High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
npx claudepluginhub markus41/claude --plugin claude-code-expertCreate and manage custom agents for Claude Code.
Deploy a first-class autonomy operating profile that composes memory, workflow, orchestration, hooks, and verification into one deployable system. More than documentation — generates preset files, enforcement hooks, and specialized agents.
Scan an existing repository, detect its full tech stack, and generate a deployable
Use `/cc-budget` to understand how much of your context window is consumed by always-on content (CLAUDE.md, rules, skills, MCP schemas) and how much remains for actual work.
Bootstrap Claude Code channel integrations for your project: generate starter server
Detect your project's CI/CD setup, generate Claude Code workflows optimized for your platform, and deploy production-ready automation for PR reviews, code generation, test validation, and security scanning.
Generate, audit, or modify Claude Code configuration files.
Comprehensive multi-agent council review with 6 protocols, 10 specialists, scoped scoring (per-scope thresholds and weights), state machine orchestration, auto-fix, and 50+ configuration flags
Comprehensive debugger for Claude Code configuration and setup issues.
Interactive documentation lookup for any Claude Code feature.
Design, create, and manage Claude Code hooks.
Use `/cc-intel` when a task is ambiguous, high impact, architecturally risky, or likely to hide non-obvious coupling. This command upgrades Claude from “helpful implementer” into a **principal engineer with receipts**.
Use `/cc-learn` to browse and follow step-by-step tutorials for common Claude Code workflows.
Configure, troubleshoot, and manage MCP servers for Claude Code.
Configure persistent memory that survives across sessions using a layered approach:
Deploy pre-built agent team configurations for common development patterns. Choose between
Use `/cc-perf` to understand where tokens and money are going in your Claude Code sessions, identify waste, and optimize for cost or speed.
Turn Claude Code into a recurring autonomous operator. `/cc-schedule` produces optimized, guardrailed prompts for common engineering maintenance workflows — ready to run on Desktop, Cloud, or in-session via `/loop`.
Analyze the current repository, detect its tech stack, and deploy a complete Claude Code
Re-analyze the current project, update the full Claude Code configuration, propagate `.claude/`
Diagnose and fix Claude Code setup and runtime issues.
Manages sub-agent lifecycle — health checks, idle detection, cleanup, retention, and escalation. Ensures no orphaned or stalled agents waste tokens.
Second-round audit agent that reviews work produced by other agents. Finds gaps, missed edge cases, inconsistencies, and quality issues that first-pass agents missed. Uses Context7 to validate library usage against official docs.
Decomposes any engineering task into a phased, risk-assessed plan with explicit verification steps and rollback paths. Invoked by /cc-autonomy plan "<task>". Writes the plan to .claude/active-task.md. Never implements — plan-only.
Final review agent for autonomous work. Reads the plan from .claude/active-task.md, diffs changed files against the plan, reads each changed file, and issues BLOCK or APPROVE with specific findings. Invoked by /cc-autonomy review after the verifier passes. Never modifies files.
Runs the verification suite after an implementation phase completes. Reads verification steps from .claude/active-task.md, detects project type, runs typecheck + lint + tests + diff check + secret scan, and produces a structured PASS or FAIL report. Never modifies files.
Expert architect for Claude Code project setup, configuration, and best practices. Deep knowledge of CLAUDE.md, settings.json, directory structure, rules, skills, hooks, and plugins.
Expert debugger for Claude Code setup issues. Diagnoses and fixes authentication, MCP servers, hooks, permissions, configuration, installation, and runtime problems.
Coordinator agent that implements fan-out/fan-in orchestration with blackboard pattern, circuit breakers, partial failure recovery, and structured consensus building
Systematic debugger — traces errors to root cause using hypothesis-driven investigation. Read-only by default, proposes fixes without applying them unless explicitly authorized.
Dependency health auditor — checks for security vulnerabilities, outdated packages, license issues, and bloat. Produces actionable upgrade reports. Read-only; does not modify package files.
Implements the Evaluator-Optimizer loop pattern — generates an artifact, evaluates it against a rubric, and iteratively refines until quality threshold is met or max iterations reached. Use for code generation, config authoring, and any task where output quality must be verified before acceptance.
Expert in Claude Code hooks system - PreToolUse, PostToolUse, Notification, Stop, and SubagentStop lifecycle events. Designs, implements, and debugs hook scripts.
Expert in Claude Code IDE integrations including VS Code extension, JetBrains plugin, terminal configuration, remote development, and CI/CD pipelines.
Focused implementation agent — writes code, edits files, runs builds. Restricted to write tools. Does not read broad context, only what's needed for the current task.
Expert in MCP (Model Context Protocol) server configuration, troubleshooting, and custom server development. Covers all official and community MCP servers.
Migration planning and execution specialist for database schema changes, API version migrations, dependency upgrades, and large-scale refactors. Emphasis on zero-downtime and rollback safety.
Analyzes incoming tasks and selects the optimal agentic design pattern (prompt chain, routing, parallelization, eval-optimizer, orchestrator-workers, reflection, or ReAct). Routes to the right pattern implementation to avoid over-engineering simple tasks or under-powering complex ones.
Expert in Claude Code security model, permissions configuration, tool allowlists/denylists, enterprise managed settings, and security hardening.
Plugin architecture specialist that designs plugin structures, scaffolds files, validates manifests, and advises on marketplace publishing readiness.
Principal-level engineering strategist for deep analysis, root-cause isolation, architecture review, and implementation pressure-testing.
Release planning and execution coordinator. Generates changelogs, tags versions, validates release readiness, coordinates with CI/CD. Emphasizes checklist-driven, reversible releases.
