Agent
Reviews code changes for API design issues including breaking contract changes, inconsistent endpoint patterns, missing validation, incorrect status codes, versioning problems, and backwards compatibility risks. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for pattern violations, broken contracts, inconsistencies with existing codebase conventions, and architectural regressions. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for logic errors, edge cases, null handling, race conditions, incorrect assumptions, and correctness bugs. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for unnecessary complexity, duplicated logic, premature abstractions, overly clever code, and maintainability issues. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for database schema safety, migration rollback risks, data integrity issues, backwards-incompatible schema changes, and unsafe data transformations. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for prose-vs-implementation drift in non-executable artifacts: documentation files (knowledge/, docs/, ADRs, PLAN, RUNBOOK, lessons-learned, READMEs), JSDoc/TSDoc/docstrings, multi-line code comments, PR description claims, and test-file header comments. Catches stale, inaccurate, or contradictory…
Agent
Reviews code changes for missing metrics, tracing, structured logging, alerting gaps, and unobservable code paths that make production incidents hard to detect and diagnose. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for performance regressions including N+1 queries, unnecessary allocations, blocking operations, missing indexes, and inefficient algorithms. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for swallowed errors, bad fallbacks, misleading success paths, empty catch blocks, and error handling that hides problems. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for missing test coverage, broken test assumptions, untested edge cases, and test quality issues. Spawned by hardcore-code-reviewer skill.
Agent
Reviews code changes for type safety issues including unsafe type assertions, any usage, missing generic constraints, incorrect type narrowing, and type-related regressions in TypeScript or typed language code. Spawned by hardcore-code-reviewer skill.
Command
Strict hardcore code review with 13 parallel subagents (bugs, security, architecture, tests, error handling, performance, complexity, observability, API contracts, data/migrations, accessibility, type safety, doc/comment drift).
Skill Claude CodeCodex
Strict hardcore code reviewer that spawns 13 parallel subagents to find bugs, security issues, silent failures, pattern violations, test gaps, performance problems, unnecessary complexity, observability gaps, API contract issues, data/migration risks, accessibility violations, type safety issues, and doc/comment drift…
Plugin Claude Code
A persistent, indexed knowledge bank that stores learnings, ADR decisions, technical context, and session notes as markdown files inside your repo. Scales to thousands of files with fast grep-based index lookups. Integrates with Claude hooks for automatic session capture.
Command
Create a formal Architecture Decision Record (ADR) in the knowledge bank.
Command
Initialize the knowledge bank in this repo. Creates .knowledge-bank/ structure and updates CLAUDE.md.
Command
Search and retrieve entries from the knowledge bank by keyword, tag, or category.
Command
Store a learning, decision, or context note in the knowledge bank.
Skill Claude CodeCodex
Use this skill to interact with the repo's persistent knowledge bank (.knowledge-bank/). Triggers when the user says: "store this", "remember this", "save a learning", "create an ADR", "what do we know about X", "recall X", "search the knowledge bank", "initialize the knowledge bank", "kb-init", "kb-store"…
Plugin Claude Code
A plugin to automatically fix PR comments.
Command
Fix issues mentioned in Pull Request.
Skill Claude CodeCodex
Automatically read GitHub pull request review comments and apply fixes to address feedback. Use this skill when the user asks to review and fix PR comments, address PR feedback, or resolve review suggestions. Triggers include phrases like "fix PR comments", "address PR feedback", "review PR.
Plugin Claude Code
A plugin to help with shopify apps.
MCP server Claude CodeCodexCursor
A command line tool for setting up Shopify Dev MCP server. Runs locally from the @shopify/dev-mcp npm package. Needs 1 environment variable to run.