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 VasiHemanth/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/vasihemanth/grok-build-plugin/grok-runtime)<a href="https://agentmods.dev/skills/vasihemanth/grok-build-plugin/grok-runtime"><img src="https://agentmods.dev/badge/skills/vasihemanth/grok-build-plugin/grok-runtime.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00904 |
| Opus 5 | $0.00019 | $0.00452 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
grok-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok companion runtime
The Grok plugin wraps the local grok CLI's headless mode (grok -p "<prompt>" --output-format json). Grok manages its own session store under ~/.grok/sessions, so the plugin does not run a separate server or broker.
Always invoke through the companion script so job tracking, prompt shaping, and tool filtering stay consistent:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" <subcommand> [flags] [text]
Or, for live search from any MCP-capable agent, call the grok_search tool (auto-wired when the plugin is installed; otherwise npx -y grok-build-x-search-mcp).
When to use Grok (routing guidance for host agents)
| Need | Prefer |
|---|---|
| Live X sentiment, breaking news, "what are people saying" | grok_search / /grok:search |
| Current package/version/docs facts beyond training cutoff | grok_search / /grok:search |
| Second opinion code review on a diff | /grok:review |
| Substantial implement/debug pass with write access | /grok:rescue or grok:grok-rescue subagent |
| Trivial local edit the host can do in one step | Do not delegate — handle inline |
Subcommands
| Subcommand | Purpose | Tool surface |
|---|---|---|
setup [--json] |
Check install + login (no API call) | none |
review [--base <ref>] [--background] [--model <m>] [focus] |
Read-only code review of a git diff | denylist of write/shell/MCP/media; --sandbox read-only |
task <text> [--background] [--resume-last|--fresh] [--read-only] [--model <m>] [--effort <low|medium|high>] |
Delegate work; write-capable by default | full (or read-only with --read-only) |
search <query> [--background] [--model <m>] |
Live X/web search | same safe profile as review (web tools kept) |
status [--job <id>] |
List or show jobs | n/a |
result [--job <id>] |
Final output + Grok session id | n/a |
cancel [--job <id>] |
Cancel a running job | n/a |
Tool filtering note (CLI bug)
On grok-cli 0.2.x, grok -p ... --tools <allowlist> often fails session creation when web tools or shell are involved (Requirements unsatisfied / run_terminal_cmd / auto_background_on_timeout). This plugin never uses --tools for search/review; it uses --disallowed-tools + --sandbox read-only + --no-subagents, and disables vendor MCP imports in the child env to prevent recursive grok_search fork-bombs.
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.
- 7d ago First seen · 53 lines · 38 tokens per session scan A b4ce7a339d80
grok-runtime is a skill published in the GitHub repository VasiHemanth/grok-build-plugin (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 904 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
work
Execute spec.json (plan mode) or review.findings.json (fix-findings mode) by dispatching subagents per chunk. Triggers on "work on", "implement", "execute plan", "carry on", "continue".
astronomer-airflow
Work with Airflow 3.x on Astronomer. Start/stop, create/trigger DAGs, read logs, run tests. Triggers on "astro", "airflow", "start airflow", "trigger dag", "dag logs".
debug
Debug issues with iterative fix loop. Gathers problem description, investigates, then enters fix-verify cycle. Triggers on "debug", "fix this", "troubleshoot". Use when the goal is to fix a specific reported issue. For exploration or new features, use brainstorm or plan-creation.
e2e
Add durable end-to-end tests for user/API-visible behavior. Detect or scaffold the E2E framework, write tests, run the app, and store evidence. Use for E2E, Playwright/Cypress, regression tests, or quality gates. Not exploratory QA.
review
Review branch changes against Archcore docs, or report project health. Use for 'review my branch', 'review the changes before merge', 'show status', 'documentation gaps', 'check if docs match code', 'close out the feature', 'ship the feature and close it out', or after a staleness warning. --drift for staleness…