# pgr

> pgr — entireio-pgr. Use this tool when you need to optimize code search with ranking, latency, and output shaping for efficient agentic search, particularly in git-based projects. It solves problems related to code retrieval and ranking, providing a stateless server for experimental purposes. The pgr tool accepts code-related inputs and outputs optimized search results, ideal for use cases requiring fast and relevant code search functionality.

Canonical page: https://skillsregistry.net/skills/entireio-pgr  
JSON: https://api.skillsregistry.net/v1/skills/entireio-pgr

## Description

PGR is an experimental, stateless MCP code-search server for studying how ranking, latency, and output shaping affect agentic search.

## Trust

- **Trust score (0–1):** 0.74
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/entireio/pgr)

## 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": "entireio-pgr"
    }
  }
}
```

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