# speedread

> speedread — brennengreen-speedread. Use this tool when you need to efficiently read and understand codebases, particularly when working with git repositories on macOS. It solves problems of slow or inefficient code review by providing budgeted, symbol-aware, and diff-aware reads. The speedread tool takes in code repositories as input and outputs a concise, token-efficient representation of the code, making it ideal for AI coding agents.

Canonical page: https://skillsregistry.net/skills/brennengreen-speedread  
JSON: https://api.skillsregistry.net/v1/skills/brennengreen-speedread

## Description

Token-efficient code reading for AI coding agents: budgeted, symbol-aware, diff-aware reads over MCP. Built for macOS.

## Trust

- **Trust score (0–1):** 0.45
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/brennengreen/speedread)

## 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": "brennengreen-speedread"
    }
  }
}
```

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