< 100 lines code): Use low end of range
  - Medium (100-500 lines): Use mid-range
  - Complex (> 500 lines): Use high end of range

Example:
  400 lines of complex code → 4,000 tokens (high complexity)
  50 lines of simple code → 2,000 tokens (low complexity)

Range-Based Estimates:

Always provide a range (min-max), not a single number:

✅ CORRECT - Range:
  "Estimated cost: $0.005 - $0.010 (depends on review depth)"

❌ WRONG - Single Number:
  "Estimated cost: $0.0075"
  (User surprised when actual is $0.0095)

Why Output Costs More:

Output tokens are typically 3-5x more expensive than input tokens:

Example Pricing (OpenRouter):
  - Grok: $0.50 / 1M input, $1.50 / 1M output (3x difference)
  - Gemini Flash: $0.10 / 1M input, $0.40 / 1M output (4x difference)
  - GPT-5 Codex: $1.00 / 1M input, $5.00 / 1M output (5x difference)

Impact:
  If input = 5,000 tokens, output = 15,000 tokens:
    Input cost: $0.0005
    Output cost: $0.0075 (15x higher despite only 3x more tokens)
    Total: $0.0080 (94% is output!)

User Approval Before Execution:

ALWAYS ask for user approval before expensive operations:

Present to user:
  "You selected 5 AI models for code review:
   - Claude Sonnet (embedded, free)
   - Grok Code Fast (external, $0.002)
   - Gemini 2.5 Flash (external, $0.001)
   - GPT-5 Codex (external, $0.004)
   - DeepSeek Coder (external, $0.001)

   Estimated total cost: $0.008 ($0.005 - $0.010)

   Proceed with multi-model review? (Yes/No)"

If user says NO:
  Offer alternatives:
    1. Use only free embedded Claude
    2. Select fewer models
    3. Cancel review

If user says YES:
  Proceed with Message 2 (parallel execution)

Pattern 5: Auto-Consolidation Logic

Automatic Trigger:

Consolidation should happen automatically when N ≥ 2 reviews complete:

✅ CORRECT - Auto-Trigger:

const results = await Promise.allSettled([task1, task2, task3, task4, task5]);
const successful = results.filter(r => r.status === 'fulfilled');

if (successful.length >= 2) {
  // Auto-trigger consolidation (DON'T wait for user to ask)
  const consolidated = await Task({
    subagent_type: "senior-code-reviewer",
    description: "Consolidate reviews",
    prompt: `Consolidate ${successful.length} reviews and apply consensus analysis`
  });

  return formatResults(consolidated);
} else {
  // Too few successful reviews
  notifyUser("Only 1 model succeeded. Retry failures or abort?");
}

❌ WRONG - Wait for User:

const results = await Promise.allSettled([...]);
const successful = results.filter(r => r.status === 'fulfilled');

// Present results to user
notifyUser("3 reviews complete. Would you like me to consolidate them?");
// Waits for user to request consolidation...

Why Auto-Trigger:

• Better UX (no extra user prompt needed)
• Faster workflow (no wait for user response)
• Expected behavior (user assumes consolidation is part of workflow)

Minimum Threshold:

Require at least 2 successful reviews for meaningful consensus:

if (successful.length >= 2) {
  // Proceed with consolidation
} else if (successful.length === 1) {
  // Only 1 review succeeded
  notifyUser("Only 1 model succeeded. No consensus available. See single review or retry?");
} else {
  // All failed
  notifyUser("All models failed. Check logs and retry?");
}

Pass All Review File Paths:

Consolidation agent needs paths to ALL review files within the session directory:

Task: senior-code-reviewer
  Prompt: "Consolidate reviews from these files:
           - $SESSION_DIR/claude-review.md
           - $SESSION_DIR/grok-review.md
           - $SESSION_DIR/qwen-coder-review.md

           Apply consensus analysis and prioritize issues."

