# deposition

> deposition — georgedagher-deposition. Use this tool when you need to track and manage local decision logs for AI agent sessions without relying on API calls. It solves problems related to decision transparency and reproducibility by providing a deterministic decision extraction process. The deposition tool takes local AI agent session data as input and outputs a reliable log of decisions made during the session.

Canonical page: https://skillsregistry.net/skills/georgedagher-deposition  
JSON: https://api.skillsregistry.net/v1/skills/georgedagher-deposition

## Description

Local-only decision log for AI agent sessions -- zero API calls, deterministic decision extraction.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **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/georgedagher/deposition)

## 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": "georgedagher-deposition"
    }
  }
}
```

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