system-information

system-information is a skill for Claude Code, Codex from symfony/ai-mate. It costs 65 tokens per session (731 once invoked), scanned A, a copy of mate-system-information, MIT.

A guide for checking which PHP packages and versions are actually installed. Composer is PHP's package manager, and composer.lock records the exact versions selected for a project.

In plain words
What is it for?
Use it to inspect one package, a group of packages, or the lock file while investigating version-specific PHP behavior. Use the separate environment-check guide for PHP itself, the operating system, or extensions.
Why use it?
It prevents debugging against version assumptions from composer.json, which states allowed ranges rather than the exact code running. This is useful when a class, method, or argument appears to be missing.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect one package, a group of packages, or the lock file while investigating version-specific PHP behavior. Use the separate environment-check guide for PHP itself, the operating system, or extensions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/symfony/ai-mate/system-information
About the project

Symfony AI Mate is a command-line assistant and MCP server that gives coding agents access to development tools tailored to a Symfony project. Developers and agents use it during development to inspect tools and run project-aware commands directly.

symfony/ai-mate · 42 stars · on GitHub · symfony.com

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.

Any agent
npx skills add symfony/ai-mate --skill system-information
Clone the repo
git clone --depth 1 https://github.com/symfony/ai-mate

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for system-information

README.md
[![agentmods](https://agentmods.dev/badge/skills/symfony/ai-mate/system-information/github.svg)](https://agentmods.dev/skills/symfony/ai-mate/system-information)
Your own site
<a href="https://agentmods.dev/skills/symfony/ai-mate/system-information"><img src="https://agentmods.dev/badge/skills/symfony/ai-mate/system-information/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.

agentmods 80×15 button for system-information

Your own site · 80×15
<a href="https://agentmods.dev/skills/symfony/ai-mate/system-information"><img src="https://agentmods.dev/badge/skills/symfony/ai-mate/system-information.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 98% copy Near-identical to another mod 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 5.1 $0.00065 $0.00731
Opus 5.5 $0.00026 $0.00292
Sonnet 5.5 $0.00013 $0.00146
Haiku 4.5 $0.00006 $0.00073

Measured 1mo ago against content hash fb3d84629533, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

system-information 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 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.

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.

Origin

This is a copy

98% identical to mate-system-information — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/system-information/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Information

Use this skill when a problem might depend on the installed dependency versions rather than the code: a bug that looks like a version mismatch, a method, argument, or class that does not exist in the release that is actually installed.

Capabilities

Need Use
PHP version, OS, OS family, loaded extensions php-environment-check skill
Installed version of a package composer show <vendor/package>
Installed versions of a family of packages composer show '<vendor>/<prefix>*'
Authoritative record of every installed version composer.lock (packages / packages-dev)

The php-environment-check skill reports the runtime only, it does not return package versions. Use Composer for those.

Resolving package versions

composer.json declares constraints (what is allowed); composer.lock records what is actually installed. For "what is really running", trust the lock, not the constraint.

  • One package: composer show symfony/console → installed version plus details.
  • A family: composer show 'symfony/ai-*' → every matching package and its version.
  • Machine-readable: composer show --format=json symfony/console.
  • No Composer binary, or you want the raw record: look the package up by name under packages in composer.lock and read its version field, but do not load the whole lock file into context.

Monorepo / path-repo note: locally linked packages (for example symlinked symfony/ai-* in this repository) report dev-main or a path reference instead of a semver tag, and that is the working copy, not a released version.

Diagnosing a version mismatch

  1. Identify the package behind the failing API; the namespace usually maps to it (Symfony\Component\Console\… → symfony/console).
  2. Read the installed version with composer show <package> (or from composer.lock).
  3. Compare it against the version the code expects: a method or argument added in a newer minor, or removed/renamed in a newer major, is the classic signature.
  4. Report the gap precisely: name the package, the installed version, and the required one: "symfony/console is 6.4 (installed), but the code calls a 7.1 API."

Read the full file on GitHub · 62 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. 1mo ago First seen · 62 lines · 65 tokens per session scan A fb3d84629533

Subscribe to this mod's changes

system-information is a skill published in the GitHub repository symfony/ai-mate (42 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 731 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to mate-system-information, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

bugfix-protocol

Protocolo sistemático de depuración en 6 fases. Enfoque estructurado ante errores con verificaciones rápidas, pruebas aisladas, regla de los 20 minutos y plantilla de informe de errores.

ellmos-ai/skills · 47 tokens

bugfix-protocol

A six-stage debugging process covering quick checks, diagnosis, isolated reproduction, a small fix, verification, and documentation. It also includes a rule to change approach or ask for help after 20 minutes without progress.

ellmos-ai/skills · 55 tokens

bugfix-protocol

Systematic 6-phase debugging protocol. Structured approach to bugs with quick checks, isolated testing, 20-minute rule, and bug report template.

ellmos-ai/skills · 34 tokens

bugfix-protocol

Systematic 6-phase debugging protocol. Structured approach to bugs with quick checks, isolated testing, 20-minute rule, and bug report template.

ellmos-ai/skills · 34 tokens

phpstan-analysis

Invoke BEFORE running PHPStan or fixing PHPStan errors. Covers error resolution strategy (refactoring > phpDoc > ignoring), common Nette error patterns, baseline management, and type tests. Use this whenever the user mentions PHPStan, static analysis, type errors, wants to suppress warnings, or manage the baseline …

nette/claude-code · 72 tokens

tracy-debugging

Invoke when fetching web pages from localhost, debugging PHP errors, or interpreting Tracy output (BlueScreen, Tracy Bar, dump). Read BEFORE running curl or Chrome to any local development PHP URL – with Tracy >= 2.12 and a detected agent, Tracy mirrors BlueScreen, Tracy Bar and dumps as markdown into the JS console…

nette/claude-code · 116 tokens