ai-demo: Skill for Claude Code

.agents/skills/mate-system-information/SKILL.md

mate-system-information is a skill for Claude Code, Codex from symfony/ai-demo. It costs 66 tokens per session (732 once invoked), scanned A, original, MIT.

A guide for finding the dependency versions actually installed in a PHP project. Dependencies are external packages that an application uses, and Composer manages them.

In plain words
What is it for?
Use it when a PHP method, argument, or class seems unavailable, to check Composer package versions and separate package-version problems from PHP runtime problems.
Why use it?
It prevents debugging against versions that are only allowed by the project configuration but are not really installed. The lock file records the exact versions in use.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is symfony/ai-demo's own configuration. It tells Claude Code and Codex how to work on ai-demo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-demo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to symfony/ai-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/symfony/ai-demo/main/.agents/skills/mate-system-information/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/symfony/ai-demo

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 mate-system-information

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/symfony/ai-demo/mate-system-information"><img src="https://agentmods.dev/badge/skills/symfony/ai-demo/mate-system-information.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00066 $0.00732
Opus 5 $0.00033 $0.00366
Sonnet 5 $0.00013 $0.00146
Haiku 4.5 $0.00007 $0.00073

Measured 10d ago against content hash a6bf5049edcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mate-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 10d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/mate-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. 10d ago First seen · 62 lines · 66 tokens per session scan A a6bf5049edcf

Subscribe to this mod's changes

mate-system-information is a skill published in the GitHub repository symfony/ai-demo (47 stars, last pushed 10d ago), licensed MIT. It adds 66 tokens to every session and 732 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

system-information

Resolve which dependency versions are actually installed, from composer show and composer.lock, when diagnosing version-specific behavior such as a method, argument or class that does not exist in the release that is really running. For the PHP runtime itself (version, OS, loaded extensions) use the…

symfony/ai-mate · 65 tokens

php-environment-check

Check the PHP runtime with server-info, its version, OS, and loaded extensions. Reach for it when a Mate tool itself fails or a capability is missing and you suspect the environment, a missing extension or an old PHP, rather than the app or its config. Not for diagnosing app behavior (profiler, log investigation) or…

symfony/ai-mate · 82 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

stack-trace-go-probe

Internal helper for meta-stack-trace-investigator. Use when a Go panic or stack trace needs Go-specific nil/error checks, go test reproducer guidance, and patch targets.

opensquilla/opensquilla · 42 tokens

stack-trace-python-probe

Internal helper for meta-stack-trace-investigator. Use when a Python traceback needs Python-specific root-cause checks, pytest reproducer guidance, and defensive patch targets.

opensquilla/opensquilla · 40 tokens