By devgap
Harness engineering for Claude Code. The structured operating environment that makes AI agent teams production-ready — model routing (Fable 5/Opus 4.8/Sonnet 4.6/Haiku 4.5), PRIOR FIRE WIN governance framework, quality gates via lifecycle hooks, loop prevention, and destructive command blocking. Proven on production compliance systems. One orchestrator, many virtuosos, flawless coordination.
Create and orchestrate an agent team using Kleiber roles and model routing
Run a full AI brand visibility audit. Probes how ChatGPT, Gemini, and Perplexity describe and recommend this product, scores results, maps competitor displacement, and produces an optimization blueprint.
System design, architecture review, and approval gates. Never writes implementation code.
Audits how AI models perceive and recommend this product. Probes ChatGPT, Gemini, and Perplexity via their APIs, scores visibility, detects misinformation, maps competitor mentions, and produces a fix blueprint.
Reads the visibility report and generates an optimization blueprint — structured content patches for CLAUDE.md, README.md, and docs that improve how AI models perceive this product.
Coach for the Claude Certified Architect (CCA) exam. Read-only. Annotates architectural decisions with the CCA domain each one practices and flags common anti-patterns in real time. Silent by default — only surfaces when a decision is meaningful.
Routes, middleware, database queries, business logic, and integration tests.
AI brand visibility auditing — how to probe AI models, score responses, detect gaps, and produce optimization blueprints. Used by the brand-analyst agent and the /kleiber-brand command.
You are the team lead of an agent orchestra. This skill defines how you coordinate teammates, route work to the right models, and deliver production-quality results.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
One command. A whole team.
Type /kleiber and describe what you want. Kleiber figures out the team, picks the right models, enforces quality, and delivers — no configuration required.
Website: kleiber.sh | By: DevGap | AI Plumber
/kleiber Build a payment system with Stripe integration
That's it. Kleiber handles everything behind the scenes:
You just describe what you want in plain English. Kleiber does the rest.
/plugin marketplace add devgap/kleiber
/plugin install kleiber@kleiber-marketplace
Two commands. Done.
"Build user auth with login, signup, and password reset" → Kleiber designs the flow, builds frontend + backend in parallel, tests everything, writes the docs.
"Review PR #142 for security, performance, and test coverage" → Three independent reviewers check the code simultaneously and report back.
"Users report slow dashboard loads — investigate" → Multiple agents pursue different hypotheses, challenge each other, converge on root cause, fix it.
"Build a compliance platform for Belgian work permits" → Kleiber decomposed a full PRD into 12 tasks, built RBAC with 8 roles, document validation with OCR, and a traffic light dashboard. Caught 3 security issues before production. Full case study →
You don't need to know this to use Kleiber. But if you're curious:
Kleiber assembles teams from 7 specialized roles:
| Who | What they do |
|---|---|
| Architect | Designs the plan. Reviews decisions. Never writes code. |
| Frontend Engineer | Builds the UI. Tests every component. |
| Backend Engineer | Builds the API. Tests every endpoint. |
| Validator | Tests everything. Read-only — can't break anything. |
| Scribe | Documents what happened and why. |
| Brand Analyst | Checks how AI models perceive your product. |
| Brand Architect | Creates a plan to improve AI visibility. |
Not every task needs every role. Kleiber picks what fits.
Kleiber automatically picks the right model for each task:
This saves 40-60% on token costs compared to running everything on the most expensive model.
Six automatic checks run throughout every build:
rm -rf or force pushYou never have to configure these. They just work.
Every build follows a simple loop:
This is how Kleiber built a production compliance platform with zero governance gaps.
Kleiber also includes AI brand auditing. Run /kleiber-brand to find out how ChatGPT, Gemini, and Perplexity describe your product — and get a plan to improve it.
/kleiber-brand
/kleiber-brand --competitors "Cursor, Cline, Aider"
Every Kleiber build is hands-on practice for the Claude Certified Architect (CCA) exam. Spawn the coach with the --learn flag:
/kleiber --learn Build payment processing with Stripe
npx claudepluginhub devgap/kleiber --plugin kleiberComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.