# ContextCrumb

> Use this tool when you need to optimize context for LLM agents, reducing token usage while preserving essential information. ContextCrumb compresses long texts, files, and catalog descriptions into denser context, enabling agents to load more useful data into their context window. It is ideal for use cases where detailed information must be conveyed efficiently, without resorting to summaries.

Canonical page: https://skillsregistry.net/skills/yuchen20-context-crumb  
JSON: https://api.skillsregistry.net/v1/skills/yuchen20-context-crumb

## Description

ContextCrumb compresses long text, local files, and MCP catalog descriptions into denser context for LLM agents. It helps agents load more useful information into the context window and reduce token usage without turning the input into a summary.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pk8efnrykf)
- **Repository:** <https://github.com/Yuchen20/Context-Crumb>

## 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": "yuchen20-context-crumb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yuchen20-context-crumb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yuchen20-context-crumb/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