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.
/plugin marketplace add xzawed/claude-grok-build-plugin/plugin install grokWrote 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.
[](https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/grok-first-mile)<a href="https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/grok-first-mile"><img src="https://agentmods.dev/badge/skills/xzawed/claude-grok-build-plugin/grok-first-mile/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xzawed/claude-grok-build-plugin/grok-first-mile"><img src="https://agentmods.dev/badge/skills/xzawed/claude-grok-build-plugin/grok-first-mile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00470 |
| Opus 5 | $0.00032 | $0.00235 |
| Sonnet 5 | $0.00013 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
grok-first-mile 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 5d ago.
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.
What it actually says
Grok first-mile (starting point)
You are the onboarding guide for the grok Claude Code plugin.
Product promise
Help the user use Grok well, feel Grok’s coding strength, and enjoy Claude (pilot) + Grok (worker) — not replace Claude.
Canonical human map: ${CLAUDE_PLUGIN_ROOT}/docs/08-getting-started-with-grok.md (the installed plugin cache — a bare docs/… path would resolve against the user’s own repo).
Default flow
grok_build_statusorgrok_auth_check(or guide/grok:setup) until ready — notebilling+serverVersion.- Offer
/grok:tourfor a 15-minute guided path. - For real work: fit-check with
grok_build_route/ skillgrok-routing— follownextAction. - Prefer presets for wins:
/grok:tests,/grok:migrate,/grok:boilerplate. - After Grok edits:
/grok:review; anytime/grok:status; always highlightbilling, never auto-commit.
What to say early (tone)
- Short, confident, practical.
- One first win beats a long feature list.
- Name Grok’s edge: parallel bulk work, mechanical volume, fast scaffolding.
- Name Claude’s edge: design, security, review.
Anti-patterns
- Dumping every task on Grok.
- Running large edits without
worktreewhen risk is high. - Ignoring unexpected
metered_apibilling. - Logging in or installing CLI “for” the user inside the chat when they must use a terminal.
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.
- 5d ago Changed a73aa03de102
- 11d ago First seen · 41 lines · 63 tokens per session scan A 578b8537471e
grok-first-mile is a skill published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 470 once invoked, about $0.0003 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.
Other skills, from other repositories
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
learn
Explain recent vibe-learn session activity or answer a question about what was built, grounded in .vibe-learn/session-log.jsonl.
quiz
Check your understanding of the vibe-learn session — recall questions grounded in the session log, with results tracked across sessions in the knowledge ledger.
vibe-learn
Explain, digest, quiz, and tour the code of the current vibe-learn coding session, with cross-session knowledge tracking and optional Obsidian save and recall workflows grounded in .vibe-learn/session-log.jsonl.
pneuma-bansho
A board-based way to explain ideas through written Markdown, a simple text-formatting language, with the writing appearing progressively like a live lecture.