Skip to main content
plugin CX Codex

kk — Claude Code plugin: what it does, how to install

kk — a workflow plugin that carries an AI assistant from design through review, tests and docs, with a permission guard on the side.

Elastic-2.0 ★ 155 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add serpro69/claude-toolbox
/plugin install kk@claude-toolbox
Open on GitHub

What kk does

Fifteen skills turn into a pipeline inside Claude: design, design review, implementation, code review, testing, documentation. Helpers sit next to them, among them /kk:clarify-docs for docs that already exist and for PR drafts. /kk:brainstorm works differently. It talks a technical idea through by asking a single question and waiting for your answer, writes nothing to disk, and does not start the design step on its own.

Profiles for Go, Java, JS/TS, Kotlin, K8s and Python bring review checklists, implementation notes, test validators and doc rubrics. The isolated review variants, /kk:review-code:isolated and /kk:review-design:isolated, add a reviewer that has not seen the chat where the change was written: an internal sub-agent and an external pass through the PAL MCP server. That external route needs a PAL build whose listmodels exposes cli_clients metadata. Plain /kk:review-code and /kk:review-design never touch PAL.

A hook screens Bash, Read/Grep/Glob, Edit/Write/NotebookEdit and capy_execute for secrets and destructive commands. It wants Claude 2.1.295+, jq and Python 3.8+; a missing interpreter or a crashed engine blocks the call instead of letting it through. A project .claude/kk-guard.json can add rules. Loosening destructive categories or the self-modification protection is left to the user-level ~/.claude/kk-guard.json, and secrets stay locked in both.

What it helps with

  • talk a technical decision through before writing code
  • turn a description into a design doc, a plan and tasks
  • get a review from a model that never saw the chat
  • block secrets and destructive commands before Bash runs
  • apply Go or Kotlin review checklists you did not write

Example prompts for the agent

  • Run /kk:brainstorm — I want to settle how caching should work here
  • Do /kk:design from this description and split it into tasks
  • Run /kk:review-code:isolated on the last changes

How to install kk

Plugin marketplace

/plugin marketplace add serpro69/claude-toolbox
/plugin install kk@claude-toolbox

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about kk

How do I install kk in Claude Code?

Add the marketplace with /plugin marketplace add serpro69/claude-toolbox, then install the plugin: /plugin install kk@claude-toolbox. The skills show up in the slash command menu marked (kk).

What does kk do?

It chains skills for one task: design, design review, implementation, code review, tests and documentation. Language profiles and a permission hook sit around that chain.

Does kk work on Codex?

The Codex distribution ships the skills and profiles only. Codex adapters and native rules come from a separate template, and its unconditional forbids can outrank the user exceptions you set for the guard.

Similar plugins

All plugins for Code review and refactoring →

From the same set30

The whole set →
review-code review-code reviews active git changes through an experienced engineering perspective. Identifies SOLID flaws, architecture issues, and security vulnerabilities. CX Codex +1 ★ 155repo stars review-design review-design is a Claude Code skill that checks design documents before implementation begins. It runs after $kk:design and reviews all documents by default. CX Codex +1 ★ 155repo stars review-spec review-spec is a Claude Code skill that compares code with feature docs and reports mismatches in both directions. Run it mid-feature or after completion. CX Codex +1 ★ 155repo stars design-reviewer design-reviewer audits feature designs and implementation plans without conversational bias. Flags ambiguities, missing edge cases, and contradictions before implementation begins. CX Codex ★ 155repo stars spec-reviewer The spec-reviewer subagent checks code against design documents to find missing work, mismatches, and conflicting or unclear docs. Use it for an independent implementation review. CX Codex ★ 155repo stars eval-grader eval-grader — a grader for skill-eval assertions that returns PASS, FAIL or PARTIAL on each, with one line of evidence. Handy when a reviewer's write-up needs a verdict from something that did not produce it. CX Codex ★ 155repo stars code-reviewer code-reviewer is a Claude Code subagent that independently evaluates git diffs for SOLID principles, architectural flaws, and security risks. CX Codex ★ 155repo stars implement This skill guides planned work and standalone fixes through implementation, verification, and code review. It selects a workflow based on the request. CX Codex +1 ★ 155repo stars

Project sponsors

Companies that keep this analytics open