Plugin Claude Code
Bundles 48 skills, 21 commands, 19 agents, 11 hooks, 1 MCP server · 2,031 tokens together
Multi-agent orchestration system for Claude Code.
not rated 40k
+194
changed yesterday A
tokens not measured
original MIT
omx_state
02MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxstate" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve state.
not rated 34k
+52 today A
tokens not measured
original MIT
omx_memory
03MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxmemory" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve memory.
not rated 34k
+52 today A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxcodeintel" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve code-intel.
not rated 34k
+52 today A
tokens not measured
original MIT
omx_trace
05MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxtrace" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve trace.
not rated 34k
+52 today A
tokens not measured
original MIT
omx_wiki
06MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxwiki" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve wiki.
not rated 34k
+52 today A
tokens not measured
original MIT
omx_hermes
07MCP server Claude CodeCodexCursor +2
One of 6 in .mcp.json
MCP server "omxhermes" as configured in Yeachan-Heo/oh-my-codex. Launched with omx mcp-serve hermes.
not rated 34k
+52 today A
tokens not measured
original MIT
SessionStart
08Hook Claude Code
One of 7 in hooks.json
Runs when a session starts on startup, resume and clear, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
original MIT
PreToolUse
09Hook Claude Code
One of 7 in hooks.json
Runs before the agent uses a tool, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 86% MIT
PostToolUse
10Hook Claude Code
One of 7 in hooks.json
Runs after a tool call finishes, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 77% MIT
Hook Claude Code
One of 7 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 86% MIT
PreCompact
12Hook Claude Code
One of 7 in hooks.json
Runs before the context is compacted, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 84% MIT
PostCompact
13Hook Claude Code
One of 7 in hooks.json
Runs after the context is compacted, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 81% MIT
Stop
14Hook Claude Code
One of 7 in hooks.json
Runs when the agent finishes a response, executing codex-native-hook.mjs via node. From Yeachan-Heo/oh-my-codex.
not rated 34k
+52 today A
tokens not measured
copy · 77% MIT
Skill Claude CodeCodex
Run an anti-slop cleanup/refactor/deslop workflow.
not rated 34k
+52
changed 1mo ago A ✓ AI review SkillSpector: pass 17 tokens
original MIT
analyze
16Skill Claude CodeCodex
Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded cross-file explanation before any changes are proposed.
not rated 34k
+52 today A ✓ AI review SkillSpector: pass 65 tokens
original MIT
ask
17Skill Claude CodeCodex
Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact.
not rated 34k
+52 today A ✓ AI review SkillSpector: warn 18 tokens
original MIT
autopilot
18Skill Claude CodeCodex
Autopilot is the first-class canonical orchestrator for hands-off delivery. Its defining default chain is mandatory.
not rated 34k
+52 today A ✓ AI review SkillSpector: pass 28 tokens
original MIT
autoresearch
19Skill Claude CodeCodex
Stateful validator-gated research loop with native-hook persistence.
not rated 34k
+52 today A ✓ AI review SkillSpector: pass 14 tokens
original MIT
Skill Claude Code
Use this skill when a task depends on current external best practices, version-aware guidance, standards, official recommendations, or upstream behavior. This is a workflow wrapper: it routes evidence gathering and synthesis; it is not a new research authority and it does not replace researcher.
not rated 34k
+52
changed 1mo ago A ✓ AI review SkillSpector: pass 23 tokens
original MIT
cancel
21Skill Claude CodeCodex
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team).
not rated 34k
+52 today A ✓ AI review SkillSpector: pass 35 tokens
original MIT
code-review
22Skill Claude CodeCodex
Run a comprehensive code review.
not rated 34k
+52
changed 1mo ago A ✓ AI review SkillSpector: pass 8 tokens
original MIT
Skill Claude CodeCodex
Configure OMX notifications - unified entry point for all platforms.
not rated 34k
+52 today A ✓ AI review SkillSpector: pass 14 tokens
original MIT
Skill Claude Code
Socratic deep interview with mathematical ambiguity gating before execution.
not rated 34k
+52
changed 1mo ago A ✓ AI review SkillSpector: warn 14 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: