# context-management

> Use this tool when you need to optimize AI agent performance by managing context window consumption and preventing compaction death spirals. It solves problems related to inefficient resource allocation and sub-agent spawn policy enforcement, taking in agent performance metrics and outputting optimized context management strategies. Ideal for use in complex AI systems where resource constraints and scalability are critical concerns.

Canonical page: https://skillsregistry.net/skills/marcus-daemon-context-management  
JSON: https://api.skillsregistry.net/v1/skills/marcus-daemon-context-management

## Description

Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-04-22

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/marcus-daemon-context-management)

## 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": "marcus-daemon-context-management"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/marcus-daemon-context-management` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/marcus-daemon-context-management/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