Lets you use the Kimi model from inside a Claude Code or Codex session to explain code, review changes, challenge a design, or pursue a goal. It gives an independent second opinion from a different model family.
Auto-invoked ships a router so the right skill fires automatically as you prompt. No remembering which skill to call.
Normal is the plain upstream plugin, installed as-is. You invoke its skills yourself.
Claude Code
The plugin> /plugin marketplace add linxule/kimi-plugin-cc> /plugin install kimi@kimi-marketplaceAuto-invocation> /plugin marketplace add flowy-sh/flowy-core> /plugin install flowy-core> /plugin install flowy-kimi
Codex
$ npx skills add linxule/kimi-plugin-cc -a codex
Cursor
$ npx skills add linxule/kimi-plugin-cc -a cursor
Gemini CLI
$ npx skills add linxule/kimi-plugin-cc -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add linxule/kimi-plugin-cc$ copilot plugin install kimi@kimi-marketplace
OpenCode
$ npx skills add linxule/kimi-plugin-cc -a opencode
Windsurf
$ npx skills add linxule/kimi-plugin-cc -a windsurf
Use Kimi to explain code, review changes, challenge a design, or work toward a goal — an independent second opinion from a different model family, inside the Claude Code, Codex, or DeepSeek Harness session you're already in.
I'm a Kimi Ambassador (academia). Kimi (Moonshot AI) supports this project through that role.
Latest release · npm package · Roadmap · Report an issue · Apache-2.0 license
Claude Code runs /kimi:review on this repository — Kimi reviews the diff, and the host verifies each claim against the tree.
Codex runs $kimi-ask — a read-only explanation of this project's entry point, from the entry shell script to the command modules.
Choose a language below. Each guide opens on this page.
选择语言，展开阅读 · Choisissez votre langue · 言語を選んで開いてください
English — Get started
Ask Kimi to explain code, review changes, challenge a design, or make a focused fix. You can use this plugin in Claude Code, Codex, or DeepSeek Harness (DSH).
The plugin runs the Kimi Code CLI on your computer. It uses your Kimi subscription or a provider you configure in Kimi. Calls count against that subscription or API account. Your host application's login stays unchanged. The selected provider receives the prompts and code needed for your task.
Start with a question or a review. Their tool rules allow reading files and deny file writes and shell commands. Other modes can change files. DSH provides the same seven operations with the same write boundaries. Read the safety limits before asking Kimi to make changes.
You need:
Windows is not currently supported. Contributors can help with the no-model Windows diagnostics checks. Check your versions in a terminal:
node --version
kimi --version
Use the Kimi Code installation guide if you need the CLI. You do not need Bun or a build step to use this plugin.
We test compatibility with exact CLI versions. A newer CLI may need a newer plugin. See supported versions and upgrades.
Run kimi in your terminal. Use /login for a Kimi subscription, or /provider to set up an API provider. Enter credentials in Kimi, never in the assistant conversation. Exit Kimi when you finish setup. If you set KIMI_CODE_HOME, use the same location for Kimi and the plugin.
Open Claude Code in your project. Enter these commands in Claude Code:
/plugin marketplace add linxule/kimi-plugin-cc
/plugin install kimi@kimi-marketplace
/kimi:setup
/kimi:setup --check
Setup installs a hook that checks Kimi's tool calls against the plugin's rules. The Probe: line should show ok. If it fails, follow the setup guidance below.
Try a question that does not change files:
/kimi:ask Explain how this project's main entry point works.
Run these commands in your terminal:
codex plugin marketplace add linxule/kimi-plugin-cc
codex plugin add kimi@kimi-marketplace
Open a new Codex task in your project. Ask it to set up the plugin:
Use $kimi-setup to install the safety hook, then check readiness.
The hook checks Kimi's tool calls against the plugin's rules. The Probe: line should show ok. If it fails, follow the setup guidance below. Then try:
Use $kimi-ask to explain how this project's main entry point works.
If you use multiple hosts, run setup in each. Each app has its own hook in the shared Kimi configuration.
DSH requires patched host and profile dependencies (zod >=4.6.6, undici >=8.12.2). Follow the host installation and audit instructions before installing this plugin.
The DSH bundle provides the same seven operations as the other hosts: kimi_ask, kimi_review, kimi_challenge, kimi_rescue, kimi_pursue, kimi_swarm, and kimi_swarm_write. They use the same companion runtime, safety hooks, jobs, budgets, and artifacts. Rescue and pursue edit the selected workspace; swarm-write returns a patch without applying or committing it.
From this repository checkout, run:
dsh plugin --profile web add ./plugins/kimi-dsh
For the published npm bundle, run dsh plugin --profile web add kimi-plugin-cc instead.
For DSH Discover, enable Custom plugin indexes and add https://raw.githubusercontent.com/linxule/kimi-plugin-cc/main/dsh/index.json as an index source.
Restart DSH when requested, then run /kimi-setup and /kimi-setup --check. Ask DSH to use one of the seven tools with a self-contained task. Job controls are /kimi-status, /kimi-result, and /kimi-cancel. /kimi-setup --models lists configured models, and /kimi-setup --uninstall removes only the DSH hook.