Don't Inline Full Reviews:

❌ WRONG - Inline Reviews (context pollution):
  Prompt: "Consolidate these reviews:

           Claude Review:
           [500 lines of review content]

           Grok Review:
           [500 lines of review content]

           Qwen Review:
           [500 lines of review content]"

✅ CORRECT - File Paths in Session Directory:
  Prompt: "Read and consolidate reviews from:
           - $SESSION_DIR/claude-review.md
           - $SESSION_DIR/grok-review.md
           - $SESSION_DIR/qwen-coder-review.md"

Pattern 6: Consensus Analysis

Consensus Levels:

Classify issues by how many models flagged them:

Consensus Levels (for N models):

UNANIMOUS (100% agreement):
  - All N models flagged this issue
  - VERY HIGH confidence
  - MUST FIX priority

STRONG CONSENSUS (67-99% agreement):
  - Most models flagged this issue (⌈2N/3⌉ to N-1)
  - HIGH confidence
  - RECOMMENDED priority

MAJORITY (50-66% agreement):
  - Half or more models flagged this issue (⌈N/2⌉ to ⌈2N/3⌉-1)
  - MEDIUM confidence
  - CONSIDER priority

DIVERGENT (< 50% agreement):
  - Only 1-2 models flagged this issue
  - LOW confidence
  - OPTIONAL priority (may be model-specific perspective)

Example: 5 Models

Issue Flagged By:              Consensus Level:    Priority:
─────────────────────────────────────────────────────────────
All 5 models                   UNANIMOUS (100%)    MUST FIX
4 models                       STRONG (80%)        RECOMMENDED
3 models                       MAJORITY (60%)      CONSIDER
2 models                       DIVERGENT (40%)     OPTIONAL
1 model                        DIVERGENT (20%)     OPTIONAL

Keyword-Based Matching (v1.0):

Simple consensus analysis using keyword matching:

Algorithm:

1. Extract issues from each review
2. For each unique issue:
   a. Identify keywords (e.g., "SQL injection", "input validation")
   b. Check which other reviews mention same keywords
   c. Count models that flagged this issue
   d. Assign consensus level

Example:

Claude Review: "Missing input validation on POST /api/users"
Grok Review: "Input validation absent in user creation endpoint"
Gemini Review: "No validation for user POST endpoint"

Keywords: ["input validation", "POST", "/api/users", "user"]
Match: All 3 reviews mention these keywords
Consensus: UNANIMOUS (3/3 = 100%)

Model Agreement Matrix:

Show which models agree on which issues:

Issue Matrix:

Issue                             Claude  Grok  Gemini  GPT-5  DeepSeek  Consensus
──────────────────────────────────────────────────────────────────────────────────
SQL injection in search              ✓      ✓     ✓       ✓       ✓      UNANIMOUS
Missing input validation             ✓      ✓     ✓       ✓       ✗      STRONG
Weak password hashing                ✓      ✓     ✓       ✗       ✗      MAJORITY
Missing rate limiting                ✓      ✓     ✗       ✗       ✗      DIVERGENT
Insufficient error handling          ✓      ✗     ✗       ✗       ✗      DIVERGENT

Prioritized Issue List:

Sort issues by consensus level, then by severity:

Top 10 Issues (Prioritized):

1. [UNANIMOUS - CRITICAL] SQL injection in search endpoint
   Flagged by: Claude, Grok, Gemini, GPT-5, DeepSeek (5/5)

2. [UNANIMOUS - HIGH] Missing input validation on POST /api/users
   Flagged by: Claude, Grok, Gemini, GPT-5, DeepSeek (5/5)

3. [STRONG - HIGH] Weak password hashing (bcrypt rounds too low)
   Flagged by: Claude, Grok, Gemini, GPT-5 (4/5)

4. [STRONG - MEDIUM] Missing rate limiting on auth endpoints
   Flagged by: Claude, Grok, Gemini, GPT-5 (4/5)

5. [MAJORITY - MEDIUM] Insufficient error handling in payment flow
   Flagged by: Claude, Grok, Gemini (3/5)

... (remaining issues)

Future Enhancement (v1.1+): Semantic Similarity

Instead of keyword matching, use semantic similarity:
  - Embed issue descriptions with sentence-transformers
  - Calculate cosine similarity between embeddings
  - Issues with >0.8 similarity are "same issue"
  - More accurate consensus detection

Pattern 7: Statistics Collection and Analysis

Purpose: Track model performance to help users identify slow or poorly-performing models for future exclusion.

