What is googlecloud-plugin GEMINI.md?

A set of always-on instructions for planning and delivering Google Cloud projects. It requires a design and several review steps before code is written.

It helps plan Google Cloud systems, route work through design and security reviews, and guide implementation across services such as Cloud Run, GKE, and BigQuery.

It prevents work from jumping straight into implementation without checking the right cloud approach, architecture, security, and costs.

googlecloud-plugin GEMINI.md — Instructions file by jpantsjoha

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/jpantsjoha/googlecloud-plugin/gemini-md

Clone the repo

git clone --depth 1 https://github.com/jpantsjoha/googlecloud-plugin

Made for: Gemini CLI.

Per session 559 This file is loaded in full into every session.

When invoked 559 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.

Model	Per session	Once invoked
Fable 5	$0.00559	$0.00559
Opus 5	$0.00280	$0.00280
Sonnet 5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured yesterday against content hash 3d7df70b9ddc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

googlecloud-plugin 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — GoogleCloud Plugin (always-on rules)

Human-led. Agent-powered. Built on Google Cloud. Read this before generating anything for a Google Cloud task.

This is the always-on context for the googlecloud-plugin on Antigravity. It installs a full GCP delivery team and a sequential gate. The skills in skills/ carry the depth; this file carries the contract.

Design before generate

Restate the intent in one sentence before writing code. If you can't, you're not ready.
No GCP implementation without a design. Route through the gate below.

The gate (sequential — do not skip)

Solution Gate — solution-designer: is this GCP, multi-cloud, or better elsewhere? Objective, not GCP-biased. (Skip only if unambiguously GCP-only.)
GCP Design Gate — gcp-architect (+ agent-architect if the workload is agentic): HLD/LLD + ADRs before code. Agentic work also defines topology, protocols (MCP/A2A/AP2), model, and eval set.
Security Gate — gcp-security: least-privilege IAM, no secrets in code, Well-Architected security pillar. Reviews the design, not the diff.
Implementation — service skills (Cloud Run, GKE, BigQuery, …). Warn before every billable action.
Quality Gate — gcp-qa runs make gate; agent-architect runs agent-eval for agentic work.
Operational Readiness Gate — gcp-ops: no SLO, alerting, or runbook means no production.

Non-negotiable safety rules

Infer intent, never infer permission. A named human authorises anything consequential, billable, or irreversible.
No credential values in any file — record location only.
No public Cloud Storage buckets or --allow-unauthenticated Cloud Run without explicit intent + gcp-security sign-off.
Never pin a preview Gemini model ID; prefer GA IDs and reverify in Model Garden for the GEAP surface.
Platform naming: use Gemini Enterprise Agent Platform (GEAP) in prose; keep legacy vertex-ai / agent_engine literals in code, gcloud, Terraform, and URLs.

Read the full file on GitHub · 33 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.

yesterday First seen · 33 lines · 559 tokens per session scan A 3d7df70b9ddc

Subscribe to this mod's changes

googlecloud-plugin GEMINI.md is an instructions file published in the GitHub repository jpantsjoha/googlecloud-plugin (4 stars, last pushed 24d ago), licensed MIT. It adds 559 tokens to every session, about $0.0028 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.

Code review Planning Security a2a adk agentic-ai ai-agents antigravity ap2

googlecloud-plugin GEMINI.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

GEMINI.md — GoogleCloud Plugin (always-on rules)

Design before generate

The gate (sequential — do not skip)

Non-negotiable safety rules

What this file has done since we first saw it

Other instructions, from other repositories

debroid AGENTS.md

AgentHound copilot-instructions.md

a2a-editor CLAUDE.md

agent-ship CLAUDE.md

adk AGENTS.md

ampersend-sdk CLAUDE.md