# jev-compactor

> jev-compactor — edwardyen724-g-jev-compactor. Use this tool when you need to compact and safeguard AI agent contexts without summarizing messages, to ensure accurate and reliable interactions. It solves problems related to context management and safety gating for AI agents, supporting various interfaces including OpenAI, Anthropic, and CLI. The jev-compactor takes in AI agent contexts and outputs compacted, verbatim messages, ideal for use cases requiring precise information preservation.

Canonical page: https://skillsregistry.net/skills/edwardyen724-g-jev-compactor  
JSON: https://api.skillsregistry.net/v1/skills/edwardyen724-g-jev-compactor

## Description

Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.

## 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:** 2026-09-19

## Source

- **Source listing:** [GitHub](https://github.com/edwardyen724-g/jev-compactor)

## 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": "edwardyen724-g-jev-compactor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/edwardyen724-g-jev-compactor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/edwardyen724-g-jev-compactor/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