Storage Location: ai-docs/llm-performance.json (persistent across all sessions)

When to Collect Statistics:

• After each model completes (success, failure, or timeout)
• During consolidation phase (quality scores)
• At session end (session summary)

File Structure (ai-docs/llm-performance.json):

{
  "schemaVersion": "2.0.0",
  "lastUpdated": "2025-12-12T10:45:00Z",
  "models": {
    "claude-embedded": {
      "modelId": "claude-embedded",
      "provider": "Anthropic",
      "isFree": true,
      "pricing": "FREE (embedded)",
      "totalRuns": 12,
      "successfulRuns": 12,
      "failedRuns": 0,
      "totalExecutionTime": 420,
      "avgExecutionTime": 35,
      "minExecutionTime": 28,
      "maxExecutionTime": 52,
      "totalIssuesFound": 96,
      "avgQualityScore": 92,
      "totalCost": 0,
      "qualityScores": [95, 90, 88, 94, 91],
      "lastUsed": "2025-12-12T10:35:22Z",
      "trend": "stable",
      "history": [
        {
          "timestamp": "2025-12-12T10:35:22Z",
          "session": "review-20251212-103522-a3f2",
          "status": "success",
          "executionTime": 32,
          "issuesFound": 8,
          "qualityScore": 95,
          "cost": 0
        }
      ]
    },
    "x-ai-grok-code-fast-1": {
      "modelId": "x-ai/grok-code-fast-1",
      "provider": "X-ai",
      "isFree": false,
      "pricing": "$0.85/1M",
      "totalRuns": 10,
      "successfulRuns": 9,
      "failedRuns": 1,
      "totalCost": 0.12,
      "trend": "improving"
    },
    "qwen-qwen3-coder-free": {
      "modelId": "qwen/qwen3-coder:free",
      "provider": "Qwen",
      "isFree": true,
      "pricing": "FREE",
      "totalRuns": 5,
      "successfulRuns": 5,
      "failedRuns": 0,
      "totalCost": 0,
      "trend": "stable"
    }
  },
  "sessions": [
    {
      "sessionId": "review-20251212-103522-a3f2",
      "timestamp": "2025-12-12T10:35:22Z",
      "totalModels": 4,
      "successfulModels": 3,
      "failedModels": 1,
      "parallelTime": 120,
      "sequentialTime": 335,
      "speedup": 2.8,
      "totalCost": 0.018,
      "freeModelsUsed": 2
    }
  ],
  "recommendations": {
    "topPaid": ["x-ai/grok-code-fast-1", "google/gemini-3-pro-preview"],
    "topFree": ["qwen/qwen3-coder:free", "mistralai/devstral-2512:free"],
    "bestValue": ["x-ai/grok-code-fast-1"],
    "avoid": [],
    "lastGenerated": "2025-12-12T10:45:00Z"
  }
}

Key Benefits of Persistent Storage:

• Track model reliability over time (not just one session)
• Identify consistently slow models
• Calculate historical success rates
• Generate data-driven shortlist recommendations

How to Calculate Quality Score:

Quality = % of model's issues that appear in unanimous or strong consensus

quality_score = (issues_in_unanimous + issues_in_strong) / total_issues * 100

Example:
- Model found 10 issues
- 4 appear in unanimous consensus
- 3 appear in strong consensus
- Quality = (4 + 3) / 10 * 100 = 70%

Higher quality means the model finds issues other models agree with.

How to Calculate Parallel Speedup:

speedup = sum(all_execution_times) / max(execution_time)

Example:
- Claude: 32s
- Grok: 45s
- Gemini: 38s
- GPT-5: 120s

Sequential would take: 32 + 45 + 38 + 120 = 235s
Parallel took: max(32, 45, 38, 120) = 120s
Speedup: 235 / 120 = 1.96x

Performance Statistics Display Format:

