filament-widgets

filament-widgets is a skill for Claude Code, Codex from leek/filament-agent-rules. It costs 47 tokens per session (417 once invoked), scanned A, original, MIT.

A set of instructions for building dashboard widgets in Filament, a Laravel tool for creating admin panels. It covers summary numbers, charts, tables, custom widgets, updates, loading, registration, and tests.

In plain words
What is it for?
Use it to create or review Filament widgets that show key figures, trends, records, or actions in an admin panel.
Why use it?
It helps keep widgets consistent with the project and avoids slow queries, missing permissions, and misplaced dashboard components.

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 to create or review Filament widgets that show key figures, trends, records, or actions in an admin panel.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/leek/filament-agent-rules/filament-widgets"><img src="https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-widgets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 417 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 $0.00047 $0.00417
Opus 5 $0.00023 $0.00209
Sonnet 5 $0.00009 $0.00083
Haiku 4.5 $0.00005 $0.00042

Measured 9d ago against content hash 39dfd4c22c91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

filament-widgets 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 9d 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-widgets/SKILL.md · 47 lines

What it actually says

Filament Widget Workflow

Use this skill for dashboard widgets and resource page widgets.

Read First

Resolve paths from the current project root:

  1. app/Filament/CLAUDE.md
  2. app/Filament/Widgets/CLAUDE.md
  3. app/Providers/Filament/CLAUDE.md for discovery and registration
  4. app/Filament/Resources/Tables/CLAUDE.md for table widgets
  5. tests/Feature/Filament/CLAUDE.md when tests are expected

Inspect nearby widgets, panel registration, model relationships, aggregate cost, cache conventions, and project chart styling.

Build Flow

  1. Choose the narrowest widget type:
    • stats overview for compact KPIs
    • chart widget for trend or distribution data
    • table widget for recent/actionable records
    • custom widget only when built-ins cannot represent the UI
  2. Keep widget queries scoped, indexed, and cacheable when expensive.
  3. Use lazy loading and polling deliberately. Poll only when data freshness is valuable and the query is cheap enough.
  4. Use semantic colors and icons that match the rest of the panel.
  5. For table widgets, reuse table rules: eager loading, authorization, filters, actions, and indexed search/sort.
  6. Register widgets through the panel or resource page surface already used by the project.
  7. Test renderability and the main displayed values, not every presentation detail.

Review Checklist

  • The widget has a clear audience and refresh strategy.
  • Aggregates do not scan large tables per request unnecessarily.
  • Visibility is policy-backed when data is sensitive.
  • Custom Blade is wrapped in Filament components and only used when needed.
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. 9d ago First seen · 47 lines · 47 tokens per session scan A 39dfd4c22c91

Subscribe to this mod's changes

filament-widgets is a skill published in the GitHub repository leek/filament-agent-rules (4 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 417 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.