claude

grok

Orchestrate Grok Build from Claude Code: rescue, plan, design, workflows, reviews, babysit, media, and documents.

8 on GitHubby stdevMacv0.5.7Apache-2.0updated 3 months ago
/

Plugin grok from marketplace grok-in-claude in stdevMac/grok-in-claude. 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 (5)

  • grok-brand-media

    Prompt recipes for Grok image/video generation from Claude Code (OG images, README banners, launch clips)

  • grok-cli-runtime

    Internal helper contract for calling the grok-companion runtime from Claude Code

  • grok-prompting

    Internal guidance for composing clear Grok task prompts from Claude Code rescue handoffs

  • grok-routing

    When Claude Code should delegate to Grok vs handle work itself

  • grok-workflows

    When and how to run Grok Rhai multi-agent workflows from Claude Code

Slash commands (17)

  • /grok:adversarial-review

    Steerable adversarial Grok review that challenges design and tradeoffs

  • /grok:babysit

    Watch PRs and fix CI/review issues via Grok pr-babysit skill

  • /grok:cancel

    Cancel an active background Grok job

  • /grok:design

    Run Grok design skill (writer/reviewer loop → design doc + PR plan)

  • /grok:document

    Generate docx/pdf/pptx via Grok document skills

  • /grok:execute-plan

    Execute a design-doc PR Plan DAG via Grok execute-plan skill

  • /grok:image

    Generate or edit images with Grok (companion copies into .grok-media/image)

  • /grok:plan

    Produce an implementation plan via Grok plan mode (read-only except plan.md)

  • /grok:rescue

    Delegate investigation, fixes, best-of-N, or worktree-isolated work to the Grok rescue subagent (supports parallel agents)

  • /grok:result

    Show the stored final output for a finished Grok job

  • /grok:review

    Run a structured read-only Grok code review (working tree, branch, or PR); may run in parallel with other Grok agents

  • /grok:sessions

    List, search, or export Grok sessions for this workspace

  • /grok:setup

    Check whether the Grok CLI is ready and optionally toggle the stop-time review gate

  • /grok:status

    Show active and recent Grok jobs with live progress when available

  • /grok:transfer

    Locate the latest Claude Code transcript and prepare a handoff into Grok

  • /grok:video

    Generate short videos with Grok from prompts, images, or references

  • /grok:workflow

    List or run Grok Rhai multi-agent workflows

Subagents (9)

  • grok-babysit

    Proactively use to watch PRs, fix CI failures, and address review comments via Grok pr-babysit.

  • grok-design

    Proactively use for architecture/design docs with consensus review (Grok /design skill). Prefer before large multi-PR work.

  • grok-document

    Proactively use to generate Word/PDF/PowerPoint documents via Grok docx/pdf/pptx skills.

  • grok-execute

    Proactively use to execute a design-doc PR Plan DAG via Grok execute-plan (worktrees, reviews, stack). Mutates git.

  • grok-media

    Proactively use for Grok image or video generation. Safe to run multiple media agents in parallel and alongside rescue/review jobs.

  • grok-plan

    Proactively use when Claude Code needs an implementation plan before coding, ambiguous multi-file design approach, or plan-mode exploration. Read-only for product code (plan.md only).

  • grok-rescue

    Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs deeper root-cause investigation, best-of-N alternatives, worktree-isolated edits, or should hand a substantial coding task to Grok. Safe to spawn multiple instances in parallel for independent workstrea

  • grok-review

    Proactively use for structured or adversarial Grok code reviews (working tree, branch, or PR). Safe to run in parallel with rescue/media agents. Read-only — never apply fixes.

  • grok-workflow

    Proactively use when running or listing Grok Rhai multi-agent workflows (fan-out review, deterministic pipelines).

Hooks (1)

  • Stop

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

View source on GitHub

Similar plugins

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

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

headroom-skill

claude

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

agentic-awesome-skills

claudecodex

Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.

200 skills

sickn33/agentic-awesome-skills 49,620

context-mode

claudecodex

Context window saver for 10 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.

3 skills · 1 MCP server

mksglu/context-mode 34,004

Maintain grok?

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