## Model Performance Statistics

| Model                     | Time   | Issues | Quality | Status    |
|---------------------------|--------|--------|---------|-----------|
| claude-embedded           | 32s    | 8      | 95%     | ✓         |
| x-ai/grok-code-fast-1     | 45s    | 6      | 85%     | ✓         |
| google/gemini-2.5-flash   | 38s    | 5      | 90%     | ✓         |
| openai/gpt-5.1-codex      | 120s   | 9      | 88%     | ✓ (slow)  |
| deepseek/deepseek-chat    | TIMEOUT| 0      | -       | ✗         |

**Session Summary:**
- Parallel Speedup: 1.96x (235s sequential → 120s parallel)
- Average Time: 59s
- Slowest: gpt-5.1-codex (2.0x avg)

**Recommendations:**
⚠️ gpt-5.1-codex runs 2x slower than average - consider removing
⚠️ deepseek-chat timed out - check API status or remove from shortlist
✓ Top performers: claude-embedded, gemini-2.5-flash (fast + high quality)

Recommendation Logic:

1. Flag SLOW models:
   if (model.executionTime > 2 * avgExecutionTime) {
     flag: "⚠️ Runs 2x+ slower than average"
     suggestion: "Consider removing from shortlist"
   }

2. Flag FAILED/TIMEOUT models:
   if (model.status !== "success") {
     flag: "⚠️ Failed or timed out"
     suggestion: "Check API status or increase timeout"
   }

3. Identify TOP PERFORMERS:
   if (model.qualityScore > 85 && model.executionTime < avgExecutionTime) {
     highlight: "✓ Top performer (fast + high quality)"
   }

4. Suggest SHORTLIST:
   sortedModels = models.sort((a, b) => {
     // Quality/speed ratio: higher quality + lower time = better
     scoreA = a.qualityScore / (a.executionTime / avgExecutionTime)
     scoreB = b.qualityScore / (b.executionTime / avgExecutionTime)
     return scoreB - scoreA
   })
   shortlist = sortedModels.slice(0, 3)

Implementation (writes to ai-docs/llm-performance.json):

# Track model performance after each model completes
# Updates historical aggregates and adds to run history
# Parameters: model_id, status, duration, issues, quality_score, cost, is_free
track_model_performance() {
  local model_id="$1"
  local status="$2"
  local duration="$3"
  local issues="${4:-0}"
  local quality_score="${5:-}"
  local cost="${6:-0}"
  local is_free="${7:-false}"

  local perf_file="ai-docs/llm-performance.json"
  local model_key=$(echo "$model_id" | tr '/:' '-')  # Handle colons in free model names

  # Initialize file if doesn't exist
  [[ -f "$perf_file" ]] || echo '{"schemaVersion":"2.0.0","models":{},"sessions":[],"recommendations":{}}' > "$perf_file"

  jq --arg model "$model_key" \
     --arg model_full "$model_id" \
     --arg status "$status" \
     --argjson duration "$duration" \
     --argjson issues "$issues" \
     --arg quality "${quality_score:-null}" \
     --argjson cost "$cost" \
     --argjson is_free "$is_free" \
     --arg now "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
     --arg session "${SESSION_ID:-unknown}" \
     '
     # Initialize model if not exists
     .models[$model] //= {"modelId":$model_full,"provider":"unknown","isFree":$is_free,
       "totalRuns":0,"successfulRuns":0,"failedRuns":0,
       "totalExecutionTime":0,"avgExecutionTime":0,"minExecutionTime":null,"maxExecutionTime":null,
       "totalIssuesFound":0,"avgQualityScore":null,"qualityScores":[],"totalCost":0,
       "lastUsed":null,"trend":"new","history":[]} |

     # Update aggregates
     .models[$model].totalRuns += 1 |
     .models[$model].successfulRuns += (if $status == "success" then 1 else 0 end) |
     .models[$model].failedRuns += (if $status != "success" then 1 else 0 end) |
     .models[$model].totalExecutionTime += $duration |
     .models[$model].avgExecutionTime = ((.models[$model].totalExecutionTime / .models[$model].totalRuns) | floor) |
     .models[$model].totalIssuesFound += $issues |
     .models[$model].totalCost += $cost |
     .models[$model].isFree = $is_free |
     .models[$model].lastUsed = $now |

     # Update min/max
     .models[$model].minExecutio

…(truncated)