No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by zachahn · Agent Tool · ★ 193
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vomit safe to install? View the security audit →
Vomit 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. I wrote a small blog post about this project: Disclaimer: The local LLM can only see what Claude tries to communicate (no access to any actions or files), so it hallucinates a bit It's pretty slow This is totally vibe-coded, only tested on Mac There is a possibility you'll completely miss Claude's message. You can use something like [AgentsView] to get the original messages, as Vomit does not touch anything during runtime (except technically it writes files to your TMPDIR) Install Usage In addition, there's a non-invasive mode if you want to run Vomit on the side. . List Claude session identifiers . Translate Claude's tokens for the specified session, or follow the latest one . See for more commands This should work with: [Llama.app] [Ollama] Anything that uses the OpenAI API? If you don't have a local LLM set up already, I think I recommend using [Llama.app], then downloading GPT-OSS 20B through it. Run the subcommand after you s
| Stars | 193 |
| Forks | 7 |
| Language | Go |
| Category | Agent Tool |
| License | GPL-3.0 |
| Quality Score | 63.3812246939958/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-09 |
| Created | 2026-08-15 |
| Platforms | claude-code, go |
| Est. Tokens | ~10k |
These tools work well together with vomit for enhanced workflows:
Looking for a vomit alternative? If you're comparing vomit with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
📜 An MCP server for conversation history search and retrieval in Claude Code
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturall
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
Create agentic AI workflows in ROBLOX Studio
Explore other popular agent tool tools:
vomit is Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless. It is categorized as a Agent Tool with 193 GitHub stars.
vomit is primarily written in Go. It covers topics such as ai, ai-tools, claude-code.
You can find installation instructions and usage details in the vomit GitHub repository at github.com/zachahn/vomit. The project has 193 stars and 7 forks, indicating an active community.
vomit is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to vomit on Agent Skills Hub include UnrealClaude, kindly-web-search-mcp-server, claude-historian-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: