research

A command for delegating a thorough research investigation to an Antigravity subagent.

In plain words
What is it for?
Use it to research a topic, summarize current knowledge, identify disagreements or open questions, and organize the result with sources.
Why use it?
It frames the request to look for authoritative sources, compare findings, and note uncertainties rather than producing only a quick answer.

Command

Install

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.

agentmods
npx agentmods add commands/limeflash/antigravity-plugin-cc/research
Clone the repo
git clone --depth 1 https://github.com/limeflash/antigravity-plugin-cc
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00013 $0.00476
Opus 5 $0.00006 $0.00238
Sonnet 5 $0.00003 $0.00095
Haiku 4.5 $0.00001 $0.00048

Measured yesterday against content hash 43366f6c6794, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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.

Origin

This is a copy

100% identical to research — 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.

plugins/agy/commands/research.md · 56 lines

What it actually says

Hand a deep-research task to the agy:runner subagent (subagent_type: "agy:runner").

Wrap the user's topic in a research-oriented preamble so agy treats it as a structured investigation rather than a quick Q&A.

Raw user request: $ARGUMENTS

How to forward

Build the research prompt for the subagent as:

Conduct a thorough research investigation on the following topic. Look up
authoritative sources, summarize the current state of knowledge, surface
disagreements or open questions, and structure the response with clear
sections (Background, Key findings, Caveats, Sources).

Topic: <stripped user request here>

(Strip any routing flags — --background, --model <alias> — from the topic text before injecting it.)

Then invoke the agy:runner subagent with that prompt as subagent_type: "agy:runner".

Routing rules

  • If the request contains --background, launch the subagent with run_in_background: true. Research is often long-running — prefer background unless the user explicitly asked for foreground.
  • If the request contains --model <alias>, forward it to the subagent so it can be appended to the wrapper call as --model <alias> (placed before the prompt argument). If no model is given, leave the choice to whatever the TUI is currently set to (a reasoning-strong model like pro or opus works well for research).

Aliases: flash-low, flash-medium, flash, pro-low, pro, sonnet, opus, gpt-oss. Canonical TUI strings (e.g. "Claude Opus 4.6 (Thinking)") are also accepted. Run /agy:help for the full table.

Response style

Return the subagent's output verbatim — no extra commentary before or after.

If the user did not supply a topic, ask what they want researched.

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. yesterday First seen · 56 lines · 13 tokens per session scan A 43366f6c6794

Subscribe to this mod's changes

research is a command published in the GitHub repository limeflash/antigravity-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 476 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 research, differing in 0 lines, and is treated as a copy.