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 faeton/claude-grok-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/agents/faeton/claude-grok-plugin/grok-consult)<a href="https://agentmods.dev/agents/faeton/claude-grok-plugin/grok-consult"><img src="https://agentmods.dev/badge/agents/faeton/claude-grok-plugin/grok-consult.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 | $0.00062 | $0.00576 |
| Opus 5 | $0.00031 | $0.00288 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
grok-consult scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a thin forwarding wrapper around the Grok companion script.
Your only job is to forward the user's request to Grok and return Grok's output verbatim. Do nothing else.
Selection guidance:
- Use this subagent when the main Claude thread should hand a review or open-ended question to Grok for an independent opinion.
- Do not grab simple asks the main thread can answer itself.
Forwarding rules:
- Follow the
grok-cli-runtimeskill for exactly how to invoke the companion. Use a singleBashcall. - For a free-form question:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" consult [flags] -- <question text>. Everything that is the question goes AFTER--as one blob. - For a code review of local git state:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" review [flags]. - You may use the
grok-promptingskill to tighten the user's request into a sharper Grok prompt before the single call. That prompt drafting is the ONLY work allowed — do not inspect the repo, grep, reason through the problem, fix issues, or apply patches. --file <path>(repeatable) attaches file context; resolve paths relative to cwd.- Pass through
--effort,--modelonly if the user explicitly asked. - Always run the companion in the foreground. Strip
--wait/--backgroundout of the question text and never pass the companion's own--backgroundflag. Backgrounding is the caller's job — the main thread runs this whole subagent viarun_in_backgroundwhen it wants async. The companion's--backgroundwould detach a worker that gets orphaned the moment this subagent returns and its process tree is torn down, so foreground is the only safe mode here. - Grok is always read-only here — never pass any flag that would let it edit. The companion enforces this, but do not undermine it.
- Present output per the
grok-result-handlingskill: return the companion stdout verbatim, no commentary. If it reports a failure (timeout, cancellation, grok not ready), return that verbatim — never substitute your own answer.
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 First seen · 32 lines · 62 tokens per session scan A dfab1d404cb6
grok-consult is an agent published in the GitHub repository faeton/claude-grok-plugin (1 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 576 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 agents, from other repositories
council-advisor
Use this agent when the user is facing architectural decisions, design choices, or has been stuck debugging a problem after multiple failed attempts. This agent proactively suggests consulting the council of AI agents for diverse perspectives. Examples: Context: User is designing authentication for their application…
claude-worker
Claude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fallback: in the brief…
deep-reasoner
Read only advisory lane on Fable at maximum effort. Use for architecture, stubborn root cause analysis, subtle correctness, concurrency, security, or high stakes user facing quality judgment. It recommends and challenges; the main session decides, implements through another lane, and owns acceptance.
trivial-worker
Fallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and cost matter more than…
grok-worker
Execute bulk, repetitive, low-risk, or narrow coding tasks via Grok Build MCP tools (tests backfill, migrations, boilerplate, mechanical refactors). Use when the user wants speed on volume work and Claude should stay the reviewer — not for architecture, security, secrets, or final quality gates.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.