Plugin Claude Code
Bundles 1 skill, 1 MCP server · 76 tokens together
Run complex work as explicit, inspectable agent graphs with branching, joins, review gates, and human checkpoints.
Skill Claude CodeCodex
Run a single prompt across multiple LLMs in parallel via OpenRouter, then synthesize their responses into one answer with a judge model. Use when the user wants multi-model fusion, ensemble LLM queries, parallel model comparison, or a second opinion across providers.
luckeyfaraday/frontier-orchestrator
MCP server Claude Code
MCP server "frontier-orchestrator" as configured in luckeyfaraday/frontier-orchestrator. Runs ${CLAUDE_PROJECT_DIR:-.}/dist/src/index.js with node. Needs 1 environment variable to run.
Skill Claude CodeCodex
Example skill loaded from resourcesdiscover.
Plugin Claude Code
Bundles 1 skill · 113 tokens together
Route heavy-duty coding tasks from your Claude Code agent to OpenAI Codex, choosing GPT-5.6 Sol, Terra, or Luna as a supervised background worker — Claude briefs, delegates, reviews, and verifies.
MCP server Claude CodeCodexCursor +2
MCP server "master-workflow" as configured in luckeyfaraday/master-workflow. Runs locally from the . Python package.
Skill Claude Code
Orchestrate a build as orchestrator → worker → critical reviewer, delegating to Codex, Grok, OpenCode, Claude, or Kimi and looping until an independent cross-model reviewer scores the diff 9/10; for long builds with several lines of work in parallel worktrees, drive them all with the run-lines workflow. Use when the…
Skill Codex needs its repo
Use when the user wants automatic task-difficulty routing for reasoning effort only, asks to run or configure the auto-reasoning harness, wants Codex/OpenAI calls to keep the model fixed while varying reasoning depth, or asks for an auditable effort-selection workflow.
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: