claude-code-zero

English | 한국어

A plugin marketplace I built from what I needed while using Claude Code.

Install

Option A — Plugin Marketplace (recommended)

Full install: skills, hooks, agents, MCP servers, scripts — everything the plugin ships.

# 1. Add the marketplace (once)
/plugin marketplace add LeeJuOh/claude-code-zero

# 2. Install a plugin
/plugin install <plugin-name>@claude-code-zero

Or from the terminal:

claude plugin add <plugin-name>@claude-code-zero

Option B — npx skills (skills only)

Installs SKILL.md files via the skills CLI. Quick, no marketplace registration needed — but hooks, agents, MCP servers, and scripts are not included. Plugins that depend on hooks (worktree-plus, rubber-duck-tutor, claw-mo, codex-advisor) or agents (vision-powers, codex-advisor) will have reduced functionality.

npx skills add LeeJuOh/claude-code-zero

Verify

Run /plugin and check the Installed tab.

Plugins

codex-advisor

Problem: First rule of agents — don't trust an agent's own output. So you get a second opinion. But a second opinion you can't check is just another confident guess, hallucinated citations and all.

Solution: codex-advisor sends your code, plans, and research to Codex — a different model, deeper on code — for an independent second opinion, then fact-checks everything Codex returns: Agreed / Disputed / Nuanced / False Positive / Uncited. You get the cross-model check and a guard against Codex's confident hallucinations.

codex-review · codex-adversarial · codex-rescue · codex-verify · codex-research · codex-transfer · codex-status · codex-result · codex-cancel · codex-setup

vision-powers

Problem: Complex analysis buried in terminal text — architecture, security issues, git diffs all lose structure. Impossible to share with teammates.

Solution: Turns the analysis into a shareable report — your pick of a self-contained interactive HTML file (Mermaid diagrams + Chart.js dashboards), portable Markdown for PRs and chat, or a claude.ai Artifact link via --artifact. Audits plugins (local, installed, or GitHub), git diffs, and markdown docs. Before delivering, Claude renders the report and reads it back as an image to catch diagrams that broke in layout.

plugin-visual · diff-visual · doc-visual · fact-check · context-health-visual · report-manager

skill-creator-pro

Problem: Building a skill that triggers when it should and actually helps is trial and error — no way to measure trigger accuracy, no structured improvement loop, no benchmark to tell you if a change helped.

Solution: Anthropic's official skill-creator coaching loop — draft, test against real prompts, review side-by-side baseline-vs-with-skill diffs, improve — plus a description-trigger optimizer and an HTML benchmark viewer. auto-optimize adds a hands-off hill-climbing pass for skills that already mostly work.

skill-creator-pro · auto-optimize

worktree-plus

Problem: Claude Code's built-in worktree leaves your gitignored files behind — .env, local config, local-only docs — so the project won't run; it doesn't track state, and can delete uncommitted work on removal.

Solution: .worktreeinclude copies the small, irreplaceable files (.env, local docs) into each worktree; .worktreelink symlinks the big, branch-invariant ones (downloaded assets, shared caches) at zero disk cost. Safety guard blocks removal if uncommitted changes or unpushed commits exist. Audit trail in .worktree.log.

worktree-setup · auto-hooks on WorktreeCreate/Remove

notebooklm-connector

Problem: Your research lives in NotebookLM but querying it means context-switching, copy-pasting, and burning tokens on ungrounded answers.

Solution: Chrome automation queries NotebookLM directly from Claude Code. Source-grounded answers with automatic follow-up rounds (default 3) to fill coverage gaps. Per-project notebook registry.

notebooklm-manager (query · add · list · search · enable/disable · remove)

claw-mo

Problem: mo markdown viewer is powerful but tedious to configure — port numbers, watch patterns, fsnotify drops files silently.

Solution: Per-project config with auto-sync hook. Every time Claude writes or edits a markdown file, it appears in mo automatically. Group-based organization, full-text search, Mermaid + KaTeX + Shiki rendering.

claw-mo-setup · claw-mo-up · claw-mo-down · claw-mo-open · claw-mo-manage

claw-mux

Problem: Claude Code is trapped in a single terminal pane. Can't send commands to other panes, read their output, or orchestrate parallel workflows.

Solution: Full cmux integration — split layouts, send commands to any pane, read screen output, automate WKWebView browsers, and report progress via sidebar primitives (status / progress bar / leveled logs).

claw-mux · cmux-browser · cmux-markdown

toolbox

Problem: Session context vanishes between conversations. Secrets end up hardcoded. References drift out of sync.

Solution: Four focused utilities — resumption-ordered handoff docs, secret extraction with auto-load hooks, sitemap discovery, and reference sync.

handoff · secret-setup · fetch-sitemap · sync-references

rubber-duck-tutor

Problem: Passively accepting AI-generated code leads to 17% worse comprehension. You merge code you don't truly understand.

Solution: Rubber duck questioning across the whole AI-coding lifecycle. Plan/spec creation suggests a branched review; shipping (git push / PR) confronts you inline — targeting the riskiest change you didn't discuss, retrying an unresolved past gap, or demoting to a non-blocking scoreboard after three ignored confrontations. Hint ladder guides without revealing answers; every fire/answer/ignore is logged.

duck · duck-prebuild · duck-verify · duck-review · duck-orient

vibeproxy-kit

Problem: Wiring VibeProxy manually (OAuth, aliases, config.yaml, shell edits) is error-prone. State is unclear — which backend is actually responding?

