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 skills/fusengine/agents/php-language-modernnpx skills add fusengine/agents --skill php-language-moderngit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/php-language-modern)<a href="https://agentmods.dev/skills/fusengine/agents/php-language-modern"><img src="https://agentmods.dev/badge/skills/fusengine/agents/php-language-modern.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01341 |
| Opus 5 | $0.00024 | $0.00671 |
| Sonnet 5 | $0.00010 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
php-language-modern 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 today.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Its focus is language features that LLMs frequently get wrong or write in a pre-8.0 style — most notably using docblock annotations (@Route, @ORM\Column) instead of native #[Attribute] syntax, which is the #1 mistake this skill exists to prevent.
Do NOT use this skill for coding style, PSR compliance, or autoloading — that is php-standards. Do NOT use it for Laravel-specific syntax conventions — that lives in the Laravel plugin.
Modern PHP Language (8.1 → 8.5)
Agent Workflow (MANDATORY)
Before writing PHP, spawn 3 agents in parallel, one Agent call each with a name:
- fuse-ai-pilot:explore-codebase - Detect the project's minimum PHP version (
composer.jsonrequire.php, CI matrix) - fuse-ai-pilot:research-expert - Verify a feature's version + syntax on php.net before using it
- mcp__context7__query-docs - Cross-check idiomatic usage
After writing, run fuse-ai-pilot:sniper for validation.
Overview
| Feature | Since | Use it for |
|---|---|---|
| Enums (backed + methods/interfaces) | 8.1 | Closed sets of values with behavior |
First-class callable syntax f(...) |
8.1 | Passing callables without strings |
| readonly properties / classes | 8.1 / 8.2 | Immutable value objects / DTOs |
#[\Override] |
8.3 | Fail-fast on broken inheritance |
Property hooks get/set |
8.4 | Computed/validated properties, no getter/setter boilerplate |
Asymmetric visibility public private(set) |
8.4 (static: 8.5) | Public read, restricted write |
Lazy objects newLazyGhost() |
8.4 | Deferred initialization in DI containers |
Pipe operator |> |
8.5 | Left-to-right data transformation chains |
clone() function + $withProperties |
8.5 | Immutable "with" updates, incl. readonly |
#[\NoDiscard] |
8.5 | Enforce return-value consumption |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed c4eb00038eb7
- yesterday First seen · 108 lines · 49 tokens per session scan A 2dd3be5e53ca
php-language-modern is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,341 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 2026-09-03.
Other skills, from other repositories
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…
craft-php-guidelines
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers…
craft-pest
Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php +…
building-telegram-bots
Writes correct, version-aware Telegram bot code. Use when writing, extending, or debugging a Telegram bot in python-telegram-bot, aiogram, grammY, or Telegraf. Not for Telegram client API (TDLib), languages other than Python and Node.js, or non-Telegram platforms.
php-cleanup
This skill should be used when the user asks to "find unused PHP code", "clean up dead code", "find unused Composer dependencies", "find unused imports", "remove dead PHP code", "run composer unused", "check for missing dependencies", "detect unused classes", "detect unused methods", "clean up use statements", "audit…
symfony-domain-modeling
Symfony domain modeling — entities, value objects, domain events, aggregates, domain exceptions. Triggers on: entity, value object, domain event, aggregate, domain exception, domain model, domain logic, business rule, invariant.