kleiber-marketplace

Kleiber Agent TappedOut

Agent team orchestration for Claude Code. Structured roles, model routing, quality gates, and loop prevention.

Named after conductor Carlos Kleiber — one orchestrator, many virtuosos, flawless coordination.

Website: kleiber-site.vercel.app | By: DevGap | AI Plumber

Why Kleiber?

Anthropic shipped native agent teams in Claude Code. Kleiber adds the opinionated layer that makes them production-ready:

• Pre-configured roles — 7 agent roles with battle-tested spawn prompts so you don't rewrite them every session
• Model routing — Opus for architecture, Sonnet for implementation, Haiku for validation. Cheapest model that can reliably do the job.
• Quality hooks — 6 hooks enforce tests, types, safety, and brand consistency at every stage of the pipeline
• Loop detection — Ralph Loop Guard stops agents after 3 repeated errors
• Destructive command blocker — Blocks rm -rf, git push --force, DROP TABLE before execution
• Delegate mode enforced — Lead agent coordinates only, never implements
• AI Visibility Auditing — BrandMind-style probes that score how ChatGPT, Gemini, and Perplexity perceive your product, with automated optimization blueprints

Prerequisites

Agent teams are experimental and disabled by default. Enable them first:

// Add to your Claude Code settings.json
{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

Or set it in your shell:

export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

Install

# Add the marketplace
/plugin marketplace add Devgapperk/kleiber

# Install the plugin
/plugin install kleiber@kleiber-marketplace

What You Get

Slash commands:

• /kleiber — creates and orchestrates agent teams with a single command
• /kleiber-brand — runs a full AI brand visibility audit

7 agent roles with pre-configured spawn prompts and model routing:

Role	Model	Purpose
Architect	Opus	Design, review, approve. Never writes code.
Engineer-Frontend	Sonnet	UI components, state, accessibility, tests
Engineer-Backend	Sonnet	Routes, queries, business logic, integration tests
Validator	Haiku	Runs tests, types, lint. Read-only.
Scribe	Haiku	Docs, changelog, decision records
Brand Analyst	Sonnet	Probes AI models, scores visibility, detects misinformation
Brand Architect	Sonnet	Reads visibility gaps, produces optimization blueprint

6 hooks enforcing quality at every stage:

Hook	Trigger	What It Does
stop-loop-guard	Stop	Detects Ralph Loops (agent spinning on same error 3+ times)
task-completed	TaskCompleted	Blocks completion if tests or types fail
teammate-idle	TeammateIdle	Prevents idle if uncommitted changes exist
post-edit-verify	PostToolUse (Write/Edit)	Type-checks after every file edit
block-destructive	PreToolUse (Bash)	Blocks rm -rf, force push, DROP TABLE
brand-drift-check	PostToolUse (Write/Edit)	Warns when doc edits contradict AI visibility baseline

2 skills:

• Orchestration — model routing rules, task decomposition protocol, quality gates, and anti-pattern detection
• Brand Visibility — AI probe patterns, scoring rubric, gap detection, and optimization blueprint patterns

Usage

Start Claude Code and use the /kleiber command:

/kleiber Build user authentication with login, signup, and password reset

Or describe the team you want directly:

Create an agent team to build [feature]. Spawn architect (opus), frontend
engineer (sonnet), backend engineer (sonnet), validator (haiku), scribe (haiku).
Use delegate mode.

Keyboard shortcuts once your team is running:

Shortcut	Action
Shift+Tab	Toggle delegate mode (lead coordinates only)
Shift+Up/Down	Switch between teammates (in-process mode)

Example Prompts

Full feature build:

/kleiber Implement a payment processing module with Stripe integration

Parallel code review:

Create an agent team to review PR #142. Three reviewers: security, performance,
test coverage. Have them report independently.

Bug investigation:

Users report [symptom]. Create a team with 4 teammates investigating competing
hypotheses. Have them challenge each other's theories.

AI Visibility Auditing

Kleiber includes BrandMind-style AI visibility auditing that measures how ChatGPT, Gemini, and Perplexity perceive and recommend your product.

What it does: