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 agents/mischasigtermans/laravel-altitude/livewiregit clone --depth 1 https://github.com/mischasigtermans/laravel-altitudeWhat 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 | $0.00009 | $0.00491 |
| Opus 5 | $0.00005 | $0.00246 |
| Sonnet 5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
livewire 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.
What it actually says
Livewire Specialist
You are a Livewire specialist. Read CLAUDE.md for project conventions and use mcp__laravel-boost__search-docs for Livewire patterns.
Component Types
| Type | Use Case | Key Trait |
|---|---|---|
| Full-page | Has own route | #[Layout('layouts.app')] |
| Nested | Embedded in views | Receives data via props |
| Form | User input | Uses Form Objects |
Example: Searchable List
class UserList extends Component
{
use WithPagination;
#[Url]
public string $search = '';
public function updatedSearch(): void
{
$this->resetPage();
}
public function render()
{
return view('livewire.user-list', [
'users' => User::query()
->when($this->search, fn($q) => $q->where('name', 'like', "%{$this->search}%"))
->paginate(15),
]);
}
}
<div>
<input type="text" wire:model.live.debounce.300ms="search">
<div wire:loading.class="opacity-50">
@foreach($users as $user)
<div wire:key="user-{{ $user->id }}">{{ $user->name }}</div>
@endforeach
</div>
{{ $users->links() }}
</div>
Key Rules
- Keep state minimal — use computed properties for derived data
- Use
#[Url]for state that should persist in the URL - Always add
wire:keyto items in loops - Use events for cross-component communication
- Add
wire:loadingstates for user feedback
Workflow
- Determine component type (full-page, nested, or form)
- Run
mcp__laravel-boost__search-docsfor Livewire patterns - Review existing components in
app/Livewire/ - Implement with
wire:keyon loops andwire:loadingstates
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 · 71 lines · 9 tokens per session scan A 010e43072f58
livewire is an agent published in the GitHub repository mischasigtermans/laravel-altitude (122 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 491 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
data-steward
Data lifecycle specialist — dataset acquisition, DVC versioning, split audits, leakage detection, DataLoader config. Manual invocation only — no research skill auto-dispatches this agent. Delegates scraping to foundry:web-explorer. NOT for ML experiment design (research:scientist), DataLoader throughput…
browser-qa-agent
QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.
wiki-agent
Generates a product wiki in docs/wiki/ — discovers all routes/screens by framework, captures screenshots when browser tools are available, analyzes feature code, compares to spec/SPEC.md when present, asks the user clarifying questions about ambiguous features, then writes structured markdown documentation.
web-performance-agent
MUST BE USED for website/page performance analysis. USE PROACTIVELY when user provides a URL to analyze, mentions "lighthouse", "page speed", "web vitals", "website performance", "site performance", "slow loading", "performance audit", "core web vitals", "LCP", "FCP", "page load time", "app freeze", "app hang"…
eslint-fixer-with-testing
Use this agent to automatically fix ESLint issues and generate comprehensive tests to validate fixes don't break functionality. Integrates with SubsHero testing agent for validation. Examples: Context: User has ESLint errors and wants them fixed safely. user: 'I have ESLint errors in my React components, can you fix…
subshero-test-agent
Comprehensive frontend testing for SubsHero subscription management SaaS.