# code-reason

> code-reason — ph0smet-code-reason. Use this tool when you need to analyze code programmatically, as it provides coding agents with program-analysis primitives such as data flow, call graphs, and taint analysis to reason about code from ground truth. It solves problems of inaccurate code analysis and guesswork by providing a reliable MCP server interface that takes in code repositories, such as git, and outputs actionable insights. This enables agents to make informed decisions and automate coding tasks with precision.

Canonical page: https://skillsregistry.net/skills/ph0smet-code-reason  
JSON: https://api.skillsregistry.net/v1/skills/ph0smet-code-reason

## Description

MCP server that gives AI agents program-analysis primitives like data flow, call graphs, taint analysis so they reason from deterministic data instead of grep-and-guess."

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-25

## Source

- **Source listing:** [GitHub](https://github.com/ph0smet/code-reason)

## 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": "ph0smet-code-reason"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ph0smet-code-reason` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ph0smet-code-reason/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