# Dual-Cycle Reasoner

> Use this tool when you need to detect and recover from repetitive behaviors in autonomous agents, such as endless scrolling or clicking patterns. The Dual-Cycle Reasoner implements a metacognitive reasoning framework that combines statistical anomaly detection, semantic analysis, and case-based reasoning to identify and diagnose failure causes, generating recovery strategies. It is ideal for developers, teams, and researchers building autonomous web agents, browser automation tasks, or self-monitoring AI systems that require robust loop prevention and adaptive learning capabilities.

Canonical page: https://skillsregistry.net/skills/cyqlelabs-dual-cycle-reasoner  
JSON: https://api.skillsregistry.net/v1/skills/cyqlelabs-dual-cycle-reasoner

## Description

This MCP server implements a dual-cycle metacognitive reasoning framework for autonomous agents, built by CyqleLabs using TypeScript with advanced loop detection and recovery mechanisms. The implementation combines statistical anomaly detection, semantic analysis using Hugging Face transformers, and case-based reasoning to identify when agents get stuck in repetitive behaviors like endless scrolling or clicking patterns, then automatically diagnoses failure causes and generates recovery strategies. Built with three core detection strategies (action pattern analysis, state invariance tracking, and progress stagnation detection), belief revision capabilities, and a case-based learning system that adapts from past experiences, it serves developers building autonomous web agents, teams needing robust loop prevention for browser automation tasks, and researchers working on self-monitoring AI systems that can break out of unproductive behavioral cycles.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cyqlelabs-dual-cycle-reasoner)
- **Repository:** <https://github.com/cyqlelabs/mcp-dual-cycle-reasoner>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cyqlelabs-dual-cycle-reasoner"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cyqlelabs-dual-cycle-reasoner` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cyqlelabs-dual-cycle-reasoner/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt