# Elenchus

> Use this tool when you need to thoroughly verify code for security, correctness, and performance issues through collaborative multi-round review sessions. Elenchus solves problems of single-pass review limitations, providing state management, context sharing, and automated verification loops to identify potential issues in codebases. It takes in code inputs and outputs verified code with confidence scores, ideal for use in contexts where multiple AI agents collaborate to ensure code quality and reliability.

Canonical page: https://skillsregistry.net/skills/jhlee0409-elenchus  
JSON: https://api.skillsregistry.net/v1/skills/jhlee0409-elenchus

## Description

Elenchus is an adversarial verification system that orchestrates multi-round code review sessions between verifier and critic roles to systematically identify security, correctness, reliability, maintainability, and performance issues. It provides state management, context sharing, and automated verification loops through MCP tools, with advanced features like differential analysis for incremental verification, response caching to reduce token usage, function-level code chunking for large codebases, and quality safeguards including periodic full verification and confidence scoring. Designed for thorough code verification workflows where multiple AI agents collaborate to catch issues that single-pass reviews might miss.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/jhlee0409-elenchus)
- **Repository:** <https://github.com/jhlee0409/elenchus-mcp>

## 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": "jhlee0409-elenchus"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jhlee0409-elenchus` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jhlee0409-elenchus/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