# Clonst

> Clonst — capritora-clonst. Use this tool when you need to ensure reliable and accurate code reviews by leveraging the combined expertise of two AI models. Clonst solves the problem of inconsistent or biased code evaluations by facilitating adversarial reviews between Claude Code and OpenAI Codex, producing a consensus-driven output. It takes in code inputs and returns a verified and validated code review output, ideal for use in high-stakes development environments where precision is crucial.

Canonical page: https://skillsregistry.net/skills/capritora-clonst  
JSON: https://api.skillsregistry.net/v1/skills/capritora-clonst

## Description

Enables adversarial code review by connecting Claude Code to OpenAI Codex, iterating until consensus is reached between the two AI models.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/en2zztkci2)
- **Repository:** <https://github.com/capritora/clonst>

## 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": "capritora-clonst"
    }
  }
}
```

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