research

research is a command for Claude Code from MarcosNahuel/antigravity-plugin-cc. It costs 63 tokens per session (629 once invoked), scanned A, original, MIT.

A command for quick web research that gathers sources at a chosen level of depth and saves the results in a research document.

In plain words
What is it for?
Use it for single-topic web searches, source gathering, and short research tasks, with low, medium, or high intensity.
Why use it?
It provides a fast way to collect information for lightweight lookups without running a full multi-round research project.

Command for Claude Code

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

Part of the antigravity plugin — 2 skills, 22 commands, 1 agent shipped together

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/marcosnahuel/antigravity-plugin-cc/research
Clone the repo
git clone --depth 1 https://github.com/MarcosNahuel/antigravity-plugin-cc

Made for: Claude Code.

Or install antigravity, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 1 agent.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/research.svg)](https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/research)
Your own site
<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/research"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00063 $0.00629
Opus 5 $0.00032 $0.00315
Sonnet 5 $0.00013 $0.00126
Haiku 4.5 $0.00006 $0.00063

Measured 6d ago against content hash 97522b6bba48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 6d 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/antigravity/commands/research.md · 49 lines

What it actually says

Route this to the antigravity:agy-rescue subagent in MODE: research.

Raw user request: $ARGUMENTS

Routing rules:

  • If the request contains --background, invoke the subagent with run_in_background: true. Research at high intensity can take 15–20min — background is the sensible default for that case but only when the user explicitly opted in. Strip the flag from the topic.
  • Parse --intensity <low|medium|high> from the user text. Default to medium if missing or invalid.
  • Strip the routing flags (--background, --intensity) from the user text. What remains IS the topic. Trim whitespace.
  • Build a slug from the topic: lowercase, replace non-alphanumeric with -, collapse repeated -, trim to 60 chars.
  • Compute today's date in YYYY-MM-DD (ISO, local time).
  • Compute WRITE_FILE = docs/agy/research/<YYYY-MM-DD>-<slug>.md (relative to the current working directory).
  • Before invoking the subagent, ensure the directory exists with one Bash call:
mkdir -p docs/agy/research

Pass this header block to the subagent followed by the topic:

MODE: research
INTENSITY: <low|medium|high>
MODEL:
RESUME: false
WRITE_FILE: docs/agy/research/<date>-<slug>.md
USER_TEXT:
<topic>

Note: --model was rejected by agy 1.0.0/1.0.1 but is accepted again in agy 1.0.5+. This plugin defaults to omitting it, so agy picks the model from its own settings; intensity controls the timeout and prompt template only.

Operating rules:

  • The subagent wraps the topic in the intensity template, invokes agy with the right timeout (low=3m, medium=8m, high=20m), writes the result to WRITE_FILE, and returns:
    1. The saved file path.
    2. The first ~30 lines of agy's output (TL;DR / Executive summary).
  • Present that to the user as-is. Do not paraphrase.
  • If the user did not provide a topic, ask once: "What topic would you like to research?"
  • If agy reports it is missing or unauthenticated, tell the user to run /agy:setup.
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. 6d ago First seen · 49 lines · 63 tokens per session scan A 97522b6bba48

Subscribe to this mod's changes

research is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (26 stars, last pushed 20d ago), licensed MIT. It adds 63 tokens to every session and 629 once invoked, about $0.0003 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 2026-08-30.