Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PracticalSwan/agent-skillsnpx agentmods add skills/practicalswan/agent-skills/php-developmentWrote 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/practicalswan/agent-skills/php-development)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/php-development"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/php-development/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/practicalswan/agent-skills/php-development"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/php-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 894 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00051 | $0.06662 |
| Opus 5.5 | $0.00020 | $0.02665 |
| Sonnet 5.5 | $0.00010 | $0.01332 |
| Haiku 4.5 | $0.00005 | $0.00666 |
Grade A, and why
php-development scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
$user = $stmt->fetch(PDO::FETCH_ASSOC); How it starts
The opening of the file, as written. The whole thing — 924 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PHP Development
Optimized for current PHP 8.x releases, PHPUnit 11+, Composer 2.x, and PDO-backed MySQL or MariaDB apps.
Expert guidance for building high-quality PHP applications with PHP 8.0+, PDO for secure database access, RESTful API design, and XAMPP environment configuration following official PHP documentation at https://php.net.
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/php-developmentand restart Codex after major changes.
MCP Availability And Fallback
Preferred MCP Server: None required
- Fallback prompt: "Use the PHP Development skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding."
- Do not claim an MCP operation was used when the active host does not expose it.
- Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.
Anti-Patterns
- Interpolating SQL directly: Prepared statements are the baseline for correctness and security in PHP data access.
- Mixing request parsing, business rules, and rendering: Tightly coupled scripts are harder to test and evolve into APIs.
- Assuming validation alone prevents XSS: Output encoding still matters when user-controlled content is rendered back to HTML.
Verification Protocol
Before claiming "skill applied successfully":
- Pass/fail: The PHP Development implementation names the target runtime, framework version, and affected files.
- Pass/fail: Build, lint, test, or equivalent local validation is run for the changed surface.
- Pass/fail: Edge cases for errors, dependency drift, and environment differences are addressed or explicitly out of scope.
- Pressure-test scenario: Apply the workflow to a change that passes happy-path tests but fails one boundary condition.
- Success metric: Zero untested success claims; every implementation claim maps to a command or artifact.
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 Changed · -1 lines 86a8b52d47ef
- 1mo ago Changed 228cfd8e4893
- 1mo ago First seen · 925 lines · 51 tokens per session scan A bbf7b017631c
php-development is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 6,662 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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-laravel
Use this skill when building Laravel applications — MVC structure, Eloquent ORM, service layer, validation, queues, and testing. This skill enforces: thin controllers, service layer for business logic, Eloquent best practices with eager loading, form request validation, and queue job structure. Requires Laravel 10+ or…
PHP Patterns
Use this skill when working in modern PHP (8+) codebases and you want predictable structure, safe IO boundaries, and maintainable application/service design.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
integration-fixture
Add a .test integration fixture for one behavior.
Behat BDD Testing
PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.
nestjs
Use when building or structuring a NestJS backend — feature modules, providers and DI wiring, provider scopes and request-lifecycle order, where to bind guards/pipes/interceptors/filters, and testing with Test.createTestingModule. NOT a bare Express/Fastify service with no DI (that is nodejs), NOT framework-agnostic…