What is WhatToEatNext GEMINI.md?

A set of Gemini CLI instructions for the WhatToEatNext project, also called Alchm.kitchen. It documents the project structure, current status, and recent work on custom agents and chat.

Use it when working on the listed WhatToEatNext, Planetary Agents, philosopher’s stone, or lab-page features.

It gives the Gemini command-line assistant project-specific context before it changes or investigates the code.

How gregcastro23/WhatToEatNext configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to gregcastro23/WhatToEatNext. 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/gregcastro23/WhatToEatNext/master/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/gregcastro23/WhatToEatNext

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gregcastro23/whattoeatnext/gemini-md.svg)](https://agentmods.dev/instructions/gregcastro23/whattoeatnext/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/gregcastro23/whattoeatnext/gemini-md"><img src="https://agentmods.dev/badge/instructions/gregcastro23/whattoeatnext/gemini-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,411 This file is loaded in full into every session.

When invoked 2,411 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.

Model	Per session	Once invoked
Fable 5.1	$0.02411	$0.02411
Opus 5	$0.01205	$0.01205
Sonnet 5	$0.00482	$0.00482
Haiku 4.5	$0.00241	$0.00241

Measured 8d ago against content hash 042a1d2dd0f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

WhatToEatNext 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 8d 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WhatToEatNext - AI Assistant Guide (Alchm.kitchen)

Version: 3.4.0 | Last Updated: July 12, 2026

Project Overview

WhatToEatNext is a sophisticated culinary recommendation system that combines alchemical principles, astrological data, and elemental harmony to provide personalized food recommendations. The site is branded as Alchm.kitchen.

We operate a three-project loop:

alchm.kitchen (WTEN): The core Next.js user-facing platform, deployed on Vercel.
api.agents.alchm.kitchen (PA Backend): The Planetary Agents Python service owning agent personas, orchestration, and LLM recipe generation.
agents.alchm.kitchen (PA UI): The Planetary Agents Next.js UI.

Current Project Status (July 2026 - v3.4.0)

🔮 PHILOSOPHER'S STONE AGENT FORGING & DYNAMIC CHAT

End-to-End Forging: Created a user interface at /philosophers-stone enabling users to forge custom agents dynamically using birth details, name, and dominant elements.
Agent Ignition & Persona Generation: Implemented a dynamic API route at /api/agent-forge/ignite to initialize custom personas and compute Sacred 7 stats using exact alchemical properties. The route writes the natal chart directly to the canonical user_profiles.natal_chart column to align with the core database schema.
Context-Aware Vector Chat: Integrated OpenAI embeddings (src/lib/embeddings/openaiEmbeddings.ts) and database migrations (database/init/59-recipe-embeddings.sql) to enable dynamic chat sessions with forged agents, complete with a recipe embedding backfill script.
Sacred 7 Stats Engine: Hardened alignment calculations (src/lib/sacred-7-stats.ts) and derived attributes (diurnal balance, planetary aspects, dignity) to drive agent conversational behavior.

🧪 LAB PAGE ALCHEMICAL STATS FIXES

Lab page stats panel "AWAITING BACKEND": Resolved the issue where the /lab page showed missing natal stats for onboarded users by implementing a robust fallback in rowToUserWithProfile to load natal charts from the legacy users.profile JSONB column if the column-level data is null.
Sign Case Mismatch: Corrected calculateAlchemicalState where sign properties lookup failed due to casing mismatches, restoring accurate alchemical and elemental calculation.
Onboarding CTA: Updated the lab page's login prompt to guide logged-in users with empty birth details to complete onboarding.

Read the full file on GitHub · 121 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.

8d ago First seen · 121 lines · 2,411 tokens per session scan A 042a1d2dd0f3

Subscribe to this mod's changes

WhatToEatNext GEMINI.md is an instructions file published in the GitHub repository gregcastro23/WhatToEatNext (0 stars, last pushed today), licensed MIT. It adds 2,411 tokens to every session, about $0.0121 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.

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

WhatToEatNext: Instructions file for Gemini CLI