What is agent-vault GEMINI.md?

A set of repository instructions for agent-vault, including how to maintain scaffolding, generate project context, author pull requests, and identify automated GitHub posts.

Use it when editing agent-vault defaults, changing generated-project behavior, creating pull requests, or writing GitHub issues and comments.

It keeps changes to the scaffold and project-generation scripts consistent and makes agent-authored GitHub activity identifiable.

How ssheld/agent-vault configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to ssheld/agent-vault. 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/ssheld/agent-vault/main/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/ssheld/agent-vault

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/ssheld/agent-vault/gemini-md/github.svg)](https://agentmods.dev/instructions/ssheld/agent-vault/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/ssheld/agent-vault/gemini-md"><img src="https://agentmods.dev/badge/instructions/ssheld/agent-vault/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ssheld/agent-vault/gemini-md"><img src="https://agentmods.dev/badge/instructions/ssheld/agent-vault/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 450 This file is loaded in full into every session.

When invoked 450 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 98% 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.

Model	Per session	Once invoked
Fable 5.1	$0.00450	$0.00450
Opus 5.5	$0.00180	$0.00180
Sonnet 5.5	$0.00090	$0.00090
Haiku 4.5	$0.00045	$0.00045

Measured 2mo ago against content hash 85e833ad8ac2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-vault 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 2mo 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

98% identical to agent-vault CLAUDE.md — 2 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 · 37 lines

What it actually says

GEMINI.md

Purpose

This repository holds reusable scaffold files for agent-vault/.

Rules

Edit scaffold/agent-vault/ for defaults used in future project initialization.
Do not store project-specific context in this repository.
Generate project context only via scripts/new-project.sh.
When updating generated-project behavior, modify scaffold files and script templates together.

PR Authoring

For agent-authored pull requests in generated projects, follow scaffold/agent-vault/AGENTS.md section PR Authoring Standards.
Use .github/pull_request_template.md when present.

GitHub Post Attribution

For GitHub issues, issue comments, and non-review PR conversation comments, begin the body with:

> 🤖 **Post by {Model Name}** · via {Client Tool}

Use your actual model name/version when known. If the exact version is unavailable, use the best identifier you have.
If the post is specifically PR review feedback or a PR review-feedback response, use the review-policy format instead.
Never present GitHub posts as if they are the human account owner's personal opinion.
Prefer repo-relative paths or GitHub links over local filesystem paths in GitHub posts.

@scaffold/agent-vault/review-policy.md

Target Project Usage

In generated project vaults:

agent-vault/Templates/ is template source only. Instantiated notes belong in canonical runtime files under agent-vault/.
Start substantive work by reading agent-vault/README.md, agent-vault/context-log.md, agent-vault/plan.md, and agent-vault/coding-standards.md.
Skim agent-vault/open-questions.md for blockers and agent-vault/decision-log.md for active decisions relevant to the task.
Use agent-vault/context-log.md as canonical cross-session memory.
Use agent-vault/daily/, agent-vault/design-log/, agent-vault/context/handoffs/, and agent-vault/decisions/ for runtime artifacts when the workflow calls for them.

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.

2mo ago First seen · 37 lines · 450 tokens per session scan A 85e833ad8ac2

Subscribe to this mod's changes

agent-vault GEMINI.md is an instructions file published in the GitHub repository ssheld/agent-vault (2 stars, last pushed 1mo ago), licensed MIT. It adds 450 tokens to every session, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to agent-vault CLAUDE.md, differing in 2 lines, and is treated as a copy.

Git and workflow ai-agent ai-agents ai-workflow-optimization

agent-vault GEMINI.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-vault GEMINI.mdssheld/agent-vault	Instructions file	2	1mo ago	MIT	A	450	Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-vault: Instructions file for Gemini CLI