# PearClaw

> Use this tool when you need to monitor and control Claude Code executions in real-time, solving issues of unauthorized or malicious actions. PearClaw connects to an OpenClaw agent, taking in code actions as input and outputting approved, blocked, or modified actions. It is ideal for use cases requiring enhanced security and oversight, such as sensitive data processing or high-stakes automation.

Canonical page: https://skillsregistry.net/skills/sideeyelabs-pearclaw  
JSON: https://api.skillsregistry.net/v1/skills/sideeyelabs-pearclaw

## Description

Provides real-time oversight for Claude Code by connecting it to an OpenClaw agent that reviews, approves, blocks, or modifies actions before they execute.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zn6sf4ig81)
- **Repository:** <https://github.com/sideEyeLabs/pearclaw>

## 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": "sideeyelabs-pearclaw"
    }
  }
}
```

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