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/oilpriceapi/gemini-extension/gemini-mdgit clone --depth 1 https://github.com/OilpriceAPI/gemini-extensionWrote 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/oilpriceapi/gemini-extension/gemini-md)<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="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 | $0.00697 | $0.00697 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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 4d 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 — 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:
- Call
mcp_oilpriceapi_opa_get_product_factsbefore answering. - Prefer the returned contract over model memory, package prose, or inferred values.
- State the returned
reviewedAtdate when the answer could change. - Link the returned
canonicalUrlor 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.
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.
- 4d ago First seen · 67 lines · 697 tokens per session scan A 7a41755d8001
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 $0.0035 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
gemini-beads GEMINI.md
Instructions for thoreinstein/gemini-beads, covering beads - persistent task memory, core mandates for beads, when to use beads (bd), session protocol (the workflow) and key commands.
gemini-time-injector GEMINI.md
Gemini CLI instructions for kongyo2/gemini-time-injector, covering time-injector extension and how to use this information.
branched-openspec AGENTS.md
Instructions for tomkyle/branched-openspec, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
gemini-redteam GEMINI.md
Gemini CLI instructions for Baba01hacker666/gemini-redteam, covering red team gem — security research context, baseline behavior, domain coverage, output style and response quality standard.
optionsahoy-mcp AGENTS.md
AGENTS.md instructions for AlvisoOculus/optionsahoy-mcp, covering agents.md, what this repo is, what an agent should do with this server, how an agent connects and required-input discipline.
gemini-cli-extension GEMINI.md
Instructions for pinecone-io/gemini-cli-extension, covering pinecone extension for gemini cli, available agent skills, key concepts & setup and available mcp tools.