rez-next GEMINI.md

rez-next GEMINI.md is an instructions file for Gemini CLI from loonghao/rez-next. It costs 1,118 tokens per session, scanned A, a copy of rez-next CLAUDE.md, Apache-2.0.

Project instructions for Gemini, a Google AI coding assistant, working on the rez-next codebase. They explain where to start, which APIs and code patterns to use, and how to run checks.

In plain words
What is it for?
Use them to guide Gemini while developing, testing, or documenting rez-next in Python and Rust.
Why use it?
They give an unfamiliar coding agent the project context needed to avoid unsupported APIs and incorrect imports.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/loonghao/rez-next/gemini-md
Clone the repo
git clone --depth 1 https://github.com/loonghao/rez-next

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 rez-next GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/loonghao/rez-next/gemini-md.svg)](https://agentmods.dev/instructions/loonghao/rez-next/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/loonghao/rez-next/gemini-md"><img src="https://agentmods.dev/badge/instructions/loonghao/rez-next/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,118 This file is loaded in full into every session.
When invoked 1,118 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.01118 $0.01118
Opus 5 $0.00559 $0.00559
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 3d ago against content hash 97297b01e92a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rez-next 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 3d 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.

Origin

This is a copy

89% identical to rez-next CLAUDE.md — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

GEMINI.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md - Google Gemini Guidance for rez-next

Important: This file references AGENTS.md for core project information. Read that file first.

For Google Gemini Agents

When working with the rez-next project, follow this guidance:

1. Start Here

Read AGENTS.md to understand:

  • Project structure and architecture
  • Available Python modules and their Rez equivalents
  • Development workflow (build, test, lint)
  • Common tasks and how to approach them

2. Key Principles

  • Progressive disclosure: AGENTS.md → llms.txt (concise) → llms-full.txt (full API) → docs/ (human guides)
  • Check coverage: Not all Rez APIs are implemented; verify before suggesting code
  • Use vx: Tool management via vx (see vx.toml)
  • Run CI early: vx just ci before submitting changes

3. Python Code Patterns

# ✅ Correct: Use rez_next as drop-in
import rez_next as rez
from rez_next.packages_ import get_latest_package

# ❌ Avoid: Direct rez imports (won't work with rez-next)
import rez

4. Rust Code Patterns

// ✅ Correct: Use the crate structure
use rez_next_version::Version;
use rez_next_package::Package;

// ❌ Avoid: Direct std types when crate types exist

5. Documentation Updates

When updating documentation:

  1. Update AGENTS.md (project map) if structure changes
  2. Update llms.txt (AI-friendly concise index) if submodule list changes
  3. Update llms-full.txt (complete API reference) for new APIs
  4. Update docs/*.md (human guides) for workflow changes
  5. Update README.md / README_zh.md for user-facing changes

6. Commit Messages

Follow Conventional Commits:

feat: add new solver heuristic
fix(solver): handle cyclic dependencies
docs: update AGENTS.md with new module
chore: upgrade dependencies

7. Testing Strategy

# Always run tests before submitting
vx just test

# Run specific tests
vx cargo test --package rez-next-solver

# Run Python tests
maturin develop --release && pytest

Read the full file on GitHub · 152 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. 3d ago First seen · 152 lines · 1,118 tokens per session scan A 97297b01e92a

Subscribe to this mod's changes

rez-next GEMINI.md is an instructions file published in the GitHub repository loonghao/rez-next (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,118 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to rez-next CLAUDE.md, differing in 24 lines, and is treated as a copy.