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.
npx agentmods add instructions/power-components/livewire-powergrid/gemini-mdgit clone --depth 1 https://github.com/Power-Components/livewire-powergridWrote 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.
[](https://agentmods.dev/instructions/power-components/livewire-powergrid/gemini-md)<a href="https://agentmods.dev/instructions/power-components/livewire-powergrid/gemini-md"><img src="https://agentmods.dev/badge/instructions/power-components/livewire-powergrid/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00998 | $0.00998 |
| Opus 5 | $0.00499 | $0.00499 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
livewire-powergrid 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.
This is a copy
100% identical to livewire-powergrid CLAUDE.md — 0 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerGrid 7.x AI Guidelines
This document outlines the architectural guidelines for AI agents working with PowerGrid 7.x.
1. Core Principles
The 7.x version prioritizes simplicity, an adaptable native skeleton, and independent test components, discarding legacy dependencies.
- PHP: 8.3+
- Livewire: 4.0+
- Tailwind CSS: 4.x+
- Removed Legacy Dependencies: Bootstrap, third-party select integrations, Lazy components, and Pulse files.
- New Required Package:
power-components/partials(imported locally).
2. Architecture & Theming
- Root
/themesDirectory: This folder is strictly for PHP classes (Tailwind, DaisyUI, Flux). - Strict Key Mapping: All CSS/theme logic is managed through a new unified
struct()method. - Absolute Separation: HTML structure is completely separated from visual styles.
3. Views
- No Theme Conditionals: Do not use logic like
@if($theme == 'bootstrap')in Blade files. - Micro-files Strategy: Table views are divided into single-purpose micro-files (e.g.,
index.blade.php,tbody.blade.php,td.blade.php). - Directives: Rely strictly on
@theme()directives.
4. Server-Side Actions
- No Cache or JS processing for Actions: Action logic and buttons are no longer processed via JavaScript or cached.
- Full Blade Rendering: Actions are fully rendered as server-side Blade components/fragments via
renderActions().
5. Performance & Partials
- Livewire DOM Isolation: Use the
power-components/partialsfragments to isolate DOM updates and boost performance. - Hot Zones: There are three demarcated Hot Zones for updates:
pg-tbodypg-paginationpg-filters
6. Testing Strategy
- Self-sufficient Tests: Tests must be independent and immune to themes.
- Core Focus: Focus testing strictly on core engine capabilities: Search, Filters, Order, and Pagination.
- No Global Fixtures: Build mini-components at runtime within the test files instead of using global fixtures.
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.
- 4d ago First seen · 96 lines · 998 tokens per session scan A e6cd4f7ca2b6
livewire-powergrid GEMINI.md is an instructions file published in the GitHub repository Power-Components/livewire-powergrid (1,693 stars, last pushed 2d ago), licensed MIT. It adds 998 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to livewire-powergrid CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
real-estate-laravel CLAUDE.md
Instructions for liberusoftware/real-estate-laravel, covering claude.md, shape of this repository, where a package is edited, commands and a single package's own suite, standalone.
real-estate-laravel AGENTS.md
Instructions for liberusoftware/real-estate-laravel, covering lerd, a local php development environment, architecture, dns modes, mcp tools and key conventions.
real-estate-laravel copilot-instructions.md
Instructions for liberusoftware/real-estate-laravel, covering lerd, a local php development environment, architecture, dns modes, mcp tools and key conventions.
relaticle AGENTS.md
AGENTS.md instructions for relaticle/relaticle, covering architecture, module boundaries (enforced by tests/arch/archtest.php), actions (the write path), i18n enforcement and chat.
relaticle CLAUDE.md
Claude Code instructions for relaticle/relaticle, covering architecture, module boundaries (enforced by tests/arch/archtest.php), actions (the write path), i18n enforcement and chat.
relaticle GEMINI.md
Gemini CLI instructions for relaticle/relaticle, covering architecture, module boundaries (enforced by tests/arch/archtest.php), actions (the write path), i18n enforcement and chat.