oh-my-customcode

Full R017 verification (5+3 rounds) before commit

Load a skill profile to switch active plugin set. Use when user wants to focus on a specific workflow (web-app/data-eng/harness-dev/minimal) and reduce skill enumeration block size per

6-stage structured development cycle with stage-based tool restrictions

Deploy applications to Vercel with auto-detection and preview URLs

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

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

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

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

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

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

Quantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).

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

Docker patterns for optimized containerization

hada.io RSS feed monitoring with LLM pre-scout filtering for oh-my-customcode relevance

Synthesize code harnesses for agent action validation — AutoHarness-inspired verifier/filter/policy generation

Show help information for commands and system

Show all available commands

Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking

Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues

Analyze GitHub issues against current codebase and perform automated triage with priority assessment

Coordinates QA workflow across planning, writing, and execution agents. Use when user requests testing, quality assurance, or test documentation.

Template for pre-reasoning → action → post-verification model allocation

10-team parallel deep analysis with cross-verification for any topic, repository, or technology. Use when user invokes /research or asks for comprehensive research.

Aggregate parallel agent results into concise output

Multi-agent structured debate with anti-groupthink mechanisms — Devil's Advocate, minority opinion protection, 2-round hard cap. Use when divergent perspectives matter more than consensus (architecture decisions, design tradeoffs, contested specifications).

Routes agent management tasks to the correct manager agent. Use when user requests agent creation, updates, audits, git operations, or verification.

Analyze task trajectories to propose reusable SKILL.md candidates from successful patterns

Apache Spark 4.0.2 best practices for PySpark and Scala distributed data processing

Show system status and health checks

Three-layer token defense stack — audit current settings, apply safe/CI levers, and monitor status

Use the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw files

Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.