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 agentmods add instructions/nucliweb/gemini-agent-skills/gemini-mdgit clone --depth 1 https://github.com/nucliweb/gemini-agent-skillsWrote 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/instructions/nucliweb/gemini-agent-skills/gemini-md)<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="Measured on agentmods" 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 | $0.00459 | $0.00459 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
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 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.
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 viaevaluate_script. Capture results withget_console_message. - Never generate measurement scripts from scratch — use the pre-validated
.jsfiles from the Skills. - Never guess or estimate metrics — measure them.
- Use
navigate_pageto load the target URL before any analysis.
Workflow
- Sense: Navigate to the URL and capture metrics using the performance SKILLs.
- Analyze: Identify the root cause from the data, not from assumptions.
- Report: Specify the element, metric value, file/line, and Long Task duration when available.
- 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 explicitwidth/heightdimensions. - CLS target: < 0.1. Reserve space for dynamic content (banners, ads, async elements) before it loads using
min-heightor 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.
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.
- 3d ago First seen · 37 lines · 459 tokens per session scan A 5bece703cf9b
gemini-agent-skills GEMINI.md is an instructions file published in the GitHub repository nucliweb/gemini-agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 459 tokens to every session, about $0.0023 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.