By hellowind777
Run third-party models inside Claude Code with Opus-compatible workflows—using native tools, agent planning, and concise structured output—by intercepting tool calls and formatting responses.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
plan_modelPlan 的显式 Claude 槽位,仅填写 opus / sonnet / haiku。留空时默认保留 Claude Code 原生 inherit 行为;仅在你想强制覆盖时填写。
${user_config.plan_model}team_model带 team_name 的原生 Agent 显式 Claude 槽位,仅填写 opus / sonnet / haiku。留空时默认保留 Claude Code 原生 inherit 行为;仅在你想强制覆盖团队 teammate 时填写。
${user_config.team_model}guide_modelClaude Code Guide(内部标识 claude-code-guide)的显式 Claude 槽位,仅填写 opus / sonnet / haiku。留空时优先镜像当前会话模型对应的原生槽位。
${user_config.guide_model}explore_modelExplore 的显式 Claude 槽位,仅填写 opus / sonnet / haiku。留空时优先镜像当前会话模型对应的原生槽位,而不是插件再硬编码轻量模型。
${user_config.explore_model}general_modelGeneral-Purpose(内部标识 general-purpose)的显式 Claude 槽位,仅填写 opus / sonnet / haiku。留空时默认保留 Claude Code 原生 inherit 行为;仅在你想强制覆盖时填写。
${user_config.general_model}primary_model高能力原生 Agent 的显式 Claude 槽位,仅填写 opus / sonnet / haiku 之一。第三方模型请在 provider / gateway / ccswitch 层映射到这些原生槽位;这里不要直接填写 cc-gpt-5.4 一类别名。
${user_config.primary_model}routing_policy路由策略。可选:native-inject、prompt-only。推荐 native-inject;在原生 Agent 调用前静默补 model。
${user_config.routing_policy}subagent_model为未显式指定模型的原生 Agent / teammate 提供统一显式模型。留空时尽量保留 Claude Code 原生 inherit / 当前会话镜像行为。
${user_config.subagent_model}default_agent_model原生 Agent 的统一默认模型偏好。推荐填写 inherit / opus / sonnet / haiku;若兼容填写 opus(1M),hello2cc 会在 Agent.model 边界归一化为宿主安全的 opus。真正的 Opus→opus(1M) 落点应在 CCSwitch 的“Opus 默认模型”中配置。
${user_config.default_agent_model}mirror_session_model是否默认把当前 Claude Code 会话的主模型别名镜像到缺失 model 的原生 Agent / Team teammate。默认 true,更接近原生槽位体验。
${user_config.mirror_session_model}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
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:
AGENTS.md, CLAUDE.md, or direct user instructionsCompared with the previous public release (v0.5.9), 0.5.11 adds two practical fixes and one behavior tightening pass:
| Area | What changed |
|---|---|
| Task completion | TaskCompleted / TaskUpdate(status=completed) no longer gets hard-blocked just because the description is thin; the hook now warns without breaking completion-state sync |
| New Claude Code compatibility | The old Task subagent tool name is now treated as an alias of Agent, covering hooks, capability detection, session continuity, and real-session regression checks |
| Output discipline | Explanation and comparison prompts are less likely to trigger team/task-board demos, and the native style now pushes replies toward concise, direct, low-ceremony wording |
team_name pollution, and preserves task-board continuity only when the host proves it exists.Clone the repository.
git clone https://github.com/hellowind777/hello2cc.git
cd hello2cc
Add the local marketplace entry.
claude plugins marketplace add "<repo-path>"
Replace <repo-path> with your local hello2cc repository path.
Install and enable the plugin.
claude plugins install hello2cc@hello2cc-local
claude plugins enable hello2cc@hello2cc-local
Reload Claude Code.
/reload-plugins
Run:
claude plugins list
Expected result:
hello2cc@hello2cc-local is installedsettings.json to force agent=hello2cc:nativeGood when your model mapping is already handled elsewhere and you only want hello2cc to align behavior:
{
"mirror_session_model": true
}
Good when you want most spawned agents to use the same Claude slot:
{
"mirror_session_model": true,
"default_agent_model": "opus"
}
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Dogdoing (刀盾狗/我的刀盾) - A loyal shield-dog that participates in every task, splitting work as a subagent. Cheers with Wow-wow-wow when idle! | 一只永远不会缺席的工作犬,每个任务都插上一爪,没活就旺旺旺喝彩!
HelloLoop 的 Claude Code 原生插件元数据,用于多 CLI 宿主分发。
npx claudepluginhub hellowind777/hello2ccRun any model with an Anthropic- or OpenAI-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) — even your Codex subscription — as real Claude Code workflows, agent-team teammates, or one-shot subagents, driven exactly like native ones. Your main session's own auth is untouched (OAuth subscription or API key, either works); API-key providers bill the provider key via apiKeyHelper, while a Codex subscription bills through a local OAuth daemon — each worker receives its credential on demand, never through its env or argv. Requires the `cc-fleet` binary on PATH, installed separately.
Meta-tools for Claude Code configuration and customization
Your ChatGPT/Codex subscription models in Claude Code's /model picker. A local gateway routes claude-codex-* models to OpenAI's Codex backend (via claude-code-proxy) and everything else to api.anthropic.com, so you switch between Claude and GPT-5.x mid-session like any other model. No OpenAI API key.
Claude Code skill pack for Anthropic (30 skills)
Concentrated Claude. Zero fluff, max power per token.
Multi-LLM orchestration: delegate to Claude, Codex, and Gemini from a single interface with session management and async jobs.