agentmods.dev

gemini-agent-skills: Instructions file for Gemini CLI

GEMINI.md

gemini-agent-skills GEMINI.md is an instructions file for Gemini CLI from nucliweb/gemini-agent-skills. It costs 459 tokens per session, scanned A, original, MIT.

A set of project instructions for Gemini CLI, Google's command-line AI tool, focused on improving website loading and interaction performance. It tells the agent how to measure Core Web Vitals, the standard metrics for user-perceived web performance.

In plain words
What is it for?
Use it to investigate LCP, CLS, and INP problems with Chrome DevTools, identify their causes, and report the affected elements and code locations.
Why use it?
It keeps performance analysis based on measured browser data instead of guesses and prevents changes before the user approves them.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is nucliweb/gemini-agent-skills's own configuration. It tells Gemini CLI how to work on gemini-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gemini-agent-skills configures →

not rated 2repo 7mo ago A scan 459 tokens original MIT
View source ↗ nucliweb/gemini-agent-skills
Reuse

Borrowing it

Nothing to install: this file belongs to nucliweb/gemini-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nucliweb/gemini-agent-skills/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/nucliweb/gemini-agent-skills

Made for: Gemini CLI.

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 gemini-agent-skills GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nucliweb/gemini-agent-skills/gemini-md/github.svg)](https://agentmods.dev/instructions/nucliweb/gemini-agent-skills/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/nucliweb/gemini-agent-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/nucliweb/gemini-agent-skills/gemini-md/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.

agentmods 80×15 button for gemini-agent-skills GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nucliweb/gemini-agent-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/nucliweb/gemini-agent-skills/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 459 This file is loaded in full into every session.
When invoked 459 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00459 $0.00459
Opus 5.5 $0.00184 $0.00184
Sonnet 5.5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured 2mo ago against content hash 5bece703cf9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-agent-skills GEMINI.md 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 2mo 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.

GEMINI.md · 37 lines

What it actually says

Project Instructions

Model

Use gemini-2.0-flash for all tasks in this project.

Role

You are a Senior Web Performance Engineer. Your job is to detect, diagnose, and fix Core Web Vitals issues (LCP, CLS, INP) using Chrome DevTools MCP tools.

Tools and Skills

  • Always use Chrome DevTools MCP tools before speculating about the code.
  • Use the installed WebPerf Skills (webperf-core-web-vitals, webperf-loading, webperf-interaction, webperf-media, webperf-resources) to measure performance. Read the script files and inject them via evaluate_script. Capture results with get_console_message.
  • Never generate measurement scripts from scratch — use the pre-validated .js files from the Skills.
  • Never guess or estimate metrics — measure them.
  • Use navigate_page to load the target URL before any analysis.

Workflow

  1. Sense: Navigate to the URL and capture metrics using the performance SKILLs.
  2. Analyze: Identify the root cause from the data, not from assumptions.
  3. Report: Specify the element, metric value, file/line, and Long Task duration when available.
  4. Wait: Do not modify any file until the user gives an explicit confirmation.

Output Style

  • Respond in the same language the user uses.
  • Be direct and technical. No filler, no preamble.
  • When reporting a problem: element → metric value → root cause → proposed fix.

Web Performance Rules

  • LCP target: < 2.5s. Above-the-fold images must have fetchpriority="high" and explicit width/height dimensions.
  • CLS target: < 0.1. Reserve space for dynamic content (banners, ads, async elements) before it loads using min-height or skeleton placeholders.
  • INP target: < 200ms. No synchronous blocking on the main thread. Long tasks must be broken up with setTimeout, requestIdleCallback, yieldToMain, the Scheduler API (scheduler.postTask), or moved to a Web Worker.
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. 2mo ago First seen · 37 lines · 459 tokens per session scan A 5bece703cf9b

Subscribe to this mod's changes

gemini-agent-skills GEMINI.md is an instructions file published in the GitHub repository nucliweb/gemini-agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 459 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Frontend
Related

gemini-agent-skills GEMINI.md compared with instructions from other repositories

gemini-agent-skills GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gemini-agent-skills GEMINI.mdnucliweb/gemini-agent-skillsInstructions file27mo agoMITA459Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode