# astral

> astral — sourikduttanyu-astral. Use this tool when you need to manage complex codebases and prevent data loss, as it warns before autocompact, checkpoints done work, and delegates large reads to subagents, optimizing workflow and minimizing disruptions. It is particularly useful for projects using Claude Code and git, where efficient context-budget management is crucial. By leveraging astral, developers can ensure seamless project execution and reduce the risk of errors.

Canonical page: https://skillsregistry.net/skills/sourikduttanyu-astral  
JSON: https://api.skillsregistry.net/v1/skills/sourikduttanyu-astral

## Description

Context-budget manager for Claude Code — warns before autocompact, checkpoints done work, delegates large reads to subagents.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/sourikduttanyu/astral)

## 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": "sourikduttanyu-astral"
    }
  }
}
```

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