gemini-extension: Instructions file for Gemini CLI

GEMINI.md

gemini-extension GEMINI.md is an instructions file for Gemini CLI from OilpriceAPI/gemini-extension. It costs 697 tokens per session, scanned A, original, MIT.

Gemini CLI instructions for using a read-only OilPriceAPI MCP connection. They require product answers to use returned facts and route price or market requests to the matching tools.

In plain words
What is it for?
Answering OilPriceAPI product questions and retrieving current prices, market snapshots, comparisons, commodity codes, or historical data.
Why use it?
They reduce unsupported claims about product details and help select the appropriate oil-price data request.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

This is OilpriceAPI/gemini-extension's own configuration. It tells Gemini CLI how to work on gemini-extension 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-extension configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OilpriceAPI/gemini-extension. 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/OilpriceAPI/gemini-extension/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/OilpriceAPI/gemini-extension

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-extension GEMINI.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oilpriceapi/gemini-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/oilpriceapi/gemini-extension/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 697 This file is loaded in full into every session.
When invoked 697 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 $0.00697 $0.00697
Opus 5.5 $0.00279 $0.00279
Sonnet 5.5 $0.00139 $0.00139
Haiku 4.5 $0.00070 $0.00070

Measured 1mo ago against content hash e76b5b4fd6f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-extension 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 1mo 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OilPriceAPI Grounding Instructions

This extension connects the current Gemini CLI session to the read-only [email protected] tool inventory. In Gemini CLI, the tools appear with the mcp_oilpriceapi_ prefix.

Ground Product Answers

For questions about OilPriceAPI product scope, offers, pricing links, catalog, freshness, authentication, entitlements, or data rights:

  1. Call mcp_oilpriceapi_opa_get_product_facts before answering.
  2. Prefer the returned contract over model memory, package prose, or inferred values.
  3. State the returned reviewedAt date when the answer could change.
  4. Link the returned canonicalUrl or the specific pricing, catalog, docs, or data-usage URL from the contract.

Do not invent or generalize a refresh interval, catalog count, plan entitlement, SLA, redistribution right, price, history depth, WebSocket capability, or execution-feed latency.

Route Data Requests

  • One latest available value: mcp_oilpriceapi_opa_get_price.
  • Broad snapshot: mcp_oilpriceapi_opa_market_overview.
  • Two to five commodities: mcp_oilpriceapi_opa_compare_prices.
  • Discover current codes: mcp_oilpriceapi_opa_list_commodities.
  • Historical series: mcp_oilpriceapi_opa_get_history.
  • Futures, drilling, storage, production, permits, forecasts, inventories, marine fuels, spreads, surcharges, and automation reads: select the matching discovered mcp_oilpriceapi_opa_* read tool.

Never claim that a broad snapshot represents every OilPriceAPI dataset. Dataset availability varies by source, market hours, plan, and account entitlement.

Present Data Precisely

  • Describe a value as "latest available," not universally "real-time."
  • Include the commodity or dataset, value, currency/unit, source timestamp, and source when the tool returns them.
  • Preserve the API commodity code when it disambiguates the result.
  • Distinguish unavailable fields from zero values.
  • Do not give trading or investment instructions from a data result.

Read the full file on GitHub · 67 lines

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. 1mo ago Changed e76b5b4fd6f5
  2. 1mo ago Changed 5add8c3a5aea
  3. 2mo ago First seen · 67 lines · 697 tokens per session scan A 7a41755d8001

Subscribe to this mod's changes

gemini-extension GEMINI.md is an instructions file published in the GitHub repository OilpriceAPI/gemini-extension (2 stars, last pushed 1mo ago), licensed MIT. It adds 697 tokens to every session, about $0.0028 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.

Related

gemini-extension GEMINI.md compared with instructions from other repositories

gemini-extension GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gemini-extension GEMINI.mdOilpriceAPI/gemini-extensionInstructions file21mo agoMITA697Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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