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 LovelaceLoom/grok-plugin-cc/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/commands/lovelaceloom/grok-plugin-cc/fan-out)<a href="https://agentmods.dev/commands/lovelaceloom/grok-plugin-cc/fan-out"><img src="https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/fan-out/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/commands/lovelaceloom/grok-plugin-cc/fan-out"><img src="https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/fan-out.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 | $0.00019 | $0.00603 |
| Opus 5 | $0.00010 | $0.00302 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
fan-out 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 9d 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
Fan a task out across several parallel Grok calls — one per expert angle — then run a synthesis call that reconciles them into one consolidated answer (a section per angle plus a ## Consolidated verdict). This is the "use Grok in many directions in one shot" command: it makes N+1 real Grok calls (the angles run concurrently), so it covers far more ground and depth than a plain /grok:ask.
How it works:
- Default angles:
researcher,reviewer,security-auditor,test-writer. Grok analyzes the task as each specialist would, then synthesizes the findings. --personas a,b,c: pick a subset of built-in angle names (researcher,reviewer,security-auditor,test-writer,implementer,design-doc-writer,design-doc-reviewer).--agents-json '<json>': name custom angles via a JSON array (advanced). Each object needs aname; the plugin validates a safety envelope and uses the names as analysis lenses.- Read-only by default.
--writeopens it up for change-making runs and requiresGROK_PLUGIN_ALLOW_WRITE=1in the environment. - Web-fetch grounding is on by default (pass
--no-web-fetchto opt out).
Note: the plugin orchestrates the parallelism itself (separate grok -p calls), rather than relying on Grok's internal subagent dispatch — that proved unreliable headless. So each angle is a genuine independent Grok analysis, and they run at the same time.
Raw user input:
$ARGUMENTS
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" fan-out "$ARGUMENTS"
Output rules:
- Return the companion's stdout verbatim — it is Grok's consolidated, multi-angle report. Do not paraphrase or re-summarize.
- If stderr contains a
[hint: ...]line about auth, surface it and suggest/grok:setup. - If
$ARGUMENTSis empty, ask the user what they want Grok to analyze instead of running the command. - Fan-out spawns several child sessions, so it costs more tokens and runs longer than
/grok:ask. Prefer it for substantial, multi-faceted tasks (audits, design reviews, "find everything wrong with X").
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.
- 9d ago First seen · 33 lines · 19 tokens per session scan A 34618b70e377
fan-out is a command published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 603 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.
Other commands, from other repositories
plan
Project spec (no args) or feature FRD (with args).
debug
Structured debugging with parallel investigation agents.
review
Multi-agent code review with parallel validation.
gemini-brainstorm-on
Re-enable Gemini grounding on every prompt (it is on by default; this only matters if you previously turned it off).
gemini-challenge
Get Gemini to argue against a decision or propose alternatives.
gemini-research
Research a topic using Gemini's search-grounded or deep research capabilities.