DSH requires Node.js 24.9 or newer and DSH >=0.2.1-rc.5 <0.3.0. See the DSH bundle guide for profile-level model, thinking, budget, review-base, and other configuration.
The existing marketplace commands above remain the default for Claude Code and
Codex. Published releases are also available as
kimi-plugin-cc on npm, including
all three compiled plugin distributions. No Bun, TypeScript, or install scripts are
needed to use the package. Kimi Code CLI and Node are still prerequisites.
For an explicitly versioned local Claude Code plugin, this example pins the 2.5.1 package:
npm install --prefix ~/.local/share/kimi-plugin-cc kimi-plugin-cc@2.5.1
claude --plugin-dir ~/.local/share/kimi-plugin-cc/node_modules/kimi-plugin-cc
Run /kimi:setup, then /kimi:setup --check in that Claude Code session. Use
one installation of the plugin per host; do not load the local copy alongside
an enabled marketplace copy. The package is a plugin, not a replacement for the
upstream kimi executable, and does not expose an npx kimi-plugin-cc command.
To update this local copy, install the desired npm version into the same prefix, restart the session, and run setup/check again. Codex users should continue to use the GitHub marketplace instructions above. Maintainers: see registry releases.
| Task | Claude Code command | Codex skill | File access |
|---|---|---|---|
| Explain code | /kimi:ask | $kimi-ask | Read-only |
| Review code changes | /kimi:review | $kimi-review | Read-only |
| Challenge a design or approach | /kimi:challenge | $kimi-challenge | Read-only |
| Make a focused fix | /kimi:rescue | $kimi-rescue | Can edit your project |
| Review several areas at once | /kimi:swarm | $kimi-swarm | Read-only |
| Prepare edits in parallel | /kimi:swarm --write | $kimi-swarm-write | Only in a temporary Git worktree; returns a patch for you to apply |
| Work toward a goal over several turns | /kimi:pursue | $kimi-pursue | Can edit your project; experimental |
Review and challenge inspect your Git diff. Use ask for general questions about your repository.
Pursue and swarm have time limits. Swarm runs tasks in parallel, so it can use more tokens than a single task.
Claude Code also has an optional review gate. It checks work when Claude finishes a turn and is off by default.
Plugin sessions use the shared Kimi Code Desktop and kimi web history. New native-v2 sessions receive a readable fallback title that Kimi can replace with a generated title. Manual renames are preserved. For missing older sessions and the native Gen Title action, see session visibility and titles.
New Kimi sessions use your configured default model. You only need to choose a model if you want a different one.
In Claude Code, run /kimi:setup --models. In Codex, ask $kimi-setup to list configured models. This reads your local model list. It does not contact providers or test credentials. A listed model can still fail because of authentication, access, or tool support.
Copy a model alias from the list. Replace provider/model with that alias:
/kimi:review -m 'provider/model' Check error handling in this diff.
In Codex, ask “Use $kimi-review with my configured model named …”. Both apps support model requests in plain language. If several models match, the assistant asks you to choose. It does not guess model IDs or switch models silently after an error.
To test a listed model, run a small task with its alias. This makes a provider call under your account.
A choice for one task does not change your saved default. To change that default, run kimi and use /model.
Resumed sessions keep their previous model unless you pass -m with a different alias. For swarm, -m selects the coordinator's model. Workers may use different models from Kimi's secondary-model settings. See model selection and provider setup.
Use these commands to follow a task:
| Action | Claude Code command | Codex skill |
|---|---|---|
| Check progress | /kimi:status | $kimi-status |
| Read the result | /kimi:result | $kimi-result |
| Cancel work | /kimi:cancel | $kimi-cancel |
Without a job ID, cancel stops the latest running task for this repository. If several tasks are running, check which one you want to stop first. Use cancel rather than interrupting the app so write-swarm can save its patch. For interrupted runs created by the unreleased recovery implementation, see preview-first swarm recovery; it never applies a patch or deletes abandoned work.
Canceling a task does not undo changes it has already made.
Ask and rescue support resuming a session. For example, /kimi:ask -r Explain the next step. continues your latest ask session. In Codex, ask $kimi-ask to resume it. See the ask options and rescue options.
The plugin also bundles one MCP stdio server for Claude Code and Codex, alongside the existing slash commands and skills. Those interfaces remain available, and the existing safety-hook setup is still mandatory.
The seven model tools are kimi_ask, kimi_review, kimi_challenge, kimi_rescue, kimi_pursue, kimi_swarm, and kimi_swarm_write. Job control uses kimi_job_status, kimi_job_result, and kimi_job_cancel.
tasks/get and cancel them with tasks/cancel.Stars on GitHub
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookLets you use the Kimi model from inside a Claude Code or Codex session to explain code, review changes, challenge a design, or pursue a goal. It gives an independent second opinion from a different model family. Install it once and the right skill fires as you prompt, with no slash command to remember. It is listed on Flowy in the Development category. It includes kimi-ask, kimi-cancel, kimi-challenge. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it