Code Review & Quality for Claude Code

Drive the Pi coding agent from Claude Code — model-agnostic, works with whatever provider pi is configured for (DeepSeek, OpenAI, Anthropic, Google, Ollama, LM Studio, or any OpenAI-compatible endpoint). /pi:review with structured findings, /pi:adversarial-review for design challenges, /pi:rescue with background job control (status/result/cancel), and an optional stop-time review gate. No OAuth (API key only). 1:1 fork of openai/codex-plugin-cc with the runtime swapped from Codex to Pi.

52 security skills covering OWASP Web Top 10:2025, LLM Top 10:2025, API Security Top 10:2023, and systems-software bug classes (memory-API misuse, crypto-library wiring, privilege handling, concurrency, numeric trust-boundary), plus three review modes (PR gate, full scan, contract review). Auto-invokes on vulnerable code and rewrites it inline.

Design-system memory and UI quality tools for Claude Code.

AI writes the code. Temper makes sure it's actually ready to ship.

Inspect full Claude Code session context: CLAUDE.md files, auto-memory, and SessionStart hook output

Curated presets of coding guidelines injected into sessions on demand

Codex CLI reflector — independent critic, oracle, and metacognition layer using OpenAI Codex as second-model reviewer

功能開發工作流 — 整合 Notion 與 Claude Code，涵蓋需求分析、規格設計、DB 設計、架構設計、程式碼骨架產生、品質審查到結案的完整生命週期管理

Ralph autonomous loop + Superpowers skills: brainstorming, TDD, systematic debugging, subagent-driven development, code review, and verification workflows

Enforces strict change transparency for code, notebook, config, and command edits so every delta is disclosed, including incidental changes.

Structural codebase indexer (MCP): search_symbols, get_file_summary, find_usages, get_dependencies + passive session memory. Cuts token usage on medium-to-large codebases (break-even ~40+ files). Self-configuring, no per-project setup.

Orchestrate complete 8D investigations with integrated tool selection and domain-specific team formation guidance. Use for RCCA, root cause analysis, corrective action, failure investigation, nonconformance analysis, quality problems, or customer complaints.

Deep test, analyze, and audit Claude skills with API tracing, script I/O capture, and security/code review agents.

Expert Swift and SwiftUI guidance for state management, navigation, testing, dependency injection, performance optimization, and code quality patterns.

Fetch npm package source code for deep implementation analysis. Use when types/docs aren't enough.

Source-backed code architecture audits, ownership topology, runtime topology, conformance and drift checks, structure metrics, ADRs, fitness functions, dependency boundaries, and refactoring strategy.

Core skills and rules: version-checker, class-builder, knowledge cutoff awareness, and strict TypeScript patterns

Search-first codebase understanding, context retrieval, mapping, pattern detection, and living project intelligence.

Safe refactoring, dead-code removal, legacy modernization, and dependency hygiene.

Multi-agent competitive simulations with 3 skills and 12 specialist agents for bug hunting, code quality, and user flow testing

Context-efficient routing: dispatch tables for workflow, review, and codebase-intelligence commands.

Dual-model code review: orchestrate two independent reviewer models over the same change set, then post the cross-referenced verdict as inline GitHub PR comments.

5 code quality enforcement hooks for maintaining standards and best practices

5 essential development safety hooks preventing common mistakes and enforcing best practices

Internal review harness, adversarial gates, and post-merge learning for coding agents

Quality enforcement: TDD discipline, code review workflows, release verification, and CI failure analysis.

Quality gates for spec-driven development: adversarial plan verification and structured code review.

Codex-backed fork of seven Superpowers workflows: brainstorming, planning, implementation, code review, debugging, TDD, and branch completion.

Comprehensive code review with dynamic multi-AI MCP integration.