> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nika.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Nika with Grok Build

> Grok reads the Claude Code kit natively: two commands install the full Nika plugin (skills, subagents, commands, hooks, oracle) · zero commands on a machine that already runs it in Claude Code.

Grok Build reads Claude Code marketplaces, plugins, skills, MCPs, agents,
hooks and instruction files natively (per xAI's own compatibility contract),
so the Nika kit installs unported. Binary first
(`brew install supernovae-st/tap/nika` ·
[other paths](/getting-started/installation)):

```sh theme={"system"}
grok plugin marketplace add supernovae-st/nika-plugins
grok plugin install nika@nika --trust
```

`--trust` is load-bearing, not ceremony: without it grok refuses the install
outright (plugins can run hooks, MCP servers and skills on your machine),
and even a later trust grant is what activates the plugin's hooks and MCP.

## Zero-config on a Claude Code machine

If the machine already runs the Nika plugin in Claude Code, grok picks up
the marketplace and the components from the Claude surfaces on its own ·
components dedup by name and a grok-side install takes priority. Verified
live: adding the marketplace answered `already configured` before we ever
taught grok about it.

## What loads (verified live 2026-08-02 · grok 0.2.117 · nika 0.107.0)

* the 4 skills (authoring · debugging · operating · migration)
* the 6 `/nika:*` commands (check · explain · new · trace · permits · doctor)
* the 3 subagents (`nika:nika-author` · `nika:nika-debugger` · `nika:nika-migrator`)
* the hook file (session map · check-on-edit · guard-run · claude dialect,
  registered as a unit)
* the read-only MCP oracle (9 tools · no execution by design)

## Prove it (deterministic · no model call · CI-able)

```sh theme={"system"}
grok inspect --json      # every component with its origin (the nika plugin path)
grok mcp doctor --json   # nika: command found · server started · handshake OK · 9 tools discovered
```

Trust those two outputs, not a model's enumeration · `inspect` names each
loaded skill, agent, hook and MCP server with the file it came from.

## Optional native presence

The project `.mcp.json` that ships with the kit is read natively. For a
machine-level stanza in grok's own dialect:

```toml theme={"system"}
# ~/.grok/config.toml
[mcp_servers.nika]
command = "nika"
args = ["mcp"]
```

## Caveats worth knowing

* Plugins stay OFF until enabled, and a plugin's hooks and MCP stay inactive
  until trusted · the refusal message teaches the exact re-run.
* Enterprise deployments can require pinned-commit installs
  (`require_sha`) · release tags satisfy it.
* Grok enforces version floors at startup · pin deliberately in CI.

Then `nika init` in the repo · the agent-teaching surface (`AGENTS.md`, the
`.agents/skills` authoring skill, editor wiring) is read natively and is
what makes the oracle useful ([agents guide](/getting-started/agents)).