What is geminiusage GEMINI.md?

A project instruction file for a Python utility that reads Gemini AI session logs, calculates usage costs, and displays reports or a terminal dashboard. It documents how the project is built and run.

It helps maintain log parsing, pricing calculations, caching, the command-line reporter, the terminal interface, configuration, and development commands.

It gives coding agents the project background and conventions they need before changing or running the usage tracker.

How rmedranollamas/geminiusage configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to rmedranollamas/geminiusage. 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/rmedranollamas/geminiusage/main/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/rmedranollamas/geminiusage

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/rmedranollamas/geminiusage/gemini-md/github.svg)](https://agentmods.dev/instructions/rmedranollamas/geminiusage/gemini-md)

Your own site

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

Per session 687 This file is loaded in full into every session.

When invoked 687 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 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 5.1	$0.00687	$0.00687
Opus 5	$0.00344	$0.00344
Sonnet 5	$0.00137	$0.00137
Haiku 4.5	$0.00069	$0.00069

Measured 9d ago against content hash 6a0489ad130d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

geminiusage 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 9d 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.

GEMINI.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Usage Tracker (GEMINI.md)

This project is a lightweight, high-performance Python utility designed to track, aggregate, and visualize token usage and costs for Google Gemini AI models. It operates by parsing session logs (JSON format), applying tiered pricing logic, and providing both a CLI reporter and an interactive Terminal User Interface (TUI).

Project Overview

Core Logic (scripts/token_usage.py): Handles recursive file scanning, JSON parsing, tiered cost calculation, and persistent caching (usage_cache.json).
Interactive Dashboard (scripts/tui.py): A curses-based TUI with auto-refresh (30s interval), live countdowns, and dynamic filtering.
Data Persistence: Uses a local cache (usage_cache.json) to avoid re-parsing unchanged session files, making it suitable for frequent execution (e.g., every 30 seconds or in tmux status bars). Concurrent executions use non-blocking locks to ensure the UI never freezes during cache rebuilds.
Configuration: Supports custom pricing overrides via ~/.gemini/pricing.json.

Building and Running

The project relies exclusively on the Python 3 standard library (no external pip dependencies required).

Commands

Run CLI Report:

python3 scripts/token_usage.py [dir] [--today|--this-week|--model]

Run TUI Dashboard:
```
python3 scripts/tui.py [dir]
```

Tmux Integration:

./scripts/tmux_status.sh [interval_seconds]

Run Tests:

python3 scripts/token-usage_test.py
python3 scripts/tui_test.py

Development Conventions

Standard Library First: Prioritize Python's standard library modules (curses, argparse, dataclasses, pathlib, json, datetime) to keep the project zero-dependency and easy to distribute.
Performance: Any changes to data ingestion must respect the usage_cache.json logic (checking mtime before parsing). Locking should always be non-blocking (fcntl.LOCK_NB) so concurrent reads (e.g. tmux status updates) degrade gracefully to parsing raw files instead of freezing.
Testing Strategy:
- Use unittest and unittest.mock for core logic and UI state testing.
- Logic tests should use tempfile.TemporaryDirectory to simulate filesystem environments.
Pricing Logic: Tiered pricing is sensitive to context thresholds (default 200k tokens). Ensure calculate_cost remains the single source of truth for pricing math.
Configuration: Custom pricing should be loaded via load_config and merged with hardcoded defaults.

Read the full file on GitHub · 54 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.

9d ago First seen · 54 lines · 687 tokens per session scan A 6a0489ad130d

Subscribe to this mod's changes

geminiusage GEMINI.md is an instructions file published in the GitHub repository rmedranollamas/geminiusage (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 687 tokens to every session, about $0.0034 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.

Analytics and metrics gemini-cli

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

geminiusage: Instructions file for Gemini CLI