second-brain

Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline

Full Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.

On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.

hada.io RSS feed monitoring for AI agent/harness articles with automated /scout analysis

Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts

Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile

Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation

Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached

Apache Airflow best practices for DAG authoring, testing, and production deployment

Analyze project and auto-configure agents, skills, rules, and guides

AWS patterns from Well-Architected Framework

Monitor Claude Code releases and auto-generate GitHub issues for each new version

Execute OpenAI Codex CLI prompts and return results

YAML-based DAG workflow engine with topological execution and failure strategies

dbt best practices for SQL modeling, testing, and analytics engineering workflows

Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.

Research-validated planning — research → plan → verify cycle for high-confidence implementation plans

Multi-angle release quality verification using parallel expert review teams

Routes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.

Review code against language-specific best practices

Django patterns for production-ready Python web applications

Docker patterns for optimized containerization

Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics

Flutter/Dart development best practices for widget composition, state management, and performance

Execute Gemini CLI prompts and return results

Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research

Show help information for commands and system

Automatically detect user intent and route to appropriate agent

Modern Java 21 patterns from Virtual Threads, Pattern Matching, Records, and Sealed Classes

Apache Kafka best practices for event streaming, topic design, and producer-consumer patterns

Show all available commands

Memory persistence operations using claude-mem

Search and recall memories from claude-mem

Save current session context to claude-mem

Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking

Parallel code verification using multiple models with severity classification

Apply verified improvement suggestions from eval-core analysis to omcustom configuration

Submit feedback about oh-my-customcode (supports anonymous submission)

Read-only report of improvement suggestions from eval-core analysis engine

Prevent session idle during background agent work via SubagentStop prompt hook auto-continuation