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.
npx agentmods add commands/haunchen/gemini-plugin-cc/askgit clone --depth 1 https://github.com/haunchen/gemini-plugin-ccWhat 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 | $0.00014 | $0.00756 |
| Opus 5 | $0.00007 | $0.00378 |
| Sonnet 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 yesterday.
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.
- yesterday 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 19d ago), licensed MIT. It adds 14 tokens to every session and 756 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
package-assistant
Convert an OfficeCLI skill into a fully wired AionUi assistant preset, or update an existing one.
spec-design
Create comprehensive technical design for a specification.
spec-tasks
Generate implementation tasks for a specification.
spec-requirements
Generate comprehensive requirements for a specification.
validate-gap
Analyze implementation gap between requirements and existing codebase.
spec-impl
Execute spec tasks using TDD methodology.