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/pushery/wirekit/agents-mdgit clone --depth 1 https://github.com/pushery/wirekitWhat 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 | $0.00721 | $0.00721 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
wirekit AGENTS.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.
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.
WireKit — guidance for AI coding assistants
WireKit is a free, MIT-licensed UI component library for Laravel Livewire
(pushery/wirekit, namespace Pushery\WireKit, component prefix
<x-wirekit::*>). If you are an AI coding assistant generating Blade, CSS, or
PHP for a project that depends on WireKit, read this first — it is the
tool-neutral entry point, discoverable without a Cursor-specific config.
Discover the API before authoring — do not guess
Run these from the project root for authoritative, version-matched data instead
of grepping vendor/:
php artisan wirekit:list # every component, grouped by category
php artisan wirekit:show <component> # props, slots, sub-components, docs URL
php artisan wirekit:icons # every icon alias, grouped by preset
php artisan wirekit:export-json --pretty # full machine-readable component manifest
php artisan wirekit:install also writes a .wirekit-schema.json manifest to the
project root — read it for zero-configuration autocomplete. For an MCP-native
editor, the WireKit MCP server exposes the same catalog as live tools.
Core conventions
- Components use the double-colon anonymous-namespace syntax —
<x-wirekit::button>, never a single colon. cardis a frame with no intrinsic padding — put content inside<x-wirekit::card.body>(orcard.header/card.footer).- Color comes from the Intent × Surface variant system plus the
--*-wk-*design tokens. Never hardcode colors, never use Tailwind palette classes (gray-*,zinc-*), and never use thedark:prefix inside WireKit markup — tokens auto-switch under the.darkclass. - Spacing/rhythm comes from
stack/row/grid/sectionplus theirgapprop (the prop isgap, notspace). Components carry no outer margins, so do not hand-rollspace-y-*/mb-*. - For a signed-in dashboard, compose the
app-shell+sidebar+header+mainsystem.navbaris a separate, alternative top-nav shell with its own mobile menu — do not nest it inside the app-shell header. - Icons use
<x-wirekit::icon name="..." size="..." />— neverclass="h-N w-N". To put an icon inside abuttonorlink, use theiconLeft/iconRightslots —buttonhas NOiconprop (a strayicon="…"renders nothing and leaks a dead attribute).iconIS a prop on ~20 other components (e.g.sidebar.item), so don't carry the attribute form over tobutton/badge.
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.
- yesterday First seen · 54 lines · 721 tokens per session scan A 3ea3407a6d89
wirekit AGENTS.md is an instructions file published in the GitHub repository pushery/wirekit (10 stars, last pushed yesterday), licensed MIT. It adds 721 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.
Other instructions, from other repositories
slate AGENTS.md
Instructions for electrikhq/slate, covering electrik slate — agent notes, stack, install reminder, authoring rules and ai sources.
livewire-powergrid CLAUDE.md
Instructions for Power-Components/livewire-powergrid, covering powergrid 7.x ai guidelines, 1. core principles, 2. architecture & theming, 3. views and 4. server-side actions.
aura-ui AGENTS.md
Instructions for BlueStarSystem/aura-ui, covering agents.md — aura ui, what this is, how to use components, livewire integration and accessibility (do not regress).
aura-ui CLAUDE.md
Instructions for BlueStarSystem/aura-ui, covering aura ui — claude code context, architecture, key directories, commands and free/pro split.
livewire-powergrid GEMINI.md
Instructions for Power-Components/livewire-powergrid, covering powergrid 7.x ai guidelines, 1. core principles, 2. architecture & theming, 3. views and 4. server-side actions.
undocumented-laravel-book CLAUDE.md
Claude Code instructions for robertogallea/undocumented-laravel-book, covering claude.md - operating guide for this project, 1. project overview, 2. folder structure, 3. reference files and reading order and 4. writing conventions (mandatory).