oh-my-customcodex

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

Multi-angle release quality verification using parallel expert review teams

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.

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

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

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

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

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

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

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

On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustomcodex: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.

Enable/disable OpenTelemetry console monitoring for GPT Codex + OMX usage tracking

Analyze GitHub issues against the 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.

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

Full R017 verification with cost-aware 5+3 rounds before commit

Analyze external URL to evaluate fit with oh-my-customcodex project and auto-create GitHub issue with verdict

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

Audit and tune Claude/Codex settings for lower token usage without changing code

Full R017 verification with cost-aware 5+3 rounds before commit

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

Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.

Create a new agent with complete structure

Fix broken agent references and symlinks

Save current session context to native memory plus omx-memory or AgentMemory-compatible backends

Publish package to npm registry with pre-checks

Manage semantic versions for npm packages

Apply bundle size optimizations

Sync documentation with project structure

Update agents from external sources (GitHub, docs, etc.)

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

CVE triage workflow for vulnerability analysis, reproduction assessment, and patch verification

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

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

Advisory model escalation based on task outcome tracking

Parallel code verification using multiple models with severity classification

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

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