Borrowing it
Nothing to install: this file belongs to agentsphp/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agentsphp/skills/master/AGENTS.mdgit clone --depth 1 https://github.com/agentsphp/skillsWrote 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/instructions/agentsphp/skills/agents-md)<a href="https://agentmods.dev/instructions/agentsphp/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/agentsphp/skills/agents-md/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/instructions/agentsphp/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/agentsphp/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00331 | $0.00331 |
| Opus 5.5 | $0.00132 | $0.00132 |
| Sonnet 5.5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
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 2mo 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.
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.jsonwith file mappings - Mixed mode: Combine discovery with explicit overrides
- Override Protection: Won't overwrite existing files unless
--overrideflag is used - Flexible Configuration: Supports both
skillsandagentskillskeys in composer.json
Commands
composer agents:skills:sync- Sync skills to the projectcomposer 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
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.
- 2mo ago First seen · 53 lines · 331 tokens per session scan A a837ab10aa80
skills AGENTS.md is an instructions file published in the GitHub repository agentsphp/skills (5 stars, last pushed 9mo ago), licensed MIT. It adds 331 tokens to every session, about $0.0013 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.
skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills AGENTS.mdagentsphp/skills | Instructions file | 5 | 9mo ago | MIT | A | 331 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |