Plugin Claude Code
Bundles 32 skills, 33 commands, 99 agents, 3 hooks · 9,699 tokens together
Self-evolving development pipeline — 3 lean agents across 6 phases with compound discovery loop, proactive research, and strict evaluation. No external dependencies.
Skill Claude CodeCodex
Use when designing or reviewing AI agent memory systems — covers memory type taxonomy (short-term, working, long-term), episodic vs semantic vs procedural memory, embedding-based retrieval with recency and importance weighting, memory compression and consolidation, cross-agent memory sharing, and anti-patterns like…
Skill Claude CodeCodex
Use when designing or reviewing multi-agent systems — covers orchestration topologies (hierarchical, flat, pipeline, hybrid), task decomposition, parallel fan-out/fan-in execution, result aggregation, shared context propagation, agent communication protocols, failure handling, token economics, and anti-patterns with…
Skill Claude CodeCodex
Use when designing or reviewing AI agents that must assess their own output quality — covers confidence scoring and calibration, chain-of-thought reflection, LLM-as-judge, hallucination self-detection, output quality verification, eval-driven development, and self-evaluation anti-patterns with examples in TypeScript…
Skill Claude CodeCodex
Use when designing multi-agent systems that must share consistent rules, values, and constraints across all agents — covers layered inheritance models, the CLAUDE.md pattern, override resolution, consistency enforcement, value propagation in parallel agents, conflict detection, and anti-patterns with TypeScript and…
Skill Claude CodeCodex
Use when designing or reviewing AI agent systems for cost and latency efficiency — covers context engineering (write/select/compress/isolate), prompt caching strategies, model routing by complexity, token budget management, context window techniques, prompt compression, and anti-patterns with TypeScript and Python…
Skill Claude CodeCodex
Use when reviewing LLM/AI-generated code — covers hallucinated APIs, plausible-but-wrong logic, authorization gaps, shallow error handling, over-abstraction, copy-paste context mismatch, missing edge cases, and outdated patterns with detection strategies and before/after examples in TypeScript, Python, and Go.
Skill Claude CodeCodex
Use when designing or reviewing AI/ML integration code — covers RAG pipeline design, prompt engineering, structured output with schema validation, tool use/function calling, LLM error handling, token budget management, hallucination mitigation, and AI/ML anti-patterns with examples in TypeScript and Python.
Skill Claude CodeCodex
Use when reviewing architecture or design for structural problems, when a codebase is hard to change or extend, when onboarding to a legacy system, or when recurring bugs suggest a deeper design flaw.
Skill Claude CodeCodex
Use when designing or reviewing rate limiting implementations — covers Token Bucket, Leaky Bucket, Sliding Window Counter, Fixed Window Counter, distributed Redis-based limiting with Lua scripts, response headers, client-side throttling/backoff, and anti-patterns across TypeScript, Go, Python, and Redis Lua.
Skill Claude CodeCodex
Use when reviewing code for architectural boundary violations, dependency direction errors, or layer coupling issues — covers 10 architectural patterns with invariants, violation signals, and dependency diagrams.
Skill Claude CodeCodex
Use when reviewing or implementing authentication and authorization — covers OAuth2 grant flows (Authorization Code + PKCE, Client Credentials, Device Flow), OpenID Connect (OIDC) and ID tokens, JWT best practices, RBAC and ABAC policy design, service-to-service authentication (mTLS, workload identity, API keys)…
Skill Claude CodeCodex
Use when designing or reviewing batch processing systems — covers distributed locking for exclusive job execution, idempotent checkpoint/resume, heartbeat-based dead job detection, job scheduling strategies, graceful shutdown, retry and DLQ for failed items, batch size optimization, and common anti-patterns across…
Skill Claude CodeCodex
Use when designing or reviewing caching layers — covers cache-aside/read-through/write-through/write-behind patterns, cache stampede and thundering herd prevention, CDN caching with Cache-Control headers, eviction policies (LRU/LFU/TTL/adaptive), multi-layer cache architecture, cache invalidation strategies, and…
Skill Claude CodeCodex needs its repo
Use when designing or reviewing CI/CD pipelines — covers pipeline design (stages, jobs, parallelism), GitOps and IaC patterns, build optimization (caching, incremental builds, artifact management), deployment strategies (blue-green, canary, rolling update, recreate), security in pipelines (SLSA, SBOM, supply chain…
Skill Claude CodeCodex needs its repo
Use when writing or reviewing documentation — covers Architecture Decision Records (ADR), API documentation (OpenAPI/AsyncAPI/JSDoc/docstrings), README and runbook standards, inline comments, technical debt registers, and documentation anti-patterns with concrete examples and red flags across TypeScript, Python, Java…
Skill Claude CodeCodex
Use when reviewing code for concurrency correctness — covers Race Conditions, Deadlocks, Thread Safety, Immutable Data, Producer-Consumer, Actor Model, Thread Pool, Async/Await pitfalls, Read-Write Locks, and Compare-and-Swap with red flags and fix strategies across TypeScript, Java, Go, and Python.
Skill Claude CodeCodex
Use when designing, reviewing, or debugging Kubernetes workloads — covers health probe design, resource requests vs limits, autoscaling (HPA/KEDA/VPA), PodDisruptionBudget and graceful shutdown, workload RBAC isolation, configuration injection, and container anti-patterns (CrashLoopBackOff, OOMKilled, Pending, fat…
Skill Claude CodeCodex
Use when reviewing C++ code — covers memory management and RAII, undefined behavior traps, template pitfalls, const correctness, move semantics, and common anti-patterns. C++ demands a specialized review lens because manual memory, implicit conversions, and template metaprogramming create failure modes invisible to…
Skill Claude CodeCodex
Universal code review patterns that apply across all languages. Use this skill when reviewing code regardless of the implementation language — covers naming clarity, complexity thresholds, dependency direction, test quality, error handling, and documentation. Load alongside a language-specific skill…
Skill Claude CodeCodex
Use when reviewing or designing data pipelines — covers ETL vs ELT, batch vs streaming vs micro-batch selection, idempotency, exactly-once delivery, watermarking, checkpointing, dead letter queues, backpressure, schema evolution, data contracts, pipeline orchestration and DAG design, with anti-patterns and red flags…
Skill Claude CodeCodex
Use when reviewing code for data validation correctness — covers validation boundary principle, TypeScript (Zod, Joi, io-ts), Python (Pydantic v2, marshmallow, dataclasses), Go (go-playground/validator), Java (Bean Validation / Hibernate Validator), schema evolution and compatibility, coercion vs strict parsing…
Skill Claude CodeCodex
Use when reviewing a PR that touches database queries, ORM usage, schema migrations, or data access layers, or when diagnosing slow queries, data integrity failures, or connection issues in production.
Skill Claude CodeCodex
Use when reviewing code for dependency coupling problems or module organisation issues — covers 6 DI patterns (Constructor, Property, Method, Interface, Service Locator, DI Container), Composition Root, Module/Package organisation, and a catalogue of DI anti-patterns with multi-language examples.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: