Grok Companion
claudeLocal Grok CLI delegation: task, review, resumable history, best-of-n tournaments, background jobs, stats, and setup health checks.
11 skills · 2 agents · hooks
Multi-model orchestration: tier agents, routing rules, blind panel, ultra fleet, model config, and drift doctor.
Plugin fusion from marketplace claude-code-fusion in okisdev/claude-code-fusion. Commands read from the repo's manifest — yesterday.
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.
configConfigures model defaults, capability scores, breadth engine selection, and orchestration posture across Claude, Codex, Grok, Cursor, and Devin. Use when changing model defaults, capability scores, lane SKUs, breadth selection, or execution posture after the model lineup changes.
doctorAudits the orchestration setup without changes for model drift, stale pins, and environment overrides. Use when routing behaves oddly, after a CLI upgrade, or when model drift is suspected.
panelConvenes a blind Codex and Grok panel on one neutral brief, seats the breadth engine for a missing track, and adjudicates the verdicts.
setupInstalls or updates the orchestration rules in ~/.claude and checks the optional permission allow. Use on first install or after a plugin update changes the rules template.
smokeRuns a four probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
statsAggregates delegation statistics and records semantic acceptance. Use after collecting and verifying a delegated result to record it as accepted or rejected, or when asked how the lanes are performing.
ultraFans the work out as a fleet of parallel Codex, Grok, and breadth engine agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit as
claude-workerClaude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fall
deep-reasonerRead only advisory lane on Fable at maximum effort. Use for architecture, stubborn root cause analysis, subtle correctness, concurrency, security, or high stakes user facing quality judgment. It recommends and challenges; the main session decides, implements through another lane, and owns acceptance
job-collectorInternal forwarder that collects one detached peer companion job from a validated engine and job id, dispatched by the orchestrator instead of polling companion state in the main loop. Not for general work.
trivial-workerFallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and co
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/rules-sync.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/breaker-check.mjs"
echo 'Context was compacted. In one line, restate the execution posture and every in-flight Fusion task still owed collection, verification, or settlement. [fusion:9902]'
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fleet-posture.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/brief-sensor.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-hook.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
command -v node >/dev/null 2>&1 || exit 0; node "${CLAUDE_PLUGIN_ROOT}/scripts/worker-lifecycle.mjs"
Local Grok CLI delegation: task, review, resumable history, best-of-n tournaments, background jobs, stats, and setup health checks.
11 skills · 2 agents · hooks
First party local Codex CLI delegation for tasks, reviews, resumable threads, and durable background jobs.
11 skills · 1 agent · hooks
Local Cursor Agent CLI delegation: multi family consults, Composer implementation in owned worktrees, review, resumable history, background jobs, and setup health checks.
10 skills · 1 agent · hooks
Local Devin CLI delegation: multi family consults, SWE implementation in owned worktrees, review, resumable history, background jobs, and setup health checks.
10 skills · 1 agent · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
14 skills · 1 command
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
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.