agent-powerups GEMINI.md

agent-powerups GEMINI.md is an instructions file for Gemini CLI from yeaight7/agent-powerups. It costs 724 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for Agent Powerups, a local-first collection of reusable tools and workflows for coding agents, managed through the apx command-line tool.

In plain words
What is it for?
Use it when building, validating, or extending the TypeScript and Node.js project, including its catalog, reusable agent assets, and apx CLI.
Why use it?
It explains the repository's structure, technologies, and development commands so agents can work consistently across its skills, commands, hooks, and configurations.

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/yeaight7/agent-powerups/gemini-md
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

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.

agentmods badge for agent-powerups GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yeaight7/agent-powerups/gemini-md.svg)](https://agentmods.dev/instructions/yeaight7/agent-powerups/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/yeaight7/agent-powerups/gemini-md"><img src="https://agentmods.dev/badge/instructions/yeaight7/agent-powerups/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 724 This file is loaded in full into every session.
When invoked 724 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 $0.00724 $0.00724
Opus 5 $0.00362 $0.00362
Sonnet 5 $0.00145 $0.00145
Haiku 4.5 $0.00072 $0.00072

Measured 4d ago against content hash 7d0eefc7ec7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-powerups 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 4d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

Agent Powerups is an "Oh My Zsh-style" collection of reusable skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for coding agents. It provides a local-first CLI tool (apx) for browsing, validating, running, and explicitly installing these agent powerups.

Main Technologies:

  • Language: TypeScript
  • Runtime: Node.js (v20+)
  • Validation: Zod (for runtime type checking), Python (for repository validation scripts)

Architecture/Structure:

The repository is structured around different "asset classes" for coding agents:

  • skills/: Reusable agent workflows (e.g., systematic debugging).
  • mcp/: Local-first GitHub MCP configs.
  • commands/: Review-first markdown command prompts.
  • hooks/: Review-before-use hook recipes.
  • agents-md/: Starter templates.
  • src/cli/: The source code for the apx CLI tool.
  • scripts/: Python scripts for validating the repo's catalog and skills.
  • catalog.json: The central registry of all shipped assets.

Building and Running

The project relies on npm for dependency management and scripts.

Setup:

npm install

Build:

npm run build
# This runs `tsc` and a post-build script (`scripts/postbuild-apx-wrapper.mjs`).

Testing:

npm run test
# This builds the project and runs tests via `scripts/run-node-tests.mjs`.

Running the CLI:

After building, run npm link once to make apx available globally:

apx doctor
apx list
apx info <asset-name>
apx check <asset-name>

Repository Validation:

Run these scripts to validate the integrity of the project's assets (important before submitting PRs):

python scripts/validate-skills.py
python scripts/validate-catalog.py
python scripts/check-requirements.py

Development Conventions

TypeScript Configuration:

  • Strict Mode: Enabled ("strict": true). Ensure all types are properly defined and handle potential null or undefined values.
  • Target/Module: ES2022 and NodeNext.

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 724 tokens per session scan A 7d0eefc7ec7a

Subscribe to this mod's changes

agent-powerups GEMINI.md is an instructions file published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 724 tokens to every session, about $0.0036 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.