Hello2cc

hello2cc

Make third-party models inside Claude Code behave closer to a native Opus session.

hello2cc does not replace your gateway, provider mapping, or account setup.
It sits in the plugin layer and keeps third-party models closer to Claude Code's native behavior around tool choice, agent routing, task and team workflow, failure handling, and response style.

Language: English | 简体中文

Overview

hello2cc is for users who already run GPT, Kimi, DeepSeek, Gemini, Qwen, or other third-party models in Claude Code through CCSwitch or a similar mapping layer.

It helps in three places:

- keep capability selection closer to Claude Code's native priorities
- reduce routing mistakes around plain agents, teams, tasks, and follow-up workflow
- tighten response behavior so replies stay more direct, restrained, and execution-first

Best for

- Claude Code sessions already connected to third-party models
- repositories that expose skills, workflows, MCP resources, or plugins
- users who want fewer detours and less prompt-shape sensitivity

Not for

- setting up API keys, providers, or model gateways
- exposing tools that Claude Code itself did not surface
- replacing CCSwitch or another provider-mapping layer
- overriding repository rules such as AGENTS.md, CLAUDE.md, or direct user instructions

What's new in 0.5.11

Compared with the previous public release (v0.5.9), 0.5.11 adds two practical fixes and one behavior tightening pass:

Features

- Native-first routing guidance: keeps the model closer to Claude Code's surfaced capability order instead of falling back to broad keyword-driven choices.
- Agent and team guardrails: distinguishes plain workers from real teammate flows, reduces accidental team_name pollution, and preserves task-board continuity only when the host proves…