Routes research tasks to the optimal MCP tool chain — Perplexity for knowledge Q&A, Firecrawl for structured extraction, Context7 for library docs. Chains tools for comprehensive results.
Expert in Claude Agent SDK, Claude API, and programmatic Claude Code usage. Covers building custom agents, tool use, streaming, multi-agent patterns, and CI/CD integration.
Security and compliance specialist that audits Claude Code setups against enterprise security checklists and produces actionable compliance reports.
Master orchestrator that prefers delegation over direct work. Manages agent teams, coordinates sub-agents, enforces audit loops, and maintains agent lifecycle health.
Specialist in designing Claude Code Agent Team topologies, sizing teams, and optimizing cross-agent coordination patterns.
Complete guide to managing sub-agent and teammate lifecycle in Claude Code — health checks, idle detection, cleanup, retention, and the mandatory audit loop.
Complete guide to the Claude Agent SDK for building custom AI agents.
Agent-team topology kits — 5 production-ready team configurations with task decomposition, file ownership, worktree guidance, and quality-gate hooks
Advanced patterns for Claude Code Agent Teams — topology design, cross-team communication, worktree coordination, failure handling, and cost management
> Orchestrate teams of Claude Code sessions working together with shared tasks, inter-agent messaging, and centralized management.
> Comprehensive pattern catalog integrating Andrew Ng's four foundational patterns, Anthropic's
Runtime behavior specs for the four autonomy profiles, the three autonomy agents (planner, verifier, reviewer), memory integration, context survival, and anti-patterns. Activate this skill to run the autonomy system — not just to read about it.
Production-ready channel server implementations — CI webhook receiver, mobile approval relay, Discord/Telegram bridge, and local fakechat dev profile. Copy-paste starter code with sender allowlists, permission relay, and security hardening.
> Push events into a running Claude Code session with channels.
> Build MCP servers that push webhooks, alerts, and chat messages into a Claude Code session.
> Track, rewind, and summarize Claude's edits and conversation to manage session state.
Patterns for integrating Claude Code into CI/CD pipelines — GitHub Actions, GitLab CI, pre-commit hooks, automated PR reviews, headless mode, and cost control
Complete reference for the Claude Code command-line interface.
Workflow packs for the 7 most common Claude Code tasks — codebase exploration, bug fixing, safe refactoring, TDD, repo review before merge, CLAUDE.md generation, and migration planning. Each pack has a start prompt, verification steps, subagent opportunities, failure modes, and completion checklist.
Computer use and GUI automation patterns — when to use GUI automation vs shell/MCP/browser tools, visual validation techniques, native app testing, and guardrails for visual regression workflows
Complete guide to all configuration files, settings, and directory structure.
Preserve critical information across `/compact` events, session boundaries, and agent handoffs.
Advanced context window management — token arithmetic, anchor budget math, compact strategies, progressive loading, and large codebase partitioning
Complete guide to managing context window, compression, and conversation flow.
Complete guide to managing costs, model routing, token usage, and caching.
Domain knowledge for multi-agent council review protocols, orchestration patterns, scoring systems, and deliberation frameworks
Evidence-driven workflow for hard coding problems, architecture decisions, root-cause analysis, and high-stakes implementation planning in Claude Code
Enterprise-grade security patterns for Claude Code — audit logging, compliance frameworks, secrets management, permission hardening, network security, and managed settings enforcement
Complete guide to extended thinking modes and thinking budget configuration.
Complete guide to Git workflows and version control within Claude Code.
Hook policy engine with 8 installable packs for safety, verification, context recovery, and teammate quality gates
Security-hardened hook script implementations — ready-to-paste templates for security-guard, auto-format, inject-context, session-init, on-stop, and lessons-learned-capture
Complete reference for the hooks lifecycle system.
Complete guide to using Claude Code with VS Code, JetBrains, and terminal editors.
LSP server detection, installation, and Claude Code integration — auto-invoke when setting up a new project, running /cc-setup, or configuring IDE tooling
Complete guide to Model Context Protocol server configuration and usage.
Complete guide to CLAUDE.md, project instructions, auto-memory, and rules.
Intelligent model selection for Claude Code — decision matrices, cost tables, budget planning, and subagent model assignment for optimal cost/quality tradeoffs
Complete reference for the permission model and security features.
Complete guide to building Claude Code plugins — manifest schema, command/skill/agent/hook authoring, MCP server development, marketplace publishing, and testing
Project sync and configuration propagation — auto-invoke when running /cc-sync or updating Claude Code setup across repos
Crafting effective prompts, CLAUDE.md instructions, rules, agent system prompts, and skill bodies for optimal Claude Code behavior
Optimal routing of research tasks across Perplexity MCP, Firecrawl MCP, and Context7 MCP.
Execution environment selection guide — helps choose between local CLI, Desktop, web, remote SSH, cloud tasks, and cowork sessions based on task requirements. Decision matrix with concrete examples.
> Use `/loop` and cron scheduling tools to run prompts repeatedly, poll for status, or set one-time reminders within a Claude Code session.
Enhanced error capture, pattern detection, automated rotation, and rule promotion
Understanding and optimizing Claude Code session performance — token tracking, bottleneck identification, caching behavior, and cost estimation
Complete reference for every settings option, configuration key, and customization.
Complete reference for all built-in and custom slash commands.
Complete guide to team features, multi-user workflows, and organizational settings.
Complete guide to testing patterns, TDD, and test execution within Claude Code.
Complete reference for every built-in tool available in Claude Code.
Complete guide to diagnosing, debugging, and fixing Claude Code setup and runtime issues.
Step-by-step tutorials and worked examples for common Claude Code workflows — setup, debugging, code review, agent teams, hooks, memory, optimization, and CI/CD
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.