agentmods.dev

research

A skill for sending a question to Google's Gemini deep-research agent and returning a report with citations. It is intended for thorough, multi-source web research rather than a quick answer.

In plain words
What is it for?
Use it when you want Gemini to investigate a topic across multiple sources, with either the standard or slower, higher-effort research mode.
Why use it?
It delegates a broad research task to a managed agent and waits for the resulting report. The input does not describe other capabilities beyond launching and reporting that research.

Skill for Claude CodeCodex

588 +1 21d ago A scan 91 tokens original MIT
View the source file FradSer/dotclaude
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 skills/fradser/dotclaude/research
Any agent
npx skills add FradSer/dotclaude --skill research
Clone the repo
git clone --depth 1 https://github.com/FradSer/dotclaude

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,010 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 $0.00091 $0.01010
Opus 5 $0.00046 $0.00505
Sonnet 5 $0.00018 $0.00202
Haiku 4.5 $0.00009 $0.00101

Measured 3d ago against content hash 950cf38c206e, 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 3d 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.

antigravity/skills/research/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity Deep Research

Run $ARGUMENTS as a deep-research query on Gemini's deep-research managed agent, wait for it to finish, and report the cited result. Two models are available: deep-research-preview-04-2026 (default) and deep-research-max-preview-04-2026 (max mode — slower, higher effort), selected with --max.

The script is at ${CLAUDE_PLUGIN_ROOT}/scripts/antigravity.py. It is self-daemonizing: research returns immediately with a run_id, a detached worker runs the research, and a status file flips to completed / failed when done. Requires GEMINI_API_KEY in the environment and uv on PATH. Deep research can take several minutes.

Phase 1: Frame the query

Goal: Turn $ARGUMENTS into a clear research question.

Actions:

  1. Use the full $ARGUMENTS text (minus a --max flag) as the research question. Pass --max through to the script when the user wants max mode (deeper, slower).
  2. If it is empty or too vague to research (no subject, scope, or constraints), ask the user one or two clarifying questions, then proceed.

Phase 2: Launch the run

Goal: Start the detached research worker.

Actions:

  1. Run the script: 
    uv run "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity.py" research --query "<question>" [--max]
  2. Capture run_id, output_file, and wait_command from stdout.
  3. If stdout reports an error (for example a missing GEMINI_API_KEY), surface it and stop.

Phase 3: Wait for completion

Goal: Block until the research finishes without busy-looping the model.

Actions:

  1. Start a Monitor on the captured wait_command. It emits one line — antigravity run <id>: completed / failed / timeout — then exits: 
    uv run "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity.py" wait --run <run_id> --timeout 1800
    Deep research is slow: set the Monitor timeout_ms to 3600000 (60 min, 2x the wait timeout) and pass --timeout 1800 to the wait command. Use a clear description like "antigravity research <run_id>".
  2. When the Monitor event arrives, check if the line contains : completed, : failed, or : timeout:
    • Contains : completed or : failed → proceed to Phase 4.
    • Contains : timeout → the research is still running (the worker keeps polling up to ~2h). Start the Monitor on the same wait_command again to keep waiting. After four consecutive timeouts (4 hours total), tell the user it is still running and give them the full command to fetch it later: 
      uv run "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity.py" status --run <run_id> --full
      then stop. Never present a timeout / still-running state as the report.

Read the full file on GitHub · 87 lines

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. 3d ago First seen · 87 lines · 91 tokens per session scan A 950cf38c206e

Subscribe to this mod's changes

research is a skill published in the GitHub repository FradSer/dotclaude (588 stars, last pushed 21d ago), licensed MIT. It adds 91 tokens to every session and 1,010 once invoked, about $0.0005 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.

Researchclaude
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens