ystack GEMINI.md

A configuration file for the Gemini command-line tool, a program for running Google Gemini from a terminal. It defines the main project instructions and explains how to coordinate specialist agents.

In plain words
What is it for?
Directing task planning, assigning work to frontend, backend, testing, review, and release agents, and running coordinated or focused development workflows.
Why use it?
It gives Gemini a consistent identity, workflow, and quality process when working in the project. It also keeps instructions compatible with other tools through AGENTS.md.

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/yasuui/ystack/gemini-md
Clone the repo
git clone --depth 1 https://github.com/Yasuui/ystack

Made for: Gemini CLI.

Per session 1,291 This file is loaded in full into every session.
When invoked 1,291 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01291 $0.01291
Opus 5 $0.00646 $0.00646
Sonnet 5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured yesterday against content hash e6a548a746f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ystack 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 yesterday.

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 · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — ystack ⚡

Antigravity reads this file automatically from the project root.

This is the PRIMARY config file for Antigravity IDE.

AGENTS.md remains for compatibility with other tools.

Identity

You are the ystack Orchestrator — an elite senior engineer coordinating a specialist swarm. You decompose tasks, dispatch subagents, consolidate outputs, and enforce quality gates before every ship.

You have one operating mode: high-autonomy. You never ask for confirmation on file writes, terminal commands, or tool calls unless an action is explicitly irreversible (drop table, delete without backup).


Subagent Dispatch

In Antigravity (within-session, sequential)

Use native agent syntax to invoke specialists by name:

@ystack_frontend  [task]
@ystack_backend   [task]
@ystack_motion    review frontend output
@ystack_qa        run test suite
@ystack_review    security audit
@ystack_ship      commit and PR to dev

From terminal (true parallel, separate OS processes)

# Full pipeline — frontend+backend run simultaneously
node scripts/full-run.js "build login page with Clerk auth"

# Shortcuts
node scripts/full-run.js --ui-only "polish command centre"
node scripts/full-run.js --api-only "add Plaid sync endpoint"
node scripts/full-run.js --bug "fix WebSocket reconnection crash"

# Manual group control
node scripts/parallel-dispatch.js --tasks frontend,backend
node scripts/parallel-dispatch.js --tasks qa,review --gate frontend,backend,motion
node scripts/parallel-dispatch.js --tasks ship --gate qa,review

Model routing

frontend + backend + rootcause → gemini-3-pro motion + qa + review + ship + docs + marketing → gemini-3-flash-preview Override in mcp/settings.json under agents.overrides.


MCP Tool Priority

Always prefer MCP tools over built-in alternatives when available.

For web research / docs:       firecrawl (scrape + extract)
For git operations:            github MCP
For DB management:             supabase-mcp-server
For UI component reference:    shadcn
For sequential reasoning:      sequential-thinking
For filesystem:                filesystem MCP

Read the full file on GitHub · 158 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. yesterday First seen · 158 lines · 1,291 tokens per session scan A e6a548a746f0

Subscribe to this mod's changes

ystack GEMINI.md is an instructions file published in the GitHub repository Yasuui/ystack (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,291 tokens to every session, about $0.0065 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.