New Provider — AI skill for Claude Code
Wire a new AI CLI provider into the runner harness.
How to install New Provider
Installs to ~/.claude/commands/tkv00-career-atelier-ai-context-pack-new-provider.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/tkv00/Career-Atelier-AI-Context-Pack/HEAD/.claude/commands/new-provider.md -o ~/.claude/commands/tkv00-career-atelier-ai-context-pack-new-provider.md Restart Claude Code, or start a new session, for it to be picked up.
What New Provider does
description: Wire a new AI CLI provider into the runner harness
Add a CLI provider: $ARGUMENTS
Read `docs/HARNESS-ENGINEERING.md` sections 5 through 7 first. That section is a list of things that cost real debugging time; assume the new CLI has its own.
The four edits
- Harness —
runner/providers/.mjsexportingspawnandextractOutput. - Login check —
runner/safety.mjs: add the slug to the allowlist and add aproviderStatusbranch that det
Alternatives in AI
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
- LongHorizon Harness — The long-horizon computer-use harness 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Aigateway
Protocol-faithful, multi-provider AI gateway for OpenAI, Anthropic, Gemini, and OpenAI-compatible APIs — nativ
Skillxp
Skill invocation runner: install an Agent Skill in a fresh fixture, invoke an agent harness headlessly, and re
Agent Harness Orchestrator
Agent Orchestrator 2026: AI-Powered Multi-Repo Task Runner & Automation Hub
Lithium
Mood stabilizer for your AI bill. Cross-provider LLM-spend aggregator (Anthropic / OpenAI / OpenRouter). Local
Dsh CLI Switch
LLM-provider plugin for DeepSeek Harness: use local AI CLIs (claude / opencode / gemini / cursor / codex) as m
Dsh Oh My Claude
Claude Code CLI as an LLM provider for dsh (DeepSeek Harness): live model list, per-session resume, approval r
Related Agents
Langertha LLM Advisor
LLM provider & market specialist for Langertha. Validates and red-teams plans, designs and ADR proposals again
Sf Lwc Engineer
Implements Lightning Web Components, Aura bundles, static resources, and their Jest specs. Use for wave-1 UI w
Judge Runner
melta shadow judge の 1 trial を実行する。design/judge/run.ts --provider file --phase prepare が書いた tasks/ .task.md を渡