Slm Gate — Development skill for Claude Code
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs.
How to install Slm Gate
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zenithfoundry/slm-gate and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Slm Gate does
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly quota.
Alternatives in Development
README
small-language-model-gate
[](https://github.com/bronz3beard/small-language-model-gate/actions/workflows/ci.yml) [](LICENSE) [](https://modelcontextprotocol.io/) [](package.json) [](tsconfig.json) [](https://github.com/bronz3beard/small-language-model-gate/pulls)
[!NOTE] **Related project — Tech-Lead-Stack:** An agent-agnostic library of Markdown "skills" plus an MCP server that turns Claude, Gemini, or GPT into a full software-delivery team (planning, building, review, security, release), organized around a nine-phase lifecycle. Its self-correcting Reflexion loop grades implementation plans against four engineering pillars before any code is written.
Table of Contents
- What is slm-gate?
- Prerequisites & Hardware Sizing
- How It Operates: Choosing Your Integration Layer
- Step-by-Step Setup Walkthrough
- Configuration Setup Guide
- Verification & Day-to-Day Use
- Architecture & Advanced Features
1. What is slm-gate?
`small-language-model-gate` (CLI shortname: **`slm-gate`**) is a **local AI pre-processing and routing layer** that sits in front of your AI coding assistant and quietly does
Related Skills
Notebook Intelligence
A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills,
FinOps
Cut a cloud bill via guided intake - provider, current architecture, monthly spend, suspected waste.
Subscriptions
List all detected subscriptions with monthly and annual costs
Agent Usage Bar
macOS menu bar app showing how much Codex and Claude quota is left, what you spent locally, and when the windo
Quota Bar
macOS menu bar app showing how much Codex and Claude quota is left, what you spent locally, and when the windo
Claude Code Optimizer
Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs
Related Agents
Cost Estimator
Estimates Cloudflare Workers costs before deploying. Reads wrangler.toml, counts D1 tables/rows, estimates KV/
LLM Integrator
LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements
Prompt Engineer Agent
Specialist in crafting, testing, and systematically optimizing prompts for LLMs — turning vague instructions i