by zachahn
Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless
# Add to your Claude Code skills
git clone https://github.com/zachahn/vomitLast scanned: 8/21/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-21T04:39:33.730Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how vomit compares with popular alternatives.
vomit is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by zachahn. Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless. It has 193 GitHub stars.
Yes. vomit passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/zachahn/vomit" and add it to your Claude Code skills directory (see the Installation section above).
vomit is primarily written in Go. It is open-source under zachahn on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh vomit against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Vomit converts Claude's token vomit into English by piping it through a local LLM. It's fully local (no telemetry) and has no external dependencies.
Vomit hooks into Claude Code, rewriting all its output within the Claude Code terminal UI.
Disclaimer:
# Install the binary to your GOPATH
go install github.com/zachahn/vomit@latest
# Setup connection details to your LLM
vomit init
# Instructions on how to replace Claude's output via hooks
vomit scrub -claude
In addition, there's a non-invasive mode if you want to run Vomit on the side. (This is deprecated.)
vomit list. List Claude session identifiersvomit tail [<session_identifier>]. Translate Claude's tokens for the specified session, or follow the latest onevomit help. See for more commandsThis should work with:
If you don't have a local LLM set up already, I think I recommend using Llama.app, and downloading GPT-OSS 20B through it. Run the init subcommand after you set this up.
ctrl-o within Claude Code to get Claude's original output.GNU GPLv3