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 roedyrustam/vibes-plug --skill gemini-agent-boostergit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/gemini-agent-booster)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/gemini-agent-booster"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/gemini-agent-booster/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/roedyrustam/vibes-plug/gemini-agent-booster"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/gemini-agent-booster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01815 |
| Opus 5 | $0.00044 | $0.00907 |
| Sonnet 5 | $0.00018 | $0.00363 |
| Haiku 4.5 | $0.00009 | $0.00181 |
Grade A, and why
gemini-agent-booster 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 10d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Agent Booster (2026 Edition — Gemini 2.5 Pro/Flash)
English
Orchestration & Integration
Connects and orchestrates with relevant domain skills like brainstorming, zero-to-prod-orchestrator, and project-context-mapper to ensure cohesive execution.
Description
Master optimization protocol for the Gemini Agent (Antigravity) to leverage native Gemini 2.5 Pro/Flash capabilities — including 1M+ token context window, multimodal vision analysis, deep research mode, thinking chains, and high-speed code generation.
Trigger Conditions
- Analyzing very large codebases, logs, or documents that require 1M+ token context.
- Performing multimodal UI audits (analyzing screenshots of running applications).
- Running deep research tasks requiring web search + reasoning synthesis.
- Generating large, complex code artifacts in a single pass.
- Delegating complex multi-step tasks to browser subagents.
Gemini 2.5 Pro/Flash Capabilities (2026)
| Capability | Gemini 2.5 Pro | Gemini 2.5 Flash |
|---|---|---|
| Context Window | 1M tokens | 1M tokens |
| Thinking / Reasoning | ✅ Extended thinking | ✅ Flash thinking |
| Multimodal (Image/Video) | ✅ | ✅ |
| Code Generation | Best-in-class | Very fast |
| Web Search (Grounding) | ✅ | ✅ |
| Deep Research | ✅ (up to 30 min) | ✅ |
| Audio | ✅ | ✅ |
| Speed | Slower | 5-10x faster |
| Cost | Higher | Lower |
1M+ Token Long-Context Strategies
When working with very large inputs (codebases, documents, logs):
- Pass full file trees — use
list_dirto get the complete file tree, then pass relevant files to maximize context. - Read whole files, not snippets — with 1M context, read entire source files rather than grepping for fragments.
- Cross-file analysis — trace data flows, imports, and interfaces across multiple files simultaneously.
- Log analysis — pass entire server logs (up to hundreds of thousands of lines) for pattern detection.
- Codebase onboarding — ingest an entire unfamiliar repo in one pass for deep architectural understanding.
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.
- 10d ago First seen · 142 lines · 88 tokens per session scan A be40e73319bc
gemini-agent-booster is a skill published in the GitHub repository roedyrustam/vibes-plug (50 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,815 once invoked, about $0.0004 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.
Other skills, from other repositories
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
update-dependencies
Upgrade project dependencies with breaking change research for major version updates. Use when the user asks to "update dependencies", "upgrade packages", "upgrade dependencies", "update deps", "upgrade deps", "update npm deps", "update Swift packages", "cargo update", "go get updates", "bundle update", or "pip…
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.
finalize
Run the post-implementation quality assurance workflow including tests, code polishing, review, and commit. Use when the user asks to "finalize implementation", "finalize changes", "wrap up implementation", "finish up", "ready to commit", or "run QA workflow".
create-changelog
Create a CHANGELOG.md following keepachangelog.com conventions with version history backfilled from GitHub releases or git tags. Use when the user asks to "create a changelog", "add a changelog", "initialize changelog", "start a changelog", "set up changelog", "generate changelog", or "backfill changelog".
ai-cold-outreach
When the user wants to build an AI-powered outreach system, write cold emails, improve deliverability, or scale personalized outreach. Also use when the user mentions 'cold email,' 'cold outreach,' 'outreach automation,' 'Instantly,' 'Smartlead,' 'Clay,' 'email sequences,' 'deliverability,' 'personalization at scale,'…