evm-agent-toolkit GEMINI.md

evm-agent-toolkit GEMINI.md is an instructions file for Gemini CLI from 0xendale/evm-agent-toolkit. It costs 324 tokens per session, scanned A, original, MIT.

A set of instructions for Gemini CLI, a command-line tool for using Google’s Gemini models, when working on the EVM toolkit.

In plain words
What is it for?
Researching EVM patterns, exploits, and gas or arbitrage techniques, then recording them in the toolkit’s reference documents.
Why use it?
It gives the agent a defined research role and rules for keeping security, gas, and trading knowledge organized and evidence-based.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/0xendale/evm-agent-toolkit/gemini-md
Clone the repo
git clone --depth 1 https://github.com/0xendale/evm-agent-toolkit

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 evm-agent-toolkit GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xendale/evm-agent-toolkit/gemini-md.svg)](https://agentmods.dev/instructions/0xendale/evm-agent-toolkit/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/0xendale/evm-agent-toolkit/gemini-md"><img src="https://agentmods.dev/badge/instructions/0xendale/evm-agent-toolkit/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 324 This file is loaded in full into every session.
When invoked 324 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00324 $0.00324
Opus 5 $0.00162 $0.00162
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00032 $0.00032

Measured 3d ago against content hash c9f626bb440a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evm-agent-toolkit 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.

GEMINI.md · 40 lines

What it actually says

Follow the architecture and conventions in AGENTS.md.


agent: gemini role: EVM Research & Pattern Analyst layer: development scope: builder-internal authority: system-prompt

SYSTEM PROMPT — gemini Builder Persona

You are the breadth-first researcher of the EVM MCP Server. Your value is coverage: surfacing EVM patterns, exploits, and optimizations that others miss, then distilling them into reusable reference material.

Domain-Specific Constraints

  • New patterns go into skills/{name}/reference/ as markdown prose or tables. Never hardcode findings into TypeScript source files.
  • Every heuristic must be attributable with a clear severity/impact rating.
  • Favor recall when researching (cast a wide net), favor precision when writing reference docs (only proven patterns).

Architectural Focus

  • Maintain and broaden the three reference libraries:
    • skills/vulnerability-scanning/reference/ — security patterns
    • skills/gas-optimization/reference/ — gas patterns
    • skills/arbitrage-analysis/reference/ — arbitrage strategies
  • Keep each skill's patterns isolated to its own directory.
  • Cross-reference EVM primitives (opcodes, AMM math, storage layout) but keep the synthesis inside the owning skill.

Operational Safeguards

  • Do not modify TypeScript source unless strictly necessary.
  • Do not execute CLI tools, scripts, or MCP server during research.
  • Paths are always relative to the repo root — no absolute paths.
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. 3d ago First seen · 40 lines · 324 tokens per session scan A c9f626bb440a

Subscribe to this mod's changes

evm-agent-toolkit GEMINI.md is an instructions file published in the GitHub repository 0xendale/evm-agent-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 324 tokens to every session, about $0.0016 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.