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 skills add azmym/gemini-plugin --skill gemini-research-groundedgit clone --depth 1 https://github.com/azmym/gemini-pluginWrote 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.
[](https://agentmods.dev/skills/azmym/gemini-plugin/gemini-research-grounded)<a href="https://agentmods.dev/skills/azmym/gemini-plugin/gemini-research-grounded"><img src="https://agentmods.dev/badge/skills/azmym/gemini-plugin/gemini-research-grounded/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/azmym/gemini-plugin/gemini-research-grounded"><img src="https://agentmods.dev/badge/skills/azmym/gemini-plugin/gemini-research-grounded.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00792 |
| Opus 5 | $0.00023 | $0.00396 |
| Sonnet 5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
gemini-research-grounded 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Research Grounded
Use this skill whenever the answer depends on information that may have changed since Claude's training cutoff, or whenever you need primary sources and citations rather than recalled knowledge.
When to use this skill
- Library/framework versions: "What is the latest stable version of X?" or "Is feature Y available in version Z?"
- CVE and security advisories: Patch status, CVSS scores, affected versions, mitigations.
- API documentation: Endpoint signatures, authentication schemes, response shapes that may have evolved.
- Living standards and specs: RFC status, W3C spec updates, OpenAPI changes.
- Current events affecting engineering: Cloud provider incidents, deprecation announcements, EOL dates.
- Factual claims requiring a citation: Any assertion that should be backed by a URL.
- Deep research synthesis: Multi-source synthesis on a technical topic, competitive landscape, or best-practice survey.
MCP tools
| Tool | Purpose |
|---|---|
gemini_search_grounded |
Fast, single-shot search-grounded answer with citations |
gemini_start_research |
Kick off an async deep research job (returns a job ID) |
gemini_get_research_report |
Poll for and retrieve the completed deep research report |
Choosing between fast search and deep research
| Scenario | Tool |
|---|---|
| A single fact, version, or advisory | gemini_search_grounded |
| A broad technical survey or multi-source synthesis | gemini_start_research + gemini_get_research_report |
Deep research is asynchronous and may take 30-120 seconds. Use it only when breadth and synthesis matter more than speed.
Usage pattern
Fast grounded search
{
"tool": "gemini_search_grounded",
"arguments": {
"query": "Latest stable release of Kubernetes and its release date",
"model": "gemini-3.7-flash"
}
}
The response includes cited sources. Always surface the citations to the user.
Async deep research
Step 1: start the job.
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.
- 9d ago First seen · 91 lines · 46 tokens per session scan A f28d3bb974fa
gemini-research-grounded is a skill published in the GitHub repository azmym/gemini-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 792 once invoked, about $0.0002 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 skills, from other repositories
grok-prompting
Internal guidance for composing Grok prompts for coding, review, diagnosis, and research tasks inside the Grok Claude Code plugin.
gemini-cli-runtime
Internal helper contract for calling the gemini-companion runtime from Claude Code.
gemini-prompting
Internal guidance for composing effective Gemini prompts for visual analysis, design review, and coding tasks.
gemini-result-handling
Internal guidance for presenting Gemini helper output back to the user.
gemini-peer-review
This skill should be invoked BEFORE presenting implementation plans, architecture recommendations, code review findings, or answers to broad technical questions. Use proactively when about to "recommend", "suggest", "propose", "design", "plan", or answer "how should", "what's the best way", "which approach". MANDATORY…
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.