Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Delegate Claude Code investigation, implementation, and review tasks to Qwen models with a structured session lifecycle and mandatory review gate on completion.
npx claudepluginhub josephyaduvanshi/qwen-companion --plugin qwenRun a Qwen review that challenges the implementation approach and design choices
Cancel an active Qwen job in this repository
Delegate investigation, an explicit fix request, or follow-up rescue work to the Qwen rescue subagent
Show the stored final output for a finished Qwen job in this repository
Run a Qwen code review against local git state using the built-in /review reviewer
Internal helper contract for calling the qwen-companion runtime from Claude Code
Internal guidance for composing Qwen Code / Qwen 3.x prompts for coding, review, diagnosis, and research tasks inside the Qwen Claude Code plugin
Internal guidance for presenting Qwen helper output back to the user
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Delegate coding tasks to Qwen Code CLI (Qwen3-Coder) via ACP. Part of cc-multi-cli-plugin. Requires the `multi` plugin.
Cross-agent review workflow: Claude implements, Codex reviews
Use Codex from Claude Code to review code or delegate tasks.
Use Copilot from Claude Code to review code or delegate tasks.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Use Gemini CLI from Claude Code to delegate investigation, implementation, and review tasks.
No model invocation
No model invocation
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Share bugs, ideas, or general feedback.
Delegate rescues and code reviews to Qwen Code from inside Claude Code.
One CLI talking to another. No broker, no protocol dance, no magic.
If this saves you an afternoon, star the repo ⭐
/qwen:setup
/qwen:rescue investigate why the auth middleware drops cookies on logout
/qwen:review
That's the whole thing. You type a slash command, Claude hands the work over to Qwen Code, and you get Qwen's answer back without Claude paraphrasing it.
/qwen:review — a read-only code review powered by qwen's native /review slash command/qwen:adversarial-review — a steerable review with structured JSON findings/qwen:rescue — hand any task off to Qwen through a thin subagent/qwen:status, /qwen:result, /qwen:cancel — manage background jobs without leaving Claude/qwen:setup — health check the runtime and toggle the optional stop-time review gateEverything is Qwen doing the work. This plugin just makes sure the output comes back to you clean, the state is persisted, and cancellation actually cancels.
I wanted codex-plugin-cc's workflow but pointed at Qwen Code.
There's already a qwen plugin floating around built on qwen's --acp (Agent Client Protocol) mode. I tried it, it didn't work for me, so I went looking for a different path.
Qwen's --output-format stream-json turned out to be almost the same shape as the stream-json protocol Claude Code uses internally: a system/init, then stream_event/content_block_delta deltas, then a final result envelope. That made the port easy. It's also way easier to debug than ACP: every event is a newline of JSON, so I can tail -f and pipe through jq while things are misbehaving.
The tradeoff is that every task spawns a fresh qwen process instead of reusing a persistent one. Cold start is 0.5 to 2 seconds. That's invisible for rescue and review workflows and I am not going to over-engineer a broker to save a second per call.