php

php is a skill for Claude Code from kouroshez/coding-os. It costs 155 tokens per session (1,361 once invoked), scanned A, original, Apache-2.0.

A guide to writing and reviewing modern PHP 8.x code, including its type system, Composer package management, and common web security risks.

In plain words
What is it for?
Use it when building, reviewing, or modernizing PHP applications, configuring Composer and autoloading, or improving PHP security.
Why use it?
It helps avoid older PHP patterns that can cause SQL injection, cross-site scripting, unsafe data handling, or hard-to-maintain code.

Skill for Claude Code

Written for Claude Code: paths in frontmatter.

Good fit Use it when building, reviewing, or modernizing PHP applications, configuring Composer and autoloading, or improving PHP security.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kouroshez/coding-os/php
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 kouroshez/coding-os --skill php
Clone the repo
git clone --depth 1 https://github.com/kouroshez/coding-os

Made for: Claude Code.

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 php

README.md
[![agentmods](https://agentmods.dev/badge/skills/kouroshez/coding-os/php/github.svg)](https://agentmods.dev/skills/kouroshez/coding-os/php)
Your own site
<a href="https://agentmods.dev/skills/kouroshez/coding-os/php"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/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.

agentmods 80×15 button for php

Your own site · 80×15
<a href="https://agentmods.dev/skills/kouroshez/coding-os/php"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/php.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,361 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 $0.00155 $0.01361
Opus 5.5 $0.00062 $0.00544
Sonnet 5.5 $0.00031 $0.00272
Haiku 4.5 $0.00015 $0.00136

Measured 1mo ago against content hash 79ccfa93321a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan_php_smells.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/core/skills/php/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modern PHP

PHP earned its insecure reputation from a decade of mysql_query("...$_GET..."). Modern PHP (8.3+) is a typed, fast, well-tooled language — the craft is using its type system and PDO, and never trusting $_GET/$_POST/$_REQUEST near a query, a shell, or output.

Scan PHP for the classic dangerous patterns: python3 scripts/scan_php_smells.py src/**/*.php

Use the 8.x type system

// Wrong — untyped, mutable, verbose, no guarantees
class Money {
  public $amount;
  public $currency;
  function __construct($amount, $currency) { $this->amount = $amount; $this->currency = $currency; }
}

// Correct — typed, readonly, promoted constructor params, enum
enum Currency: string { case USD = 'USD'; case EUR = 'EUR'; }

final class Money {
  public function __construct(
    public readonly int $amount,            // promoted + readonly = immutable
    public readonly Currency $currency,
  ) {}
}

declare(strict_types=1); at the top of every file makes type declarations enforced, not coerced. Use readonly for value objects, enum for fixed sets, match (exhaustive, strict ===) over switch, and union/nullable types. Detail → references/modern-php.md.

Never build SQL from request data

// Wrong — SQL injection, the canonical PHP breach
$id = $_GET['id'];
$db->query("SELECT * FROM users WHERE id = $id");

// Correct — PDO prepared statement; the value never touches the SQL text
$stmt = $pdo->prepare('SELECT * FROM users WHERE id = ?');
$stmt->execute([$_GET['id']]);

Use PDO with prepared statements (or an ORM) for every query. The legacy mysql_* functions are removed; mysqli without bound params is the same hole. Query craft (parameterization, joins, plans) is owned by sql-authoring.

Escape on output, validate on input

// Wrong — reflected XSS
echo "<p>Hello {$_GET['name']}</p>";

// Correct — escape for the output context
echo '<p>Hello ' . htmlspecialchars($_GET['name'], ENT_QUOTES, 'UTF-8') . '</p>';

Read the full file on GitHub · 117 lines

Files

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.

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. 1mo ago First seen · 117 lines · 155 tokens per session scan A 79ccfa93321a

Subscribe to this mod's changes

php is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 155 tokens to every session and 1,361 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories