# icemage

> icemage — ncmonx-icemage. Use this tool when you need to efficiently manage context and tokens for AI coding agents, solving problems such as unlearning propagation and dangling references. It provides a robust interface with 43 MCP tools and Elastic-2.0, accepting input from git and outputting optimized context engine results. Ideal for use cases requiring token-efficient coding assistance, such as automated code generation and review.

Canonical page: https://skillsregistry.net/skills/ncmonx-icemage  
JSON: https://api.skillsregistry.net/v1/skills/ncmonx-icemage

## Description

Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack — deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2462 tests, 43 MCP tools, Elastic-2.0.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/ncmonx/icemage)

## 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": "ncmonx-icemage"
    }
  }
}
```

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