# pi-cmp

> pi-cmp — songpham-pi-cmp. Use this tool when you need to quickly analyze and understand the structure of a codebase, as it provides fast querying capabilities for symbol search, call chains, and architecture, among others, by leveraging a local tree-sitter knowledge graph. It solves problems related to slow codebase navigation and analysis, offering a more efficient alternative to grep and read fallbacks. Ideal for use cases where rapid code comprehension and exploration are crucial, such as during debugging, refactoring, or onboarding to new projects.

Canonical page: https://skillsregistry.net/skills/songpham-pi-cmp  
JSON: https://api.skillsregistry.net/v1/skills/songpham-pi-cmp

## Description

Codebase Memory for pi. Provides cbm_* tools that answer structural questions about a codebase (symbol search, call chains, architecture, git change blast radius, and more) by querying a local tree-sitter knowledge graph, avoiding slow grep/read fallbacks.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/n1u2k8i1te)
- **Repository:** <https://github.com/songpham/pi-cmp>

## 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": "songpham-pi-cmp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/songpham-pi-cmp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/songpham-pi-cmp/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