# ctxfw

> ctxfw — heuristicolab-ctxfw. Use this tool when you need to optimize context processing for AI coding agents, reducing unnecessary data and improving performance. The ctxfw tool eliminates context bloat by pruning topological dependencies, resulting in faster processing times. It takes in AST data and outputs a streamlined context, ideal for use cases involving large codebases and git integrations.

Canonical page: https://skillsregistry.net/skills/heuristicolab-ctxfw  
JSON: https://api.skillsregistry.net/v1/skills/heuristicolab-ctxfw

## Description

High-assurance in-memory Tree-Sitter AST context firewall and pruning MCP server for coding agents (-72.4% token mass).

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/heuristicolab/ctxfw)

## 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": "heuristicolab-ctxfw"
    }
  }
}
```

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