Documentation

Technical deep-dive into NoMoreAISlop's analysis pipeline

Getting Started

What is NoMoreAISlop?

NoMoreAISlop analyzes your Claude Code sessions to reveal how you collaborate with AI. It examines your prompts, tool usage patterns, and coding style to generate a personalized assessment of your developer-AI workflow.

Quick Start

Run the CLI to analyze your sessions:

bash
$ npx no-ai-slop

What Data is Analyzed

NoMoreAISlop reads Claude Code session logs from ~/.claude/projects/. These are JSONL files containing your conversation history with Claude.

JSONL Structure

Each session file contains message blocks of these types:

  • user - Your prompts and messages
  • assistant - Claude's responses
  • tool_use - Tool invocations (Read, Edit, Bash, etc.)
  • tool_result - Results from tool executions

Path Encoding

Claude Code encodes project paths by replacing / with -. For example, /Users/you/projects/myapp becomes -Users-you-projects-myapp.

How Analysis Works

The analysis pipeline runs in four phases, using Gemini 3 Flash for AI-powered analysis.

Phase 1: Session Scanning (CLI)

A memory-efficient 4-phase algorithm identifies your highest-quality sessions:

  1. File Discovery - Scans ~/.claude/projects/ for session files
  2. Pre-filter - Filters by size and recency to reduce candidates
  3. Quality Scoring - Scores top 100 candidates on message count, duration, tool diversity, recency
  4. Parse Selection - Parses the top 15 highest-quality sessions

Phase 2: AI Analysis Pipeline

Three parallel analyzers extract structured data from your sessions:

Module A: Data Analyst

Extracts behavioral patterns, coding style indicators, and representative quotes from your sessions.

Module C: Productivity Analyst

Analyzes efficiency metrics, work patterns, and productivity indicators.

Multitasking Analyzer

Examines cross-session patterns and context-switching behavior.

Phase 2.5: Insight Generation (Premium+)

Six specialist agents run in parallel for deep analysis:

PatternDetectiveCross-session behavior patterns
AntiPatternSpotterInefficiency detection
KnowledgeGapLearning opportunities
ContextEfficiencyContext utilization analysis
MetacognitionSelf-awareness and blind spots
TemporalAnalyzerTime-based quality and fatigue

Phase 3: Type Synthesis

Refines your coding style classification using all Phase 2 insights. Combines 5 types with 3 control levels for 15 personality combinations.

Phase 4: Content Writer

Transforms all outputs into a personalized narrative, connecting evidence quotes to dimension insights and applying tier-based content filtering.

Pipeline Overview

~/.claude/projects/ --> CLI Scanner --> Session Selection
        |
   Gemini 3 Flash
        |
  +--------------------------------------------+
  | Module A (Data) --+                        |
  | Module C (Prod) --+--> Phase 2.5           |
  | Multitasking -----+    (6 Agents)          |
  |                            |               |
  |                     Type Synthesis         |
  |                            |               |
  |                     Content Writer         |
  +--------------------------------------------+
        |
   Supabase --> Web Report

CLI Reference

Main Command

bash
$ npx no-ai-slop

Analyzes your Claude Code sessions and generates a shareable report. First-time users are guided through device-flow authentication.

Authentication Commands

Check Status

bash
$ npx no-ai-slop status

Shows your current authentication status and linked account.

Logout

bash
$ npx no-ai-slop logout

Clears your local authentication credentials.

Help

bash
$ npx no-ai-slop help

Displays available commands and usage information.

Authentication Flow

NoMoreAISlop uses OAuth-style device flow authentication:

  1. CLI generates a unique device code
  2. Browser opens to authentication page
  3. You sign in with your account
  4. CLI receives authentication token
  5. Token is stored locally for future sessions

Output

After successful analysis, the CLI displays a celebration animation and provides a shareable URL to your personalized report.

Understanding Your Report

The 5 Coding Styles

StyleDescription
ArchitectPlans extensively before coding
AnalystVerifies and investigates thoroughly
ConductorOrchestrates AI tools and workflows
SpeedrunnerOptimizes for velocity
TrendsetterExplores cutting-edge approaches

The 3 Control Levels

LevelDescription
ExplorerOpen exploration - discovering solutions through experimentation
NavigatorBalanced navigation - exploration with route planning
CartographerStrategic mapping - charting territory before advancing

The 6 Dimensions

DimensionMeasures
AI Collaboration MasteryPlanning quality, verification habits, instruction clarity
Context EngineeringWRITE/SELECT/COMPRESS/ISOLATE strategies
Tool MasteryRead/Edit/Bash patterns, tool variety
Burnout RiskSession length, frequency, context switching
AI Control IndexStrategic control vs reactive acceptance
Skill ResilienceIndependent coding ability vs AI reliance

Our Mission

The Question

Are you getting better with AI—or just more dependent?

Our Philosophy

Technology moves fast. AI is making it exponential.

Here's the uncomfortable truth: when thinking becomes optional, we stop doing it. And when we stop thinking, we stop growing.

AI isn't the problem. Unconscious dependency is.

The developers who thrive won't be those who delegate everything—they'll be those who know when to think for themselves and when to let AI multiply their work. AI should be a force multiplier, not a replacement for judgment.

Our Vision

We're building a future where humans use tools—not the other way around.

Our goal is simple: help you see yourself clearly. How are you actually using AI? What mistakes keep repeating? Are you thinking critically—or just accepting?

Self-awareness is the first step to growth. We start with developers—the community at the frontier of human-AI collaboration.

Our Values

Think First

AI amplifies judgment. It doesn't replace the need for it.

Open Source

Our methodology is transparent. See exactly how we evaluate.

Privacy First

Your data stays yours. Analysis happens locally.