Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/haunchen/gemini-plugin-ccWrote 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/haunchen/gemini-plugin-cc/ask)<a href="https://agentmods.dev/commands/haunchen/gemini-plugin-cc/ask"><img src="https://agentmods.dev/badge/commands/haunchen/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.
<a href="https://agentmods.dev/commands/haunchen/gemini-plugin-cc/ask"><img src="https://agentmods.dev/badge/commands/haunchen/gemini-plugin-cc/ask.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 | $0.00014 | $0.00756 |
| Opus 5.5 | $0.00006 | $0.00302 |
| Sonnet 5.5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00076 |
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Gemini a question via the Antigravity CLI (agy). Optionally provide a file for context.
Step 1: Parse --model parameter
Check if $ARGUMENTS contains --model <value>:
- If yes: extract the value as MODEL, remove
--model <value>from $ARGUMENTS - If no: set MODEL = flash
Map the alias to an agy model slug:
flash→gemini-3.6-flash-high(the default)pro→gemini-3.1-pro-high— an older generation than 3.6 flash; available for explicit opt-in, not recommended- Anything else is passed through unchanged (run
agy modelsto list available slugs).
Step 2: Determine input
Split the remaining $ARGUMENTS into QUESTION and optional FILE_PATH:
- Check if the last token in $ARGUMENTS is an existing file path (use
test -f <last_token>) - If yes: Read the file contents as CONTEXT, the rest of $ARGUMENTS is the QUESTION
- If no: the entire $ARGUMENTS is the QUESTION, no CONTEXT
If QUESTION is empty, tell the user: "Please provide a question. Example: /gemini:ask What does this regex do? src/utils.js"
Build ASK_INPUT:
- If CONTEXT exists:
Question: {QUESTION} --- {CONTEXT} - If no CONTEXT:
Question: {QUESTION}
Step 3: Call agy
The system prompt lives in the gemini-ask agent, installed by /gemini:setup. The agent's tools whitelist keeps the run read-only — there is no separate policy file.
Run the following bash command, passing ASK_INPUT via stdin.
output=$(printf "%s" "$ASK_INPUT" | agy --agent gemini-ask --model $MODEL --print-timeout 5m 2>&1)
echo "$output"
Note: We pipe input via stdin instead of -p to handle large inputs and special characters safely.
Step 4: Present results
Show the Gemini response directly to the user. Do not modify, summarize, or reformat it.
Error handling
- If
agycommand is not found: suggest running/gemini:setupfirst - If the output reports
no output producedand a denied permission (read_file): the agent tried to open a file and agy auto-denied it, because a headless run cannot show a permission prompt — and the denial discards the whole answer. The install is fine, so do not send the user to/gemini:setup. Re-run after passing the file in as an argument, so its contents travel in the prompt and the agent has no reason to reach for the filesystem - If the command fails with an auth error: suggest running
agyinteractively to re-authenticate via Google OAuth - If the output reports a quota or rate-limit error (429, RESOURCE_EXHAUSTED, overloaded): show it as-is and suggest retrying later, or picking a different model with
--model(agy modelslists the slugs). There is no automatic fallback - If the command times out or returns an error: show the error message and suggest retrying
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.
- 1mo ago First seen · 65 lines · 14 tokens per session scan A aaf71b079a19
ask is a command published in the GitHub repository haunchen/gemini-plugin-cc (1 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 756 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 2026-08-31.
Other commands, from other repositories
ia-refine-prompt
Transform a vague prompt into precise, structured AI instructions.
prompt-audit
Discover and review LLM prompts in this codebase against the best-practices rubric. Reports findings and proposed diffs in the terminal — never edits without approval.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
bootstrap
Start a new PromptKit prompt assembly session.
prompt
Create or optimize prompts using best practices.
review
Send the current git diff to Antigravity (agy) for code review. Optional focus text to steer the review.