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.
npx agentmods add instructions/symfony/ai-mate/agents-mdgit clone --depth 1 https://github.com/symfony/ai-mateWrote 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/symfony/ai-mate/agents-md)<a href="https://agentmods.dev/instructions/symfony/ai-mate/agents-md"><img src="https://agentmods.dev/badge/instructions/symfony/ai-mate/agents-md.svg" alt="Measured on agentmods" 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 | $0.02008 | $0.02008 |
| Opus 5 | $0.01004 | $0.01004 |
| Sonnet 5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade B, and why
ai-mate AGENTS.md scanned grade B 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 4d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- `src/Command/`: CLI commands (init, discover, clear-cache, debug:*, tools:*, resources:read) How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
AI agent guidance for the Mate component.
Component Overview
Standalone command-line assistant (vendor/bin/mate) that exposes project-aware development
tools to coding agents and developers. Tools are plain PHP methods annotated with the native
#[MateTool] attribute (resources/resource templates use #[MateResource] /
#[MateResourceTemplate]); Mate discovers them by reflection and runs them from the CLI. Does
not use MCP and does not integrate with the AI Bundle.
Architecture
Core Classes
- App: Console application builder
- ContainerFactory: DI container management with extension discovery
- ComposerExtensionDiscovery: Discovers extensions via
extra.ai-matein composer.json - ReflectionDiscoverer: Scans directories for
#[MateTool]/#[MateResource]/#[MateResourceTemplate]methods - SchemaGenerator / DocBlockParser: Build a JSON input schema from a method signature +
@paramPHPDoc - CapabilityRegistry: Feature-filtered lookup of discovered tools/resources
- ToolInvoker / ResourceReader: Resolve the handler from the DI container and invoke it
Attributes
Symfony\AI\Mate\Attribute\MateTool: marks a method as a CLI tool (paramsname,title,description)Symfony\AI\Mate\Attribute\MateResource: marks a method as a static resourceSymfony\AI\Mate\Attribute\MateResourceTemplate: marks a method as a templated resource
Key Directories
src/Command/: CLI commands (init, discover, clear-cache, debug:, tools:, resources:read)src/Container/: DI container managementsrc/Discovery/: Reflection-based discovery + schema generationsrc/Invocation/: Tool/resource invocation and argument castingsrc/Capability/: Built-in toolssrc/Bridge/: Embedded bridge packages (Symfony, Monolog)
Bridges
- Symfony Bridge (
src/Bridge/Symfony/): Container introspection and profiler access - Monolog Bridge (
src/Bridge/Monolog/): Log search and analysis
Essential Commands
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.
- 4d ago First seen · 183 lines · 2,008 tokens per session scan B 267038f39e28
ai-mate AGENTS.md is an instructions file published in the GitHub repository symfony/ai-mate (33 stars, last pushed 4d ago), licensed MIT. It adds 2,008 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ai-demo AGENTS.md
Instructions for symfony/ai-demo, covering agents.md, project overview, development commands, setup and vector store must be set up before indexing.
ai-demo CLAUDE.md
Instructions for symfony/ai-demo: This file provides guidance to Claude Code (claude.ai/code) when working with code in the Symfony AI demo application.
instructor-php AGENTS.md
AGENTS.md instructions for cognesy/instructor-php, covering key reference files, monorepo root, individual subpackages, code style and agents package style.
ec-cube AGENTS.md
AGENTS.md instructions for EC-CUBE/ec-cube, covering agents.md, ai 向けドキュメント インデックス（定義ファイルと読み込み）, 定義ファイルを増やすときの原則, プロジェクト概要 and 技術スタック.
laravel-mcp-server AGENTS.md
Instructions for opgginc/laravel-mcp-server, covering common commands, testing and quality assurance, mcp tool development, mcp notification development and configuration publishing.
ec-cube CLAUDE.md
Claude Code instructions for EC-CUBE/ec-cube, a project described as: EC-CUBE is the most popular e-commerce solution in Japan.