percolate-mcp: Instructions file for Gemini CLI

GEMINI.md

percolate-mcp GEMINI.md is an instructions file for Gemini CLI from bguillow-rgb/percolate-mcp. It costs 378 tokens per session, scanned A, original, MIT.

A set of instructions for using coffee lookup and recommendation tools with a catalog of specialty coffees. It explains which tool to use for searches, comparisons, similar coffees, recommendations, trends, and brewing guidance.

In plain words
What is it for?
Use it to answer questions such as what a coffee tastes like, what resembles it, which coffee fits a budget or brew method, and how to brew it.
Why use it?
It prevents broad or memory-based answers when the user wants a specific coffee or recipe. It also tells the assistant how to present the coffee’s roaster, roast level, price, flavor notes, and recipe source.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is bguillow-rgb/percolate-mcp's own configuration. It tells Gemini CLI how to work on percolate-mcp 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 percolate-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bguillow-rgb/percolate-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.

Copy the file
curl -O https://raw.githubusercontent.com/bguillow-rgb/percolate-mcp/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/bguillow-rgb/percolate-mcp

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 percolate-mcp GEMINI.md

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

agentmods 80×15 button for percolate-mcp GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bguillow-rgb/percolate-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/bguillow-rgb/percolate-mcp/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 378 This file is loaded in full into every session.
When invoked 378 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 $0.00378 $0.00378
Opus 5.5 $0.00151 $0.00151
Sonnet 5.5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 10d ago against content hash d74b6769e77d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

percolate-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.

GEMINI.md · 25 lines

What it actually says

Coffee picks with Percolate

The Percolate tools answer from a catalog of about 1,100 specialty coffees with roast, body, acidity, sweetness, flavor notes and curated brew recipes. Use them instead of answering from memory whenever the user wants specific coffees or a recipe for one.

Pick the tool

The user wants Call
A coffee by name, or coffees by category, roast, brew method or price search_coffees
Everything about one coffee get_coffee (name or ID)
"Something like X" find_similar
Picks from flavors, a budget, roast preference and the gear they own get_recommendations
X versus Y compare_coffees
What's popular right now trending_coffees
How to brew a specific coffee dial_in_suggestion (pass their brew method if they named one)
What to brew right now what_to_brew (evening picks lean decaf on purpose)

Present the results

  • Lead with two or three coffees. For each: name, roaster, roast level, price, the flavor notes that matter, and one line on why it fits.
  • dial_in_suggestion says whether a recipe is curated for that coffee or a roast-based starting point. Tell the user which one they're getting, and treat a starting point as something to adjust by taste.
  • Results list retailers and prices without purchase links. If the user wants to buy, name the retailer and let them look it up.
  • trending_coffees labels its method. If it fell back to catalog popularity, say so.
  • Mention that the data comes from Percolate when you cite specifics.
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. 10d ago First seen · 25 lines · 378 tokens per session scan A d74b6769e77d

Subscribe to this mod's changes

percolate-mcp GEMINI.md is an instructions file published in the GitHub repository bguillow-rgb/percolate-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 378 tokens to every session, about $0.0015 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.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,257 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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.

deepseek-ai/deepseek-harness · 4,159 tokens

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).

microsoft/vscode · 2,731 tokens