ask

ask is a command for Claude Code from stevenc81/gemini-plugin-cc. It costs 16 tokens per session (875 once invoked), scanned A, original, Apache-2.0.

A command that sends a prompt to a Gemini language model through the Antigravity command-line tool and returns the model's answer. It can also pass files and selected command options.

In plain words
What is it for?
Use it to ask Gemini a question, select a model, attach one or more files, request JSON output, or run the request in the supported background mode.
Why use it?
It separates asking the external model from answering or editing the project directly. This helps keep the command's role limited to forwarding the prompt and returning the result.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/Bob.

Part of the gemini plugin — 3 commands shipped together

Good fit Use it to ask Gemini a question, select a model, attach one or more files, request JSON output, or run the request in the supported background mode.

Compare 6 commands from other repositories ↓
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 stevenc81/gemini-plugin-cc
Claude Code
/plugin install gemini

Made for: Claude Code.

Or install gemini, the plugin that ships this one along with the rest of its 3 commands.

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 ask

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevenc81/gemini-plugin-cc/ask/github.svg)](https://agentmods.dev/commands/stevenc81/gemini-plugin-cc/ask)
Your own site
<a href="https://agentmods.dev/commands/stevenc81/gemini-plugin-cc/ask"><img src="https://agentmods.dev/badge/commands/stevenc81/gemini-plugin-cc/ask/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.

agentmods 80×15 button for ask

Your own site · 80×15
<a href="https://agentmods.dev/commands/stevenc81/gemini-plugin-cc/ask"><img src="https://agentmods.dev/badge/commands/stevenc81/gemini-plugin-cc/ask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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 $0.00016 $0.00875
Opus 5.5 $0.00006 $0.00350
Sonnet 5.5 $0.00003 $0.00175
Haiku 4.5 $0.00002 $0.00088

Measured 1mo ago against content hash b8ebc9e84a2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ask 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 1mo 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.

plugins/gemini/commands/ask.md · 58 lines

What it actually says

Send a prompt to a model through agy --print (Antigravity CLI) and return its answer.

Raw slash-command arguments: $ARGUMENTS

Core constraint:

  • Your only job is to run the command and return its output verbatim to the user.
  • Do not answer the prompt yourself, edit files, or act on the answer.

Input handling:

  • Split the raw arguments into flags and the prompt. Flags are --model <id>, --file <path> (may repeat), --dir <folder> (may repeat), --json and --background. Everything else is the prompt.
  • --model takes any model ID from agy models. The default is gemini-3.8-flash-medium.
  • --dir gives Gemini read access to a folder, such as a source tree. It may repeat for several folders in one project. Use it instead of --file when there are many files. Do not combine --dir and --file.
  • If there is no prompt, stop and tell the user: "Nothing to ask. Add a prompt after /gemini:ask."

Building the command:

  • Do not paste $ARGUMENTS into the shell command. Build the arguments yourself.
  • Pass --json, --model <id>, each --dir <folder> and each --file <path> as their own arguments. Leave out any flag the user did not give, and leave out --background.
  • Single-quote each value, writing each ' inside it as '\''. Example: --file '/Users/me/Bob'\''s notes.md'.
  • Pass the prompt verbatim via stdin using a quoted heredoc. Do not paraphrase it.

Execution mode rules:

  • If the raw arguments include --background, run in a Claude background task.
  • Otherwise, run in the foreground.

Foreground flow:

  • Set the Bash timeout to 600000 (10 minutes). --timeout-ms 540000 gives the model 9 minutes, so a long run comes back marked as cut off before the Bash limit kills it.
  • Invoke with a quoted heredoc so the prompt is piped in literally (no shell expansion inside it):
node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" ask --timeout-ms 540000 --model 'gemini-3.8-flash-high' --file '/Users/me/Bob'\''s notes.md' <<'GEMINI_ASK_INPUT_EOF'
<the prompt, verbatim>
GEMINI_ASK_INPUT_EOF
  • Always keep --timeout-ms 540000 in the foreground.
  • Return the command's stdout verbatim, exactly as-is.
  • Do not paraphrase, summarize, or add commentary before or after it.

Background flow:

  • Launch with Bash in the background using the same heredoc form, without --timeout-ms:
Bash({
  command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" ask --model 'gemini-3.8-flash-high' --file '/Users/me/notes.md' <<'GEMINI_ASK_INPUT_EOF'
<the prompt, verbatim>
GEMINI_ASK_INPUT_EOF`,
  description: "Gemini ask",
  run_in_background: true
})
  • After launching, tell the user: "Gemini ask started in the background. You will be notified when it finishes." Then stop. If you are a subagent, do not send your final report yet: a subagent sends only one report, so a report sent now loses the ask output. You are woken when the task finishes.
  • When it finishes, return its output verbatim.
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. 1mo ago Changed b8ebc9e84a2c
  2. 1mo ago Changed · +1 lines fe317682bbd3
  3. 1mo ago First seen · 57 lines · 16 tokens per session scan A 4b7160939664

Subscribe to this mod's changes

ask is a command published in the GitHub repository stevenc81/gemini-plugin-cc (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 875 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.

Related

ask compared with commands from other repositories

ask next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
askstevenc81/gemini-plugin-ccCommand01mo agoApache-2.0A16Claude Code
promptsaadshahd/moo.mdCommand38yesterdayMITA22Claude Code
bootmicrosoft/PromptKitCommand11417d agoMITA14GitHub Copilot
music-suno-promptfrankxai/Starlight-Intelligence-SystemCommand107d agoMITA23Claude Code
prompt-showyaleh/meta-ccCommand221mo agoMITA12Claude Code
aiterrene-foundation/kailash-coc-claude-pyCommand132mo agoApache-2.0A0Claude Code
develop-image-prompt.evaldavistroy/claude-marketplaceCommand51mo agoMITA0Claude Code