Skip to content
CAI
Software that uses CAICheck a score

SuperClaude-Org/SuperClaude_Framework

58.4

Adequate · 16 November 2026

6k

lines of production code

Python

with TypeScript

5

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

SuperClaude is an AI agent orchestration framework that provides a suite of specialized agents and execution engines for automated software development tasks. It features a code-driven architecture with capabilities for parallel task execution, self-correction, and pre-execution confidence checking to ensure reliability. The system is distributed as a dual-platform package for both Python and Node.js environments, integrating with Claude Code via slash commands and MCP servers.

Features

Added pre-implementation confidence check skill

A new 'Confidence Check' skill has been added to the project's skills directory, providing a TypeScript implementation and documentation for assessing readiness before starting work. This tool requires a confidence score of at least 90% to proceed, evaluating five criteria: absence of duplicate implementations, architecture compliance, verification of official documentation, presence of working open-source references, and clear identification of the root cause. The skill includes a \ConfidenceChecker\ class that calculates a score based on these checks and provides recommendations to either proceed, investigate further, or stop entirely, aiming to prevent wrong-direction execution and save tokens.

.claude, skills · high confidence

New scripts for PyPI publishing, plugin building, and workflow analysis

The \scripts\ directory now includes a comprehensive set of tools for distribution and optimization. Users can build and publish the package to PyPI using \publish.sh\ (a wrapper) or \build\_and\_upload.py\ (advanced control), with support for TestPyPI and production releases. A new \build\_superclaude\_plugin.py\ script generates plugin distribution artifacts by rendering manifests and copying assets. Additionally, \ab\_test\_workflows.py\ and \analyze\_workflow\_metrics.py\ provide statistical analysis and A/B testing capabilities for workflow variants, while \cleanup.sh\ and \uninstall\_legacy.sh\ help manage build artifacts and remove old SuperClaude configurations.

scripts · high confidence

SuperClaude Framework version 4.3.0 release with expanded agent library

The SuperClaude package has been updated to version 4.3.0, introducing a comprehensive set of specialized AI agent definitions for the \src/superclaude/agents/\ directory. This release adds new personas including Backend Architect, DevOps Architect, Frontend Architect, Python Expert, Security Engineer, Quality Engineer, and Refactoring Expert, alongside enhanced capabilities for Deep Research, Business Strategy analysis, and Project Management (PM Agent). The package now exposes core components such as \ConfidenceChecker\, \ReflexionPattern\, and \SelfCheckProtocol\ in its public API.

src/superclaude · high confidence

SuperClaude plugin restored with version 4.3.0 and full agent/command suite

The SuperClaude plugin for Claude Code has been restored and updated to version 4.3.0. This change introduces the complete framework configuration, including 30 slash commands, 20 domain-specialist agents (such as Backend Architect, Security Engineer, and PM Agent), 7 auto-triggering skills, and lifecycle hooks. It also registers two new MCP servers, Context7 and Sequential Thinking, to support library documentation and multi-step problem solving.

plugins/superclaude · high confidence

Removals

Removal of legacy base installation framework

The \setup/base\ module, which previously provided the \Component\ abstract base class and the \Installer\ orchestrator for managing installable components, has been removed. This deletion eliminates the legacy architecture that handled component registration, dependency resolution, system requirement validation, and backup creation during installation.

setup/base · high confidence

Removal of legacy component-based installation system

The \setup/components\ directory has been removed, eliminating the previous modular installation architecture that managed Core, Commands, MCP, and Hooks components as distinct Python classes. This change removes the specific logic for installing framework files, slash commands, MCP servers, and placeholder hooks via the old component registry, indicating a shift to a different installation mechanism.

setup/components · high confidence

Removal of legacy setup module and version 3.0.0 metadata

The \setup/\_\init\\_.py\ file has been deleted, removing the legacy installation suite code that previously defined the project version as 3.0.0 and established core path constants for configuration and profiles. This change eliminates the standalone Python installation system in favor of the current project structure.

setup · high confidence

Removal of legacy setup operations module

The \setup/operations\ package, which previously housed the \install\, \update\, \uninstall\, and \backup\ CLI commands along with their shared \OperationBase\ class, has been completely removed. This change eliminates the legacy unified CLI hub structure for these management tasks, indicating that the installation and maintenance workflows have been restructured or moved to a different location in the codebase.

setup/operations · high confidence

Removal of legacy setup utility modules

The \setup/utils\ package has been removed, deleting the \\_\init\\_.py\, \logger.py\, \security.py\, and \ui.py\ files. This eliminates the previous installation-time components including the \Logger\ class (with colorized console and file output), the \SecurityValidator\ (for path and filename validation), and the \ui\ utilities (\ProgressBar\, \Menu\, \Colors\).

setup/utils · high confidence

Removal of setup/core module

The \setup/core\ package has been removed from the installation system. This change deletes the \ConfigManager\, \SettingsManager\, \FileManager\, \Validator\, and \ComponentRegistry\ classes, along with their associated configuration loading, validation, and file management logic.

setup/core · high confidence

Architecture

Repository restructuring to src/ layout and legacy setup removal

The project has migrated to a standard Python src/ layout, moving package code into src/superclaude/ and tests into tests/ to prevent accidental imports and align with PEP 517 best practices. The legacy setup/ directory and its associated installation logic have been removed, replacing the old file-copying installation method with a standard pip/uv editable install. This change also introduces a new .env.example file for environment variables, a .pre-commit-config.yaml for code quality and secret detection, and updates the Makefile to reflect the new build and test commands.

(repo-wide) · high confidence

Behavioural changes

SuperClaude V4 Beta: Major framework restructuring

This release introduces a major framework restructuring (V4 Beta) that replaces the previous command definitions with new Python-based execution engines and a new synchronization script. The \scripts/sync\_from\_framework.py\ script is added to automate pulling content from the SuperClaude\_Framework repository and transforming it for distribution as a Claude Code plugin with namespace isolation (sc: prefix). The \src/superclaude/execution/\ directory now contains new Python modules: \parallel.py\ for automatic parallelization of independent tasks, \reflection.py\ for a 3-stage pre-execution confidence check, and \self\_correction.py\ for learning from past failures. Concurrently, the old \SuperClaude/Commands/\ markdown files (e.g., analyze.md, build.md, task.md) and \SuperClaude/Core/\ configuration files (e.g., COMMANDS.md, FLAGS.md) are removed, indicating a shift from static markdown-based command definitions to a more dynamic, code-driven execution model.

SuperClaude · high confidence

Test coverage

Initial test suite for SuperClaude Framework

Added a comprehensive test suite for the SuperClaude Framework, including unit tests for core components (CLI install, confidence checking, parallel execution, reflection, reflexion, self-check, and self-correction) and integration tests for the execution engine and pytest plugin. The suite also includes shared fixtures in conftest.py and verifies specific behaviors such as handling zero elapsed time in parallel execution and correct API key environment variable names for the magic MCP server.

tests · high confidence

Dependencies

Initial release of SuperClaude v4.3.0 with dual PyPI and NPM packaging

This change introduces the official build manifests for SuperClaude v4.3.0, enabling distribution via both PyPI (Python) and NPM (Node.js). The Python package (\pyproject.toml\) defines the core framework as a pytest plugin with CLI capabilities, requiring Python 3.10+ and dependencies like pytest, click, and rich. The NPM wrapper (\package.json\) provides a Node.js interface for the same framework, targeting Node 16+ and including post-install scripts for setup. This establishes the foundational packaging structure for the dual-platform release.

(dependencies) · high confidence

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 54.7 → 58.4 (+3.7)
  • Rubric changed (rubric-2026.11.2 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 51.3 → 61.3 (+10.0)
  • Architecture 96.5 → 95.7 (-0.8)
  • Maturity 67.8 → 66.1 (-1.7)
  • Readiness 46.7 → 49.6 (+2.9)
  • Security 63.4 → 63.4 (0.0)
  • Performance 85.7 → 85.7 (0.0)

Resolved (9)

  • Duplicated block (27 lines × 2) (plugins/superclaude/scripts/clean_command_names.py)
  • Duplicated block (5 lines × 2) (scripts/ab_test_workflows.py)
  • FileSyncer.sync_directory (cognitive 27) (scripts/sync_from_framework.py)
  • FileTooLong: scripts/sync_from_framework.py (scripts/sync_from_framework.py)
  • Further orphaned files (smaller)
  • Off-boarding risk: anonymized user #1
  • Orphaned knowledge (scripts/sync_from_framework.py)
  • Scanner failed to run — not a clean result
  • Scanner failed to run — not a clean result

New (14)

  • Concentrated knowledge decay
  • Edited copies of one member (3 members, 16+ corresponding lines) (src/superclaude/execution/init.py)
  • Edited copy of a member (68 corresponding lines) (src/superclaude/cli/install_commands.py)
  • Edited copy of a member (9 corresponding lines) (scripts/ab_test_workflows.py)
  • Low coverage: setup.py (setup.py)
  • Low coverage: src/superclaude/version.py (src/superclaude/version.py)
  • Low coverage: src/superclaude/cli/doctor.py (src/superclaude/cli/doctor.py)
  • Low coverage: src/superclaude/cli/install_commands.py (src/superclaude/cli/install_commands.py)
  • Low coverage: src/superclaude/cli/install_mcp.py (src/superclaude/cli/install_mcp.py)
  • Low coverage: src/superclaude/cli/install_skill.py (src/superclaude/cli/install_skill.py)
  • Low coverage: src/superclaude/cli/main.py (src/superclaude/cli/main.py)
  • Most significant orphaned file (scripts/sync_from_framework.py)
  • Most significant orphaned file (src/superclaude/cli/install_mcp.py)
  • Orphaned file (src/superclaude/execution/parallel.py)

Architecture

  • Unchanged — 0 containers · 1 contexts · 0 edges

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

SuperClaude-Org/SuperClaude_Framework was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 16 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit fe68862c8ed9e2afb8120c2d9e27d0c3a7ce73a2 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.83+preprod-a489942cf94b.