gemini-extension GEMINI.md

Instructions for connecting an agent to ObjectStack, a system where business data tables and business actions are exposed as tools.

In plain words
What is it for?
Use it to inspect, filter, report on, create, or update ObjectStack records, or to run actions such as approvals, conversions, and workflow triggers.
Why use it?
They tell the agent to discover available data and actions first and to respect the signed-in user's permissions and row-level access rules.

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/objectstack-ai/gemini-extension/gemini-md
Clone the repo
git clone --depth 1 https://github.com/objectstack-ai/gemini-extension

Made for: Gemini CLI.

Per session 1,188 This file is loaded in full into every session.
When invoked 1,188 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 $0.01188 $0.01188
Opus 5 $0.00594 $0.00594
Sonnet 5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured yesterday against content hash 3b9372c1868d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini-extension 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 · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ObjectStack

This skill connects you to an ObjectStack environment. An ObjectStack environment exposes its data objects (tables) and its business actions (registered app logic: approvals, conversions, flow triggers) as tools over the Model Context Protocol (MCP). Every operation runs as you — under your account's permissions and row-level security — so you may see a subset of rows, or get a permission error on a write. That is expected governance, not a failure.

When to use

Use these tools whenever the user wants to inspect or change data in their ObjectStack app — look up records, filter/report, create or update entries, clean up data — or run a business action the app defines (approve a request, convert a lead, kick off a flow). Prefer these tools over guessing — the environment is the source of truth, and an action is always better than hand-editing the records it would have touched.

Connect

This skill drives the MCP server at:

<YOUR_ENV_MCP_URL>

Two authentication tracks are supported:

OAuth (recommended for interactive clients). Add the URL as a remote MCP server with no credentials; the deployment is its own OAuth 2.1 authorization server, so an OAuth-capable client (claude.ai custom connectors, Claude Desktop, Claude Code) discovers it automatically, registers itself, and opens a browser login. You sign in as yourself and every tool call runs under your own permissions. Example (Claude Code):

claude mcp add --transport http objectstack <YOUR_ENV_MCP_URL>

API key (headless: CI, scripts, agents without a browser). Send an ObjectStack API key as a request header (the key is shown to you once when created; treat it like a password):

x-api-key: <YOUR_API_KEY>

(Authorization: ApiKey <YOUR_API_KEY> and Authorization: Bearer <YOUR_API_KEY> are also accepted.) If your MCP client supports custom headers on a remote server, set the header there.

Discover before you act

The schema is not baked into this skill — it is discovered live, so it is always current even as the app evolves:

Read the full file on GitHub · 112 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 · 112 lines · 1,188 tokens per session scan A 3b9372c1868d

Subscribe to this mod's changes

gemini-extension GEMINI.md is an instructions file published in the GitHub repository objectstack-ai/gemini-extension (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,188 tokens to every session, about $0.0059 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.