claude

omcx

Cross-model forge, blind TDD, adversarial stress testing, mixed-model teams, race, pipeline, and auto-chaining workflows.

2 on GitHubby jhcdevv2.0.0Apache-2.0updated 7 months ago
/

Plugin omcx from marketplace omc-codex in jhcdev/omc-codex. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (3)

  • codex-cli-runtime

    Internal helper contract for calling the codex-companion runtime from Claude Code

  • codex-result-handling

    Internal guidance for presenting Codex helper output back to the user

  • gpt-5-4-prompting

    Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin

Slash commands (16)

  • /omcx:adversarial-review

    Run a Codex review that challenges the implementation approach and design choices

  • /omcx:auto-plan

    Claude plans & executes → Codex reviews → auto-fix — works for features, fixes, refactoring, and any task needing design-first approach. Auto cross-model fallback

  • /omcx:auto-ralph

    Claude iterates until done → Codex validates — works for any task needing persistence: features, bugs, refactoring, migration. Auto Codex fallback

  • /omcx:auto-validate

    Cross-model validation: Codex reviews → Claude synthesizes — with fallback when either model is unavailable

  • /omcx:blind-test

    Blind TDD: one model writes tests/checks from spec, the other implements/fixes from those tests — works for new features, bug fixes, refactoring, and any task where independent verification matters

  • /omcx:cancel

    Cancel an active background Codex job in this repository

  • /omcx:forge

    Forge: the ultimate cross-model workflow for ANY task — plan → test → build → harden → review. Works for features, bugs, refactoring, analysis, debugging, and everything in between.

  • /omcx:pipeline

    Full autonomous pipeline for ANY task — plan → execute → verify → review → fix. Routes each phase to the best model, with automatic cross-model fallback

  • /omcx:race

    Race: N Claude agents vs M Codex agents solve the same task in parallel — compare all results, pick the best or merge strengths

  • /omcx:rescue

    Delegate quick scoped tasks to Codex — best for focused fixes, diagnosis, and targeted implementation where sandboxed speed matters

  • /omcx:result

    Show the stored final output for a finished Codex job in this repository

  • /omcx:review

    Run a Codex code review against local git state

  • /omcx:setup

    Check whether the local Codex CLI is ready and optionally toggle the stop-time review gate

  • /omcx:status

    Show active and recent Codex jobs for this repository, including review-gate status

  • /omcx:stress

    Red vs Blue: Codex challenges (adversarial tests, edge cases, attack vectors), Claude defends (fixes) — works for hardening any code, debugging, security review, and quality assurance

  • /omcx:team

    Mixed-model team: N Claude agents + M Codex agents working in parallel — each handles tasks matching its strength, cross-model review at the end

Subagents (1)

  • codex-rescue

    Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Codex through the shared runtime

Hooks (3)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/scripts/session-lifecycle-hook.mjs" SessionStart

  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT}/scripts/session-lifecycle-hook.mjs" SessionEnd

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/stop-review-gate-hook.mjs"

View source on GitHub

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

code-review

claude

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

1 command

anthropics/claude-code 155,476

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

headroom-skill

claude

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

Open Code Review

codex

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain omcx?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted