code-cli-any-llm CLAUDE.md

code-cli-any-llm CLAUDE.md is an instructions file for coding agents from x22x22/code-cli-any-llm. It costs 2,941 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for code-cli-any-llm, a NestJS and TypeScript gateway that lets Gemini CLI use other language-model providers through the Gemini API format. NestJS is a framework for building Node.js services, and SSE is a way to stream server updates over a connection.

In plain words
What is it for?
Use it when developing or maintaining the gateway, including provider integrations, request and response conversion, streaming, tool calls, error handling, health checks, and monitoring.
Why use it?
It gives an agent the project background, design rules, current implementation status, and setup or development commands. This reduces the risk of making changes that conflict with the gateway's architecture.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/x22x22/code-cli-any-llm/claude-md
Clone the repo
git clone --depth 1 https://github.com/x22x22/code-cli-any-llm

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-cli-any-llm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/x22x22/code-cli-any-llm/claude-md.svg)](https://agentmods.dev/instructions/x22x22/code-cli-any-llm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/x22x22/code-cli-any-llm/claude-md"><img src="https://agentmods.dev/badge/instructions/x22x22/code-cli-any-llm/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,941 This file is loaded in full into every session.
When invoked 2,941 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02941 $0.02941
Opus 5 $0.01470 $0.01470
Sonnet 5 $0.00588 $0.00588
Haiku 4.5 $0.00294 $0.00294

Measured 3d ago against content hash f23d1df0794f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-cli-any-llm CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a NestJS TypeScript project called "code-cli-any-llm" - a Gemini API Gateway that enables Gemini CLI to access non-Gemini LLM providers. The project implements a translation gateway service that allows seamless, non-intrusive connectivity to various LLM providers (OpenAI, Anthropic, Qwen, etc.) through Gemini API compatibility.

Key Design Principles:

  • 100% Gemini API compatibility - no modifications needed to Gemini CLI
  • Provider abstraction layer for easy extension
  • High-performance streaming support with Server-Sent Events (SSE)
  • Production-ready with monitoring, error handling, and graceful shutdown

Current Implementation Status

Phase 3: Core Implementation - Completed ✅

  • ✅ Full NestJS architecture with modular design
  • ✅ OpenAI provider implementation with retry logic
  • ✅ Request/response transformers for Gemini ↔ OpenAI format
  • ✅ Streaming support with proper SSE formatting
  • ✅ Tool calling support (7+ format conversions)
  • ✅ Comprehensive error handling and validation
  • ✅ Health check and monitoring endpoints
  • ✅ YAML-based configuration system
  • ✅ Global configuration management with home directory support
  • ✅ Graceful shutdown handling

API Endpoints:

  • GET /api/v1/health - Health check
  • POST /api/v1/models/{model}:generateContent - Standard content generation
  • POST /api/v1/models/{model}:streamGenerateContent - Streaming content generation

Common Development Commands

Installation and Setup

pnpm install  # Install dependencies

# First run - global config will be auto-created
pnpm run start:dev
# This will create ~/.code-cli-any-llm/config.yaml and show you what to configure

# Edit the global config with your API key
# ~/.code-cli-any-llm/config.yaml - set your apiKey

# Optional: Create project-specific overrides
cp config/config.example.yaml config/config.yaml  # Copy configuration
# Edit config/config.yaml with any project-specific settings

Read the full file on GitHub · 345 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 345 lines · 2,941 tokens per session scan A f23d1df0794f

Subscribe to this mod's changes

code-cli-any-llm CLAUDE.md is an instructions file published in the GitHub repository x22x22/code-cli-any-llm (5 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 2,941 tokens to every session, about $0.0147 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens