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 ericrisco/rsc-harness --skill phpgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/php)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/php"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/php/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/ericrisco/rsc-harness/php"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/php.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.04181 |
| Opus 5.5 | $0.00039 | $0.01672 |
| Sonnet 5.5 | $0.00019 | $0.00836 |
| Haiku 4.5 | $0.00010 | $0.00418 |
Grade A, and why
php 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 1mo 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modern PHP (8.x)
Write PHP the way the 2025-2026 ecosystem does: declare(strict_types=1) at the top of
every file, typed everything, Composer-first, statically analyzed at the top level — not
the way a 2015 WordPress plugin did. This skill owns the language and its
framework-agnostic ecosystem: the type system, Composer + PSR-4, PER-CS style, the PSR
interop interfaces, and the quality toolchain.
Version targeting. Floor is 8.3 (security-only, the lowest you should support).
Default new code to 8.4 (property hooks, asymmetric visibility). Use 8.5 features
(|>, clone with, array_first/array_last, #[\NoDiscard]) only when the deploy
runtime is confirmed 8.5+ — 8.5 released 2025-11-20. 7.x and 8.0-8.2 are EOL; never target
them.
When to use
- Authoring/reviewing/refactoring any
.phpfile or acomposer.json. - Designing classes: enums, DTOs, value objects, readonly classes, interfaces, traits.
- Standing up a vanilla-PHP project: Composer, PSR-4 autoload, namespaces, entrypoint.
- Wiring quality gates: PHPStan/Psalm, Pint/PHP-CS-Fixer, Rector, CI.
- Modernizing legacy 5.x/7.x patterns to 8.x idioms.
- Picking framework-agnostic libs (Symfony components, Guzzle, Monolog, Doctrine DBAL, league/*) and PSR-compatible interop.
When NOT to use (delegate)
| The ask is about | Route to | This skill keeps |
|---|---|---|
| Eloquent, Blade, Artisan, container bindings, queues | laravel | the PHP underneath Laravel only |
WP hooks, the loop, wp_*, $wpdb |
wordpress | nothing WP-specific |
| Shopify app/theme SDK work | shopify | nothing Shopify-specific |
| OWASP threat modeling, authz/abuse review | secure-coding | PHP-native controls (PDO, password_hash, escaping) |
| REST resource naming, status-code contract as a discipline | api-design | PHP request/response code only |
| DB schema/index tuning | mysql / postgresdb | PDO usage from the PHP side |
The type system, Composer, PSR, and the static-analysis toolchain are canonical here and nowhere else in the catalog.
What ships with it
5 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.
- 1mo ago First seen · 398 lines · 97 tokens per session scan A ac309696b5f3
php is a skill published in the GitHub repository ericrisco/rsc-harness (237 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 4,181 once invoked, about $0.0004 per session on Opus 5.5. 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
php-expert
Expert-level PHP development with PHP 8+, Laravel, Composer, and modern best practices. Use when the user mentions Laravel, Composer, Symfony, PHPUnit, or PSR standards, or when the task involves PHP 8+ Features, Object-Oriented PHP, Modern PHP, or Constructor Property Promotion.
neuron-symfony-integration
Integrate Neuron AI agents into a Symfony 8 app, from packages, env keys, a Doctrine migration for the Neuron tables and services.yaml wiring to a shared agent bound per request with for(), a thread voter, JSON and AG-UI (CopilotKit) or useChat streaming with StreamedResponse, reload with pending approvals, Messenger…
laravel-patterns
Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.
laravel-security
Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.
laravel-plugin-discovery
Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.
create-module
Scaffold a new Marko module — a self-contained Composer package with composer.json, namespaced src/, and Pest tests. Use this skill whenever the user asks to create, add, or scaffold a new Marko module or package. Concrete triggers: 'create a module named payment', 'scaffold an acme/blog package', 'add a new module…