skills AGENTS.md

A Composer plugin for PHP projects that discovers AI-agent skills from installed packages and copies them into the project's .claude/skills folder. Composer is PHP's tool for managing packages and their dependencies.

In plain words
What is it for?
Use it to discover, list, and synchronise skills from Composer packages, using automatic, manually configured, or combined discovery modes.
Why use it?
It keeps skills from dependencies available in the project and protects existing skill files from being overwritten unless explicitly requested.

Instructions file for CodexOpenCode

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/agentsphp/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/agentsphp/skills

Made for: Codex, OpenCode.

Per session 331 This file is loaded in full into every session.
When invoked 331 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 $0.00331 $0.00331
Opus 5 $0.00166 $0.00166
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured yesterday against content hash a837ab10aa80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills AGENTS.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 yesterday.

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.

AGENTS.md · 53 lines

What it actually says

AGENTS.md

A Composer plugin for discovering and syncing AI agent skills from PHP packages.

Project Overview

This Composer plugin enables automatic discovery and installation of AI agent "skills" (prompts, instructions, templates) from PHP packages. It syncs skill files from dependencies into a project's .claude/skills directory.

Key Features

  • Package Discovery: Scans all installed Composer packages for skill definitions
  • Three Discovery Modes:
    • Discovery mode: Auto-discovers skills from folders (each folder = one skill, all files included)
    • Explicit mode: Skills defined manually in composer.json with file mappings
    • Mixed mode: Combine discovery with explicit overrides
  • Override Protection: Won't overwrite existing files unless --override flag is used
  • Flexible Configuration: Supports both skills and agentskills keys in composer.json

Commands

  • composer agents:skills:sync - Sync skills to the project
  • composer agents:skills:list - List all discovered skills

Requirements

  • PHP: >=8.2
  • Architecture: Composer plugin with PSR-4 autoloading

Development

# Install dependencies
make install

# Run all quality checks (phpstan + code style)
make qa

# Run code style checks
make cs

# Fix code style issues automatically
make csf

# Run static analysis (PHPStan level 9)
make phpstan

# Run test suite
make tests

# Generate code coverage
make coverage
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. yesterday First seen · 53 lines · 331 tokens per session scan A a837ab10aa80

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository agentsphp/skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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 2026-08-31.