verificar-min-version

verificar-min-version is a skill for Claude Code from FacturaScripts/fs-claude-plugin. It costs 57 tokens per session (1,765 once invoked), scanned A, original, MIT.

A compatibility checker for FacturaScripts plugins. It compares the plugin's declared minimum version with the core classes, methods, properties, and extension points it actually uses.

In plain words
What is it for?
Use it to determine the correct core and PHP minimum versions for a plugin and identify the code symbol that sets that requirement.
Why use it?
It helps avoid plugins that claim compatibility but fail on older core versions, while also avoiding unnecessarily high version requirements.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the fs-dev plugin — 29 skills, 12 agents, 3 hooks shipped together

Good fit Use it to determine the correct core and PHP minimum versions for a plugin and identify the code symbol that sets that requirement.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add FacturaScripts/fs-claude-plugin
Claude Code
/plugin install fs-dev

Made for: Claude Code.

Or install fs-dev, the plugin that ships this one along with the rest of its 29 skills, 12 agents, 3 hooks.

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 verificar-min-version

README.md
[![agentmods](https://agentmods.dev/badge/skills/facturascripts/fs-claude-plugin/verificar-min-version/github.svg)](https://agentmods.dev/skills/facturascripts/fs-claude-plugin/verificar-min-version)
Your own site
<a href="https://agentmods.dev/skills/facturascripts/fs-claude-plugin/verificar-min-version"><img src="https://agentmods.dev/badge/skills/facturascripts/fs-claude-plugin/verificar-min-version/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 verificar-min-version

Your own site · 80×15
<a href="https://agentmods.dev/skills/facturascripts/fs-claude-plugin/verificar-min-version"><img src="https://agentmods.dev/badge/skills/facturascripts/fs-claude-plugin/verificar-min-version.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,765 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 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 $0.00057 $0.01765
Opus 5.5 $0.00023 $0.00706
Sonnet 5.5 $0.00011 $0.00353
Haiku 4.5 $0.00006 $0.00177

Measured 10d ago against content hash d263ed86d639, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verificar-min-version 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.

fs-dev/skills/verificar-min-version/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditoría de compatibilidad y seguridad de un plugin

La auditoría tiene dos partes independientes: la compatibilidad con el core (min_version) y la seguridad (qué hace el plugin en el servidor y en el navegador). Haz las dos salvo que el usuario pida solo una. La de seguridad no necesita el clon del core: si falta, hazla igualmente.

Flujo

  1. Lee el facturascripts.ini del plugin y anota min_version, min_php y require.

  2. Localiza un clon git del core con todas sus etiquetas. Orden de búsqueda del script: --core, FS_CORE_PATH, settings.corePath de ~/.fs-claude.json, la raíz de la instalación cuando el plugin vive en Plugins/, y el directorio actual. Si no hay ninguno, pide clonar https://github.com/NeoRazorX/facturascripts.git y detente: sin historial no se puede datar ningún símbolo.

  3. Ejecuta el script de auditoría:

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check-min-version.py" <ruta_plugin> --core <ruta_core>
    
  4. Lee completo el perfil ../../agents/compatibility-auditor.md para interpretar el informe y verificar a mano los símbolos de confianza media o baja.

  5. Ejecuta la auditoría de seguridad:

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check-security.py" <ruta_plugin>
    
  6. Revisa en el código cada hallazgo de severidad alta o media siguiendo el apartado «Cómo revisar los hallazgos» del perfil, y clasifícalo como justificado, a vigilar o sospechoso.

  7. Concluye con dos apartados:

    • Compatibilidad: el min_version correcto, el símbolo concreto que lo determina y el archivo donde aparece.
    • Seguridad: los hallazgos revisados con su archivo, contexto de ejecución, destino y clasificación; los dominios externos; y lo que ha quedado sin revisar.

Opciones de check-min-version.py

Opción Uso
--json Informe completo para procesar símbolo a símbolo
--include-tests Analiza también Test/, excluido por defecto
--min-confidence alta Deja solo clases, llamadas estáticas, métodos con receptor tipado y pipes
--plugins-dir Directorio Plugins/ para atribuir los símbolos de otros plugins
--max-version X Incumple si el plugin usa algo retirado en la versión X del core o antes
--workers N Ajusta las consultas simultáneas a git

Read the full file on GitHub · 104 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 Changed · +3 lines d263ed86d639
  2. 23d ago Changed · +33 lines · +13 tokens per session 87dea47d331d
  3. 24d ago First seen · 68 lines · 44 tokens per session scan A 083149675cb7

Subscribe to this mod's changes

verificar-min-version is a skill published in the GitHub repository FacturaScripts/fs-claude-plugin (10 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 1,765 once invoked, about $0.0002 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 2026-09-23.

Related

Other skills, from other repositories

sentry-php-sdk

Full Sentry SDK setup for PHP. Use when asked to "add Sentry to PHP", "install sentry/sentry", "setup Sentry in PHP", or configure error monitoring, tracing, profiling, logging, metrics, crons, or AI monitoring for PHP applications. Supports plain PHP, Laravel, and Symfony.

getsentry/sentry-for-ai · 71 tokens

php-quality-tooling

Use when setting up PHPStan, Rector, or PHP-CS-Fixer on a non-Laravel PHP project, incl. CI wiring. Do NOT use for Laravel (Pint/Larastan), tests, or syntax.

fusengine/agents · 51 tokens

wp-phpstan

Use when configuring, running, or fixing PHPStan static analysis