claudecodex

Grok Skills

Grok as a peer implementer for Claude Code: default integration=direct lands live-tree edits for one-shot code (no consent gate); auto/review are opt-in worktrees; ACP peer is opt-in multi-turn (always external worktree; stop-time apply). runMode direct is a separate installed-home security posture. Review, reason, setup, continue-run, and verified handoff included. See plugin/references/integration-modes.md. Not affiliated with xAI.

8 on GitHubby Stephane Fourdrinierv2.1.0MITupdated 2 months agoDevelopment & Workflow
/

Plugin grok from marketplace grok-skills in sfourdrinier/grok-skills. 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 (19)

  • adversarial-review

    Hostile Grok review that challenges design; web on by default

  • cancel

    Cancel a running Grok job

  • cleanup

    Report (dry-run) or remove a Grok run's owned session state and worktree by run id

  • code

    Have Grok implement code (default: live tree; opt-in isolated worktree). Nothing is committed or pushed

  • debate

    Bounded Grok debate: two opposing reason passes, then synthesis

  • dual-lens

    Run adversarial-review then review on the same target (dual-lens harden recipe)

  • handoff

    Read a verified implementation handoff for a completed Grok code run (runId only; no apply)

  • implement

    One-call delegate: Grok code then auto-handoff verification (verify-only; mode-aware integrate elsewhere)

  • jobs

    List recent Grok jobs for this workspace

  • peer

    ACP multi-turn peer channel (start/prompt/stop). Opt-in; engineer-coder default is one-shot code. Disable with GROK_DISABLE_ACP=1

  • preflight

    Check Grok wrapper readiness (binary, auth, sandbox, state) - no task is run

  • reason

    Get a cold, isolated Grok second opinion on named artifacts (architecture, debugging, plan critique)

  • result

    Show stored output for a finished Grok job

  • review

    Run a full-context, read-only Grok code review over a workspace path

  • setup

    Check Grok readiness and install/refresh Codex agents; optionally toggle stop gate / run mode / agents scope. Use after plugin install and when agents are missing.

  • status

    Read a Grok run by id: finished envelope, or running progress if still in progress (read-only)

  • transfer

    Package the current Claude session into a Grok task pack

  • verify

    Have Grok independently verify a change in an existing worktree (no source edits, hermetic)

  • grok-cli

    Use when the user says to use Grok, wants a Grok review, wants a second opinion from Grok, or asks to delegate a task to Grok. Also use for getting an independent code review from Grok, having Grok reason about an architecture or debugging question, having Grok implement code (live tree by default,

Subagents (2)

  • grok-engineer-coder

    Use when the user wants Grok to implement or change code (feature, bugfix, refactor, multi-file edit, or tests). Default: one-shot code in the supplied workspace. Host stays dispatcher. Prefer only when the user asked for Grok / a second implementer - not when the main thread is already mid-edit in

  • grok-rescue

    Use when stuck and need a cold Grok second opinion or root-cause diagnosis via the hardened wrapper (reason). Prefer for investigation and plan critique - not for pure implementation (use grok-engineer-coder). May run code only if the user already supplied target and base; otherwise hand implementat

Hooks (4)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/scripts/session-lifecycle-hook.mjs" SessionStart --host claude

  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/scripts/session-lifecycle-hook.mjs" SessionEnd --host claude

  • Stop

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

  • SubagentStop

    node "${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/scripts/subagent-stop-hook.mjs"

View source on GitHub

Similar plugins

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

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain Grok Skills?

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