# t-saur

> t-saur — iulianbondari-t-saur. Use this tool when you need to efficiently store and retrieve data in a deterministic and content-addressed manner, solving problems of data integrity and version control for AI agents. The t-saur archive format provides per-file reads, grep functionality, and an MCP server, with verified byte-for-byte accuracy. It is ideal for use cases requiring reliable data storage and retrieval, such as AI model training and deployment, with inputs including files and directories, and outputs including verified archives and searched results.

Canonical page: https://skillsregistry.net/skills/iulianbondari-t-saur  
JSON: https://api.skillsregistry.net/v1/skills/iulianbondari-t-saur

## Description

Archive format built for AI agents: deterministic, content-addressed .tsr archives with per-file reads, grep and an MCP server, verified byte for byte. Rust, format v1 frozen.

## Trust

- **Trust score (0–1):** 0.49
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/iulianbondari/t-saur)

## 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": "iulianbondari-t-saur"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/iulianbondari-t-saur` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/iulianbondari-t-saur/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