Solution: Explicit state management with backup/rollback. Per-backend isolation probe tells you exactly which model handles each alias. Pre-existing alias migration with Keep / Merge / Reset modes.

setup-aliases · cc-list

Plugin Management

/plugin disable <plugin-name>@claude-code-zero    # Disable
/plugin enable <plugin-name>@claude-code-zero     # Re-enable
/plugin update <plugin-name>@claude-code-zero     # Update to latest
/plugin uninstall <plugin-name>@claude-code-zero  # Uninstall

License

MIT License

{
  "name": "claude-code-zero",
  "metadata": {
    "description": "Claude Code plugins, curated and shareable"
  },
  "owner": {
    "name": "LeeJuOh",
    "email": "xop4p@naver.com"
  },
  "plugins": [
    {
      "name": "notebooklm-connector",
      "source": "./plugins/notebooklm-connector",
      "version": "1.3.3",
      "description": "Query Google NotebookLM notebooks from Claude Code through Chrome automation, with coverage-checked follow-up queries and a notebook library (add, list, search, enable/disable, remove)."
    },
    {
      "name": "toolbox",
      "source": "./plugins/toolbox",
      "version": "2.0.1",
      "description": "Personal utility commands and tools for Claude Code"
    },
    {
      "name": "vibeproxy-kit",
      "source": "./plugins/vibeproxy-kit",
      "version": "0.9.3",
      "description": "State-aware VibeProxy alias manager for Claude Code. Discover VibeProxy state, choose backend-specific cc-* aliases, and rewrite only managed config and shell blocks without clobbering manual edits."
    },
    {
      "name": "vision-powers",
      "source": "./plugins/vision-powers",
      "version": "5.0.0",
      "description": "Visualize Claude Code plugins, git diffs, and markdown docs as HTML or markdown reports with diagrams. On a capable account, HTML reports publish as claude.ai Artifacts (--local writes a local file instead). Skills: plugin-visual (plugin audit with security and architecture), diff-visual (catch up on a diff before review, with a quiz), doc-visual (diagrams per section), fact-check (verify claims against code and git history), report-manager (list, open, delete, search, refine). Reports take --format md and --lang."
    },
    {
      "name": "worktree-plus",
      "source": "./plugins/worktree-plus",
      "version": "3.2.2",
      "description": "Replaces Claude Code's built-in worktree — aligns with native git worktree where CC diverges (HEAD base, origin/* auto-tracking) and adds layers native lacks: .worktreeinclude/.worktreelink for gitignored files with a /worktree-setup skill that scans and builds them, upstream-aware removal guard, idempotent re-entry."
    },
    {
      "name": "skill-creator-pro",
      "source": "./plugins/skill-creator-pro",
      "version": "2.1.0",
      "description": "Create, test, and iteratively improve Claude Code skills with the official lean coaching loop, an eval harness for benchmarking with variance analysis, automated description-trigger optimization, and a user-started autonomous output-quality optimizer"
    },
    {
      "name": "codex-advisor",
      "source": "./plugins/codex-advisor",
      "version": "5.2.0",
      "description": "Get Codex's second opinion — and actually trust it: a different model reviews your code, plans, and research, and a fresh independent verifier subagent — never the session that wrote the work — judges every finding (Agreed/Disputed/Nuanced/Unverifiable, plus False Positive/Uncited from the citation script) before you act, catching hallucinated citations. Skills: setup, review, adversarial, rescue, verify, research, status, result, cancel, transfer. Task delegation (rescue) wraps your verbatim request in adaptive, preview-approved prompt blocks. Transfer hands the whole session off to a resumable Codex thread (v1.0.5+). Prompt-running skills accept --model/--effort via config.toml, also passed at run time when a project's own .codex/config.toml would override them."
    },
    {
      "name": "rubber-duck-tutor",
      "source": "./plugins/rubber-duck-tutor",
      "version": "3.1.3",
      "description": "Rubber duck tutor that keeps you engaged across the whole AI-coding lifecycle — before you ask AI to build (/duck-prebuild), once code is written and before you ship (/duck-verify, /duck-review), and when orienting to unfamiliar code (/duck-orient), plus /duck for auto-detect. /coach is its teaching sibling, manual-invocation only: /coach <topic> explains and drills a concept, /coach <file> or a bare /coach right after generating code dissects it section by section (what/why-this-way/where-it-breaks), and /coach alone surfaces an unresolved gap from a past duck session and teaches it — resolved only once you pass the exercise, not by saying you understand. Ship-point hooks triage what you just pushed against six risk categories and target the riskiest change you didn't actually discuss, fall back to retrieving an unresolved gap from a past session, or demote to a non-blocking scoreboard after three ignored confrontations in a row. Confrontation telemetry (fired/answered/ignored) is queryable from /duck-orient. Doesn't overlap /code-review or /grilling — duck only checks whether you understand, never whether the code or plan is good, and never teaches — that's coach's job."
    },
    {
      "name": "claw-mo",
      "source": "./plugins/claw-mo",
      "version": "2.8.2",
      "description": "Manage mo markdown viewer sessions: autosync new Claude-written .md via PostToolUse hook, group-based organization, restart-on-up for fsnotify-miss recovery, file deep-linking, stdin pipe support, cmux browser integration, per-project watch patterns, port isolation"
    },
    {
      "name": "claw-mux",
      "source": "./plugins/claw-mux",
      "version": "1.2.1",
      "description": "cmux terminal integration: terminal I/O, topology control, browser automation, markdown viewer, notifications",
      "tags": [
        "cmux",
        "terminal",
        "browser-automation",
        "terminal-io"
      ]
    }
  ]
}