agentmods.dev

tour

tour is a command for Claude Code from xzawed/claude-grok-build-plugin. It costs 13 tokens per session (901 once invoked), scanned A, original, MIT.

A guided 15-minute tour for checking whether the Grok plugin is ready and demonstrating a small delegation. Grok is treated as a worker while Claude remains the coordinator.

In plain words
What is it for?
It is for checking readiness, explaining subscription billing, running a no-edit routing demonstration, and showing where to find setup, testing, migration, boilerplate, and routing guidance.
Why use it?
It explains the authentication and billing status before use and keeps the demonstration from making destructive changes or committing files automatically.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server shipped together

not rated 1repo changed yesterday A scan 13 tokens original MIT

Good fit It is for checking readiness, explaining subscription billing, running a no-edit routing demonstration, and showing where to find setup, testing, migration, boilerplate, and routing guidance.

Compare 6 commands from other repositories ↓
View source ↗ xzawed/claude-grok-build-plugin
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add xzawed/claude-grok-build-plugin
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tour

README.md
[![agentmods](https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/tour.svg)](https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/tour)
Your own site
<a href="https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/tour"><img src="https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/tour.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00901
Opus 5 $0.00006 $0.00451
Sonnet 5 $0.00003 $0.00180
Haiku 4.5 $0.00001 $0.00090

Measured yesterday against content hash c1f274cc9313, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tour scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/tour.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the Grok starting-point tour for this Claude Code plugin. Goal: the user finishes with (1) auth ready, (2) one successful subscription-billed delegation if they allow it, (3) a clear sense of when to use Grok next.

Do not skip safety: no auto-commit, no destructive bulk work, no forcing API billing.

Step 1 — Ready?

Prefer grok_build_status (or grok_auth_check if status is unavailable).

  • If ready: false / ok: false: show the message and stop with exact fix steps. Offer /grok:setup. Do not invent install paths beyond the message.
  • If ready: report mode, expected billing, serverVersion, and continue.

Step 2 — Explain the deal (short)

In 3–5 bullets, tell the user:

  • Claude stays the orchestrator; Grok is the worker for bulk/low-risk/narrow work.
  • Every run reports billing — they should want subscription if on SuperGrok / Premium+.
  • Grok edits files but never auto-commits; they review diffs.
  • Full human map: point to ${CLAUDE_PLUGIN_ROOT}/docs/08-getting-started-with-grok.md if present, or summarize /grok:tests, /grok:migrate, /grok:boilerplate, /grok:route.

Step 3 — Route demo (no edits)

Call grok_build_route with a sample task, e.g.
task: "backfill unit tests for the parser module"
Show risk, worker, reasons, suggestedTool, and nextAction.
Explain: this tool never bills or edits.

Step 4 — First win (ask permission)

Ask whether to run a tiny sample in a throwaway absolute cwd they approve (or their current project only if they explicitly accept).

If yes:

  1. grok_build_delegate with English prompt:
    Create a file grok-tour-hello.txt containing exactly: ok
  2. If status is not completed (auth_error, timeout, or grok_error), show the returned message and stop — do not report the run as done; filesChanged may still list partial edits. Otherwise show summary, filesChanged, and billing in bold. ⚠️ filesChanged is a git diff, so outside a git repository it is always empty even though the file was written. Run the tour in a git init-ed directory, or say plainly that the list is empty for that reason and point at the file itself.
  3. If billing is metered_api and they expected subscription, tell them the server is running with GROK_BUILD_AUTH_MODE=api — that setting alone decides the tag (subscription mode strips the API-key vars, so a shell key cannot cause it).
  4. Remind: review then delete the sample file or commit themselves — you do not commit.

Read the full file on GitHub · 75 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · +3 lines c1f274cc9313
  2. 2d ago Changed · +2 lines 3835b93f288f
  3. 7d ago First seen · 70 lines · 13 tokens per session scan A 1f2f17dca8ad

Subscribe to this mod's changes

tour is a command published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 901 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude Codeai-coding-assistantclaude-code-plugindeveloper-toolsgrokmcp
Related

Other commands, from other repositories

merge

Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.

azrtydxb/procoder · 23 tokens

pr

Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.

azrtydxb/procoder · 20 tokens

spec

Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.

azrtydxb/procoder · 31 tokens

copilot-leak

Copilot's auto-review escapes: find them since the last look, sanitise them, and turn each one into a lesson.

azrtydxb/procoder · 26 tokens

docs

The documentation report: references, diagrams, drift, API docs, badges, README structure, links, Pages.

azrtydxb/procoder · 22 tokens

plan

Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.

azrtydxb/procoder · 27 tokens