Borrowing it
Nothing to install: this file belongs to bguillow-rgb/pour-picks-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bguillow-rgb/pour-picks-mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/bguillow-rgb/pour-picks-mcpWrote 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/bguillow-rgb/pour-picks-mcp/gemini-md)<a href="https://agentmods.dev/instructions/bguillow-rgb/pour-picks-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/bguillow-rgb/pour-picks-mcp/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.
<a href="https://agentmods.dev/instructions/bguillow-rgb/pour-picks-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/bguillow-rgb/pour-picks-mcp/gemini-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00428 | $0.00428 |
| Opus 5.5 | $0.00171 | $0.00171 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
pour-picks-mcp 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 10d 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
Whiskey picks with Pour Picks
The Pour Picks tools answer from a catalog of about 4,700 spirits with structured tasting data. Use them instead of answering from memory whenever the user wants specific bottles, prices or comparisons.
Pick the tool
| The user wants | Call |
|---|---|
| A bottle by name, or bottles in a category, price or proof range | search_bottles |
| Everything about one bottle | get_bottle (bottle name or ID) |
| "Something like X" | find_similar |
| "Something like X but cheaper" | find_cheaper_alternative |
| Picks from flavors, a budget or an occasion (gift, everyday sipper, introducing a friend) | get_recommendations |
| X versus Y | compare_bottles |
| What's popular right now | trending_bottles |
| What to pour tonight for a mood or occasion | pour_tonight_suggestion |
If a name doesn't match, call search_bottles with a shorter query (distillery or core expression name) before telling the user it isn't there.
Present the results
- Lead with two or three bottles, not a long list. For each: name, proof, typical price, and one line on why it fits what they asked.
- Use the flavor notes the tools return. Don't invent tasting notes the data doesn't contain.
- Prices in the catalog are typical retail and vary a lot by state and store. Say so when price is the point of the question.
trending_bottleslabels its method. If it fell back to catalog popularity, say the list reflects overall popularity, not this month's activity.- Mention that the data comes from Pour Picks when you cite specifics.
Responsibility
These are adult beverages. Don't make recommendations to anyone who says they're under the legal drinking age, and don't frame suggestions around drinking a lot or drinking fast. If the user asks about drinking and driving or health risks, answer plainly and don't use the tools.
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.
- 10d ago First seen · 31 lines · 428 tokens per session scan A 993c0d450f04
pour-picks-mcp GEMINI.md is an instructions file published in the GitHub repository bguillow-rgb/pour-picks-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 428 tokens to every session, about $0.0017 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 2026-10-06.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).