Codexclaw — AI skill for Claude Code
Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search.
How to install Codexclaw
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lidge-jun/codexclaw and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Codexclaw does
Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plugin, no external harness.
Alternatives in AI
- EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
- Multi Workflow — 工作流 - 多模型协同开发 (Multi-Model Collaborative Development) 1.9k ★
- Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
README
**English** | [한국어](README.ko.md) | [中文](README.zh.md)
codexclaw
Development discipline and multi-model subagents for OpenAI Codex,
packaged as a single plugin.
Workflow inspiration: [OMO / oh-my-openagent](https://github.com/code-yeongyu/oh-my-openagent). Some components are adapted from historical MIT-licensed LazyCodex/OMO; [credits, pinned sources and modifications](NOTICE.md). CodexClaw is a separate, unofficial project.
codexclaw turns the Codex runtime into a disciplined development environment. It does not ship its own agent harness — it layers skills, hooks, and components directly on `codex`, adding structured workflows, coding discipline, and multi-model orchestration that the base runtime doesn't provide.
Features
**Dev Skill Family** — 12 surface-specific routers (`dev-architecture`, `dev-backend`, `dev-frontend`, `dev-testing`, `dev-security`, `dev-debugging`, `dev-data`, `dev-devops`, `dev-code-reviewer`, `dev-scaffolding`, `dev-diagram-viewer`, `dev-uiux-design`) governed by a canonical parent (`dev`). Every router inherits the parent's rule classes, verification gate, and safety rules. 155 unique rule IDs
Related Skills
Gitos
The discipline layer for AI-assisted development. gitos turns any repository into a self-driving, multi-agent
Obsidian Vault RAG Assistant
Obsidian Vault RAG Knowledge Assistant: local MiniLM embeddings + numpy retrieval, measured eval harness (reca
Claudecode Harness
Production-grade orchestration harness for Claude Code — Context discipline, subagents, and multi-model consen
Longe
A self-improving harness for any LLM, in one Rust binary. Persistent Lua REPL as the single tool, three-level
Smart Switch
Multi-app model provider switcher: manage OpenAI/Anthropic-protocol providers (base URL + API key + models) an
Multi Model Router
Route AI tasks to the best model using a single OpenAI-compatible API key. This Claude Code skill selects, con
Related Agents
Fable Orchestrator
Staged-execution orchestrator for large, multi-part, or multi-session tasks. Use when fable-mode discipline mu
Docs Dev
Owns the dbdocs package — the click CLI plus the extract/site pipeline that turns dbt artifacts into a single-
Registry Search
Single-purpose, read-only dedup helper for reducer subagents. Given a discriminating query text + a sharded re
