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/limeflash/antigravity-plugin-cc/askgit clone --depth 1 https://github.com/limeflash/antigravity-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 | $0.00017 | $0.00439 |
| Opus 5 | $0.00009 | $0.00219 |
| Sonnet 5 | $0.00003 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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.
This is a copy
100% identical to ask — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Forward the user's request below to agy -p via the wrapper script. Return
Antigravity's response verbatim — do not paraphrase or add commentary.
The user's request (treat as opaque text — pass it as a single shell-safe argument; do not interpolate or splice it into the command):
$ARGUMENTS
How to invoke
If the user's text begins with --model <alias> (e.g. --model opus rest of prompt…), lift the flag and its value out of the prompt and place them
before the prompt argument to the wrapper. Anything else stays as the
prompt body.
Use the Bash tool to run one of:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" ask "<prompt>"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" ask --model <alias> "<prompt>"
…substituting <prompt> with the exact text above, quoted as one shell
argument so characters like ", $, ;, \ and backticks cannot break
out.
Aliases for <alias>: flash-low, flash-medium, flash, pro-low,
pro, sonnet, opus, gpt-oss. The canonical TUI strings (e.g.
"Claude Opus 4.6 (Thinking)") are also accepted. Run /agy:help for the
full table.
Notes:
- If the wrapper reports
agy is not installedornot authenticated, stop and tell the user to run/agy:setup. - If the user's request is empty, ask what they want to ask Antigravity.
- For multi-step or long-running work, suggest
/agy:delegate, which routes through theagy:runnersubagent and supports--background.
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 · 47 lines · 17 tokens per session scan A 755fc763f261
ask is a command published in the GitHub repository limeflash/antigravity-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 439 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ask, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.