claude-code-expert

Plugin claude-code-expert from marketplace claude-orchestration in TheLobbi/claude. Commands read from the repo's manifest — 16 days ago.

Skills (70)

• agent-lifecycle
• agent-sdk
• agent-team-topologies

  Agent-team topology kits — 5 production-ready team configurations with task decomposition, file ownership, worktree guidance, and quality-gate hooks

• agent-teams-advanced

  Advanced patterns for Claude Code Agent Teams — topology design, cross-team communication, worktree coordination, failure handling, and cost management

• agent-teams
• agentic-patterns
• autonomy-profiles

  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.

• channels-bootstrap

  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.

• channels-user-guide
• channels
• checkpointing
• cicd-integration

  Patterns for integrating Claude Code into CI/CD pipelines — GitHub Actions, GitLab CI, pre-commit hooks, automated PR reviews, headless mode, and cost control

• cli-reference
• common-workflows

  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

  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

• configuration
• context-anchoring
• context-budgeting

  Advanced context window management — token arithmetic, anchor budget math, compact strategies, progressive loading, and large codebase partitioning

• context-management
• cost-optimization
• council-review

  Domain knowledge for multi-agent council review protocols, orchestration patterns, scoring systems, and deliberation frameworks

• deep-code-intelligence

  Evidence-driven workflow for hard coding problems, architecture decisions, root-cause analysis, and high-stakes implementation planning in Claude Code

• enterprise-security

  Enterprise-grade security patterns for Claude Code — audit logging, compliance frameworks, secrets management, permission hardening, network security, and managed settings enforcement

• extended-thinking
• git-integration
• hook-policy-engine

  Hook policy engine with 8 installable packs for safety, verification, context recovery, and teammate quality gates

• hook-script-library

  Security-hardened hook script implementations — ready-to-paste templates for security-guard, auto-format, inject-context, session-init, on-stop, and lessons-learned-capture

• hooks-system
• ide-integrations
• lsp-integration

  LSP server detection, installation, and Claude Code integration — auto-invoke when setting up a new project, running /cc-setup, or configuring IDE tooling

• mcp-servers
• memory-instructions
• model-routing

  Intelligent model selection for Claude Code — decision matrices, cost tables, budget planning, and subagent model assignment for optimal cost/quality tradeoffs

• permissions-security
• plugin-development

  Complete guide to building Claude Code plugins — manifest schema, command/skill/agent/hook authoring, MCP server development, marketplace publishing, and testing

• project-sync

  Project sync and configuration propagation — auto-invoke when running /cc-sync or updating Claude Code setup across repos

• prompt-engineering

  Crafting effective prompts, CLAUDE.md instructions, rules, agent system prompts, and skill bodies for optimal Claude Code behavior

• research-routing
• runtime-selection

  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.

• scheduled-tasks
• self-healing-advanced
• session-analytics

  Understanding and optimizing Claude Code session performance — token tracking, bottleneck identification, caching behavior, and cost estimation

• settings-deep-dive
• slash-commands
• teams-collaboration
• testing-workflows
• tools-reference
• troubleshooting
• worked-examples

  Step-by-step tutorials and worked examples for common Claude Code workflows — setup, debugging, code review, agent teams, hooks, memory, optimization, and CI/CD

• cc-agent-teams

  Select and coordinate multi-agent teams (topology kits, role-based squads, lifecycle, worktree isolation). Use this skill whenever launching parallel agents, designing a review board, running a debug council, scheduling an orchestrator-workers team, configuring agent tool restrictions, or deciding b

• cc-agentic-patterns
• cc-auto-mode
• cc-autonomy-mode
• cc-context-budgeting
• cc-deep-code-intelligence
• cc-hook-authoring
• cc-mcp
• cc-model-routing
• cc-monitor-tool
• cc-orchestration-blackboard
• cc-plugin-development
• cc-prompt-budget-preflight
• cc-prompt-engineering
• cc-second-brain
• cc-security-compliance
• cc-stack-setup
• cc-stack-sync
• cc-ultraplan
• cc-verify-between-waves
• cc-worktree-management

Slash commands (12)

• /claude-code-expert:cc-autonomy

  Configure Claude Code autonomous operating mode — profile selection (conservative, balanced, aggressive, unattended-review), permission block generation, gate agent wiring.

• /claude-code-expert:cc-channels

  Install event-driven channel servers — CI webhook receiver, mobile approval relay, Discord bridge, fakechat dev profile. Integrates with MCP cc_kb_channel_server.

• /claude-code-expert:cc-council

  Multi-agent council review — security + performance + test + architecture perspectives delivered in parallel with weighted synthesis. Uses blackboard pattern with council-coordinator.

• /claude-code-expert:cc-debug

  Diagnose Claude Code issues — plugin load failures, MCP connection problems, hook misfiring, permission denials, skill/agent not triggering. Absorbs legacy cc-troubleshoot.

• /claude-code-expert:cc-help

  Plugin help — task-routing table that maps "I want to X" to the right command, skill, or agent in the claude-code-expert plugin.

• /claude-code-expert:cc-hooks

  Install, list, remove, and debug Claude Code hook packs. Integrates with the 8 security-hardened packs in the plugin's MCP KB.

• /claude-code-expert:cc-intel

  Deep evidence-driven analysis for hard coding problems — architecture decisions, root-cause investigation, high-stakes refactor planning, performance bottleneck isolation. Invokes the principal-engineer-strategist agent.

• /claude-code-expert:cc-memory

  Wrap engram for CC-scoped memory operations — search, export, consolidate, edit-always, review. Bridges engram (tier 1) and Obsidian vault (tier 2) via the memory-consolidator agent.

• /claude-code-expert:cc-orchestrate

  Launch a multi-agent workflow by agentic pattern (chain, routing, parallelization, eval-optimizer, orchestrator-workers, reflection, ReAct, blackboard). Runs pattern-router to select if pattern isn't specified.

• /claude-code-expert:cc-setup

  Deploy or audit the full 5-layer Claude Code stack (CLAUDE.md + skills + hooks + agents + memory) in the current repository. Absorbs the legacy cc-bootstrap command via --audit.

• /claude-code-expert:cc-skills

  The claude-code-expert plugin ships 21 skills. Reading CLAUDE.md and hunting for trigger keywords is not a good discovery UX. /cc-skills lists every skill in the plugin, grouped by category, with its trigger phrases and a one-line description so you can find the right one in

• /claude-code-expert:cc-sync

  Idempotent update of an existing Claude Code setup — re-fingerprint, propagate to sub-repos, refresh docs, section-merge CLAUDE.md. Absorbs legacy cc-config via --fix-drift.

Subagents (18)

• cc-audit-reviewer

  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.

• cc-autonomy-planner

  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.

• cc-autonomy-reviewer

  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.

• cc-autonomy-verifier

  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.

• cc-council-coordinator

  Coordinator agent that implements fan-out/fan-in orchestration with blackboard pattern, circuit breakers, partial failure recovery, and structured consensus building

• cc-debugger

  Scope — generic code-level bugs in the user's codebase. Systematic root-cause tracer using hypothesis-driven investigation; read-only by default, proposes fixes without applying them unless explicitly authorized. For Claude Code itself (MCP, hooks, plugin install), use the `claude-code-debugger` age

• cc-dependency-auditor

  Dependency health auditor — checks for security vulnerabilities, outdated packages, license issues, and bloat. Produces actionable upgrade reports. Read-only; does not modify package files.

• cc-evaluator-optimizer

  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.

• cc-implementer

  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.

• cc-memory-consolidator

  Bridges the three memory tiers — reads engram (tier 1, never writes), promotes reusable patterns and decisions into the Obsidian vault (tier 2) and plugin baseline rules (tier 3). Read-only on engram and on user-curated Obsidian notes; writes only auto-generated notes. Invoke for memory consolidatio

• cc-migration-lead

  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.

• cc-pattern-router

  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.

• cc-plugin-architect

  Plugin architecture specialist that designs plugin structures, scaffolds files, validates manifests, and advises on marketplace publishing readiness.

• cc-principal-engineer-strategist

  Principal-level engineering strategist for deep analysis, root-cause isolation, architecture review, and implementation pressure-testing.

• cc-release-coordinator

  Release planning and execution coordinator. Generates changelogs, tags versions, validates release readiness, coordinates with CI/CD. Emphasizes checklist-driven, reversible releases.

• cc-research-orchestrator

  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.

• cc-security-compliance-advisor

  Security and compliance specialist that audits Claude Code setups against enterprise security checklists and produces actionable compliance reports.

• cc-team-orchestrator

  Master orchestrator that prefers delegation over direct work. Manages agent teams, coordinates sub-agents, enforces audit loops, and maintains agent lifecycle health.

Similar plugins