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 skills add leek/filament-agent-rules --skill filament-actionsgit clone --depth 1 https://github.com/leek/filament-agent-rulesWrote 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/skills/leek/filament-agent-rules/filament-actions)<a href="https://agentmods.dev/skills/leek/filament-agent-rules/filament-actions"><img src="https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-actions/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.
<a href="https://agentmods.dev/skills/leek/filament-agent-rules/filament-actions"><img src="https://agentmods.dev/badge/skills/leek/filament-agent-rules/filament-actions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00050 | $0.00767 |
| Opus 5 | $0.00025 | $0.00383 |
| Sonnet 5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
filament-actions 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filament Action Workflow
Use this skill for UI actions rendered by Filament. Do not confuse these with
domain actions under app/Actions/; a Filament action should call domain logic,
not contain it.
Read First
Resolve paths from the current project root:
app/Filament/CLAUDE.mdapp/Filament/Actions/CLAUDE.mdapp/Filament/Resources/Tables/CLAUDE.mdfor table actionsapp/Filament/Resources/Schemas/CLAUDE.mdfor modal schemastests/Feature/Filament/CLAUDE.mdwhen tests are expected
Check global action defaults in service providers before adding modal, color, slide-over, icon, or confirmation settings locally.
Build Flow
- Identify the action surface:
- page header action
- table header action
- table record action
- toolbar or bulk action
- schema action
- notification action
- Use
Filament\Actions\*imports. - Use
schema([...])orsteps([...])for action modal input. - Add
requiresConfirmation()for destructive or irreversible actions. - Set visibility and authorization from policies or explicit abilities.
- Delegate non-trivial work to an app-level action/service.
- Add success and failure notifications for work that changes state or can fail.
- Chunk or queue bulk work that can touch many records.
- Extract the action class only when it is reused or too large inline.
Review Checklist
- The action has the right scope for the data it needs.
- The UI does not show unauthorized actions.
- Modal input is validated by the schema.
- Bulk actions are authorized and do not process huge selections in one request.
- Tests call the action and cover validation/error paths where meaningful.
Deep Pattern: Reuse Across Surfaces
An extracted Action can be reused on page headers, table rows, and relation
manager headers when its setup does not assume a record exists. Keep bulk
behavior in a separate BulkAction class.
protected function getHeaderActions(): array
{
return [
EmailCustomerAction::make(),
];
}
$table->recordActions([
EmailCustomerAction::make(),
]);
$table->toolbarActions([
BulkActionGroup::make([
EmailCustomersBulkAction::make(),
]),
]);
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.
- 10d ago First seen · 110 lines · 50 tokens per session scan A daf74b1d27f6
filament-actions is a skill published in the GitHub repository leek/filament-agent-rules (4 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 767 once invoked, about $0.0003 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 skills, from other repositories
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
miniapp-dev
A development guide for BitFun MiniApps, which are small applications that run inside BitFun. It covers creating new MiniApps as well as maintaining the MiniApp framework.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…
ss-copy
Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.