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-when-to-usegit 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-when-to-use)<a href="https://agentmods.dev/skills/azmym/gemini-plugin/gemini-when-to-use"><img src="https://agentmods.dev/badge/skills/azmym/gemini-plugin/gemini-when-to-use/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-when-to-use"><img src="https://agentmods.dev/badge/skills/azmym/gemini-plugin/gemini-when-to-use.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 | $0.00044 | $0.00952 |
| Opus 5 | $0.00022 | $0.00476 |
| Sonnet 5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
gemini-when-to-use 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini When To Use
This is the master routing skill for the Gemini plugin. Before invoking any other gemini-* skill, consult this guide to decide whether a Gemini consult is warranted and which capability to reach for.
When to invoke this skill
- You are uncertain whether the task justifies a Gemini call at all.
- The task touches multiple Gemini capabilities and you need to pick the right one.
- You want to avoid hallucination on a fact, version number, CVE, or post-training claim.
- A user asks "use Gemini" without specifying which capability.
Cost discipline rules
- Do not call Gemini for tasks Claude can handle confidently. Simple string manipulation, well-known algorithms, boilerplate generation, and in-context refactors do not need a second opinion.
- One Gemini call per sub-task. Do not fan out multiple parallel Gemini calls unless each covers a distinct, independent concern.
- Prefer cheaper tools first. Use
gemini_generate(chat/reason) before reaching forgemini_search_groundedor deep research unless freshness is required. - File analysis is expensive. Upload files to Gemini only when the file is genuinely too large for Claude's context or is a non-text format (PDF, image, audio, video).
Anti-hallucination triggers
Invoke a Gemini skill whenever the response would otherwise rely on:
- A library version, API endpoint, or config key that may have changed since training cutoff.
- A CVE, security advisory, or patch status.
- A claim about a living document (spec, RFC, standard) that may have been updated.
- An assertion about the current state of a third-party service or cloud provider.
The five subagent roles (agents/ directory)
These are pre-built agent configurations for common Gemini workflows. Prefer them over raw MCP calls for structured tasks:
| Subagent | File | Best for |
|---|---|---|
| Researcher | agents/gemini-researcher.md |
Deep research synthesis, primary sources with citations |
| Summarizer | agents/gemini-summarizer.md |
Condensing long documents, transcripts, or codebases |
| Validator | agents/gemini-validator.md |
Fact-checking claims, verifying logic, sanity-checking before commit |
| Challenger | agents/gemini-challenger.md |
Devil's advocate critique, stress-testing designs or decisions |
| Reviewer | agents/gemini-reviewer.md |
Generalist diff/PR review (security, threading, version drift, docs, dead code); manual, advisory via the gemini-consult rule |
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.
- 8d ago First seen · 71 lines · 44 tokens per session scan A 46575f3b910e
gemini-when-to-use is a skill published in the GitHub repository azmym/gemini-plugin (1 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 952 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-result-handling
Internal guidance for presenting Gemini helper output back to the user.
gemini-prompting
Internal guidance for composing effective Gemini prompts for visual analysis, design review, and coding tasks.
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.