# readproof

> readproof — fbzz-readproof. Use this tool when you need to ensure data integrity and reproducibility for AI agents, solving problems of unstable data identities and inconsistent reads. Readproof provides a lockfile and replay primitive with features like content-addressed snapshots and byte-exact replay, accepting input data and outputting evidence bundles. It is particularly useful in contexts where data freshness and consistency are crucial, such as in machine learning model training and validation.

Canonical page: https://skillsregistry.net/skills/fbzz-readproof  
JSON: https://api.skillsregistry.net/v1/skills/fbzz-readproof

## Description

Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay, evidence bundles.

## Trust

- **Trust score (0–1):** 0.85
- **Verification tier:** verified
- **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/fbzz/readproof)

## 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": "fbzz-readproof"
    }
  }
}
```

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