Claude-PHP-SDK copilot-instructions.md

Project instructions for a framework-independent PHP software development kit (SDK) for the Claude API. An SDK is a library that helps PHP programs call a service without building every network request themselves.

In plain words
What is it for?
Use them when adding Claude API endpoints, implementing synchronous or asynchronous clients, handling errors, or organizing PHP classes and dependencies.
Why use it?
They explain the intended API coverage, PHP standards, error handling, and client structure so contributors can keep the library compatible with its Python counterpart and PHP frameworks.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/claude-php/claude-php-sdk/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/claude-php/Claude-PHP-SDK

Made for: GitHub Copilot.

Per session 3,375 This file is loaded in full into every session.
When invoked 3,375 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03375 $0.03375
Opus 5 $0.01688 $0.01688
Sonnet 5 $0.00675 $0.00675
Haiku 4.5 $0.00337 $0.00337

Measured 2d ago against content hash 472e14d05927, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Claude-PHP-SDK copilot-instructions.md 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 2d 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.

.github/copilot-instructions.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for Claude PHP SDK

This is a PHP clone of the Anthropic Python SDK (https://github.com/anthropics/anthropic-sdk-python), designed as a universal, framework-agnostic PHP SDK following PSR standards for easy integration with Laravel, Symfony, Slim, and other frameworks.

Project Goals

  • API Parity: Full implementation of latest Claude API endpoints (Messages, Files, Batches, Models APIs)
  • PSR Compliance: Follow PHP Standards Recommendations (PSR-12 coding style, PSR-11 containers for DI)
  • Dependency Injection Ready: Support framework-agnostic DI patterns for seamless integration
  • Latest Models & Features: Support Claude Sonnet 4.5, Haiku 4.5, Opus 4.1, plus extended thinking, streaming, tool use, vision, embeddings
  • Async & Sync Support: Both synchronous and asynchronous clients via Amphp/PHP async patterns
  • Python SDK Parity: Mirror error handling, configuration, and patterns from the official Python SDK

Architecture & Core Components

Directory Structure (to be created)

Claude-PHP-SDK/
├── src/
│   ├── Anthropic.php           # Main client class (factory/entry point)
│   ├── Client/                 # Core HTTP client implementation
│   ├── Messages/               # Messages API (main resource)
│   ├── Files/                  # Files API resource
│   ├── Batches/                # Batch processing API
│   ├── Models/                 # Models API
│   ├── Embeddings/             # Embeddings API
│   ├── Resources/              # Base resource classes
│   ├── Requests/               # Request builders/DTOs
│   ├── Responses/              # Response objects & streaming
│   └── Contracts/              # Interfaces for DI
├── tests/
├── composer.json
└── README.md

Key Architectural Patterns

  1. Client Pattern: Anthropic class acts as main entry point, returns resource instances

    $client = new Anthropic(apiKey: $key);
    $response = $client->messages->create([...]);
    

Read the full file on GitHub · 374 lines

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. 2d ago First seen · 374 lines · 3,375 tokens per session scan A 472e14d05927

Subscribe to this mod's changes

Claude-PHP-SDK copilot-instructions.md is an instructions file published in the GitHub repository claude-php/Claude-PHP-SDK (146 stars, last pushed 3mo ago), licensed MIT. It adds 3,375 tokens to every session, about $0.0169 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 2026-08-30.