A structural analysis tool that identifies duplicated, inconsistent, and dead code patterns to guide intelligent refactoring.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pattern-mine
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pattern-mine using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Pattern Mine?
Pattern Mine is a sophisticated codebase analysis engine that goes beyond basic linting to discover the underlying architectural logic of your project. It identifies four distinct types of patterns: convergent logic that should be unified, divergent implementations that cause bugs, emerging abstractions that are ready for extraction, and fossilized code that serves no modern purpose. By treating patterns as repeated decisions, it helps developers transition from a codebase that simply grew to one that is intentionally cultivated.
As part of the broader ecosystem of Openclaw Skills, this tool operates entirely locally with zero external dependencies. It analyzes your code's structure and semantics without making any API calls, ensuring your proprietary logic stays private while providing actionable insights into your project's health and evolution.
Pattern Mine Use Cases
- Identifying high-impact refactoring targets before major architectural shifts.
- Streamlining onboarding by showing new developers the actual conventions used in the codebase.
- Detecting security vulnerabilities caused by inconsistent implementations of critical logic like sanitization.
- Removing unreachable or redundant code patterns inherited from legacy systems.
- Prioritizing technical debt cleanup during sprint planning based on frequency of duplication.
How Pattern Mine Works
- Extraction: The skill parses source files into structural representations, identifying functional blocks and their operational signatures.
- Similarity Mapping: It builds a similarity matrix to compare blocks based on behavior, input/output, and side effects rather than just text.
- Clustering: Blocks are grouped into categories like convergent or divergent based on their semantic consistency and age.
- Trend Analysis: The engine evaluates the Rule of Three for emerging patterns and checks commit history for fossilized ones.
- Reporting: It generates a prioritized Mine Report that highlights the highest ROI cleanup tasks and potential bug risks.
Pattern Mine Setup
Pattern Mine is a zero-dependency tool compatible with macOS, Linux, and Windows. To add it to your Openclaw Skills workflow, use the following commands:
# Install the pattern-mine skill
openclaw install pattern-mine
# Run the mining operation on your source directory
openclaw run pattern-mine ./src
Pattern Mine Data Schema & Taxonomy
Pattern Mine classifies findings using a specific taxonomy and organizes metadata to assist in refactoring decisions:
| Data Point | Description |
|---|---|
| Pattern Type | Categorization into Convergent, Divergent, Emerging, or Fossilized clusters. |
| Instance Count | The number of unique locations where the pattern was detected. |
| Extraction ROI | A calculated metric based on lines saved multiplied by the frequency of change. |
| Canonical Form | The most common or robust version of a detected pattern suggested as the standard. |
| Location Mapping | Precise file paths and line ranges for every detected occurrence. |
Pattern Mine Advanced Features
- Semantic Detection: Recognizes identical logic even when written with different syntax or variable names.
- Fossilization History: Analyzes commit data to prove when a defensive pattern has become obsolete.
- Divergence Alerts: Flags implementations that deviate from established internal standards, preventing special-case bugs.
- Growth Tracking: Monitors emerging patterns across scan sessions to suggest the optimal time for abstraction.
- Privacy-First Analysis: Operates with zero API requirements, keeping all code analysis strictly on the local machine.
SKILL.md
Loading
Related Openclaw Skills
Parallax
Parallax is a multi-perspective reasoning framework that evaluates technical decisions through five distinct stakeholder lenses to eliminate blind spots.
Osmotic Pressure
A sophisticated diagnostic tool that identifies and maps complexity imbalances across software boundaries to prevent architectural collapse.
ResonanceEngine
ResonanceEngine is a zero-cost algorithmic tool that analyzes conversational micro-signals to optimize AI bot responses for maximum engagement and conversion.
Smart Memory
A local, zero-cost persistent memory system that enables AI agents to remember user preferences and project context without external APIs.
Peripheral Vision
A situational awareness skill that monitors upstream dependencies and downstream consumers for changes that could break your current work.
Phantom Limb
Phantom Limb is a cognitive diagnostic tool that detects ghost references and silent dependencies that no longer exist in your live environment.
Featured*
