filament-dashboard

filament-dashboard is a skill for Claude Code, Codex from leek/filament-agent-rules. It costs 48 tokens per session (999 once invoked), scanned A, original, MIT.

A guide for building Filament dashboards and custom panel pages, including widgets, tabs, notices, embedded Livewire components, navigation, and page actions.

In plain words
What is it for?
Use it when creating or reviewing dashboards, custom admin pages, widgets, page layouts, navigation, metrics, and page-specific actions.
Why use it?
It helps decide whether existing dashboard parts are enough and keeps custom pages organized, responsive, and consistent with the panel.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

Good fit Use it when creating or reviewing dashboards, custom admin pages, widgets, page layouts, navigation, metrics, and page-specific actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leek/filament-agent-rules/filament-dashboard
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.

Any agent
npx skills add leek/filament-agent-rules --skill filament-dashboard
Clone the repo
git clone --depth 1 https://github.com/leek/filament-agent-rules

Made for: Claude Code, Codex.

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 filament-dashboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-dashboard/github.svg)](https://agentmods.dev/skills/leek/filament-agent-rules/filament-dashboard)
Your own site
<a href="https://agentmods.dev/skills/leek/filament-agent-rules/filament-dashboard"><img src="https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-dashboard/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.

agentmods 80×15 button for filament-dashboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/leek/filament-agent-rules/filament-dashboard"><img src="https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00999
Opus 5 $0.00024 $0.00500
Sonnet 5 $0.00010 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured 10d ago against content hash 1276f6b97dcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

filament-dashboard 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 10d 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.

.agents/skills/filament-dashboard/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Filament Dashboard And Page Workflow

Use this skill for dashboards and custom panel pages. Prefer composing existing Filament widgets, schema components, and embedded Livewire components before building bespoke Blade-heavy pages.

Read First

Resolve paths from the current project root:

  1. app/Filament/CLAUDE.md
  2. app/Filament/Pages/CLAUDE.md
  3. app/Filament/Widgets/CLAUDE.md
  4. app/Providers/Filament/CLAUDE.md
  5. app/Filament/Actions/CLAUDE.md when the page has actions
  6. tests/Feature/Filament/CLAUDE.md when tests are expected

Inspect existing panel pages, dashboard widgets, navigation groups, panel discovery paths, and global defaults.

Build Flow

  1. Decide whether the request is really a dashboard page. If the standard panel dashboard plus widgets is enough, register widgets instead of creating a page.
  2. If a custom page is needed, keep standard Filament page behavior and compose custom content through schema components, widgets, or embedded Livewire.
  3. Use tabs, sections, grids, callouts, and prime components for layout and explanatory content.
  4. Keep expensive metrics in widgets or query objects with clear caching, polling, and lazy-loading behavior.
  5. Use page header actions for page-level commands and delegate domain work.
  6. Register navigation metadata consistently with nearby pages and clusters.
  7. Add render tests and targeted assertions for critical widgets/actions.

Avoid

  • Reimplementing a resource page as a custom page when only one area is custom.
  • Large Blade views that bypass Filament theming and authorization.
  • Dashboard queries that run expensive aggregates on every request without caching, filters, or lazy loading.

Deep Pattern: Tabbed Dashboard Pages

When a dashboard swaps widget sets without leaving the route, drive the tabs from a single array and keep widget references as class strings so Livewire can serialize state between requests.

final class Analytics extends Page
{
    protected static string $view = 'filament.admin.pages.analytics';

    public string $activeTab = 'overview';

    public function getTabs(): array
    {
        return [
            [
                'key' => 'overview',
                'title' => 'Overview',
                'icon' => 'heroicon-o-home',
                'widgets' => [OrdersOverview::class, RevenueChart::class],
            ],
            [
                'key' => 'revenue',
                'title' => 'Revenue',
                'icon' => 'heroicon-o-currency-dollar',
                'widgets' => [RevenueBreakdown::class, TopProducts::class],
            ],
        ];
    }

    public function getActiveTabData(): ?array
    {
        return collect($this->getTabs())->firstWhere('key', $this->activeTab);
    }
}

Read the full file on GitHub · 124 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. 10d ago First seen · 124 lines · 48 tokens per session scan A 1276f6b97dcd

Subscribe to this mod's changes

filament-dashboard is a skill published in the GitHub repository leek/filament-agent-rules (4 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 999 once invoked, about $0.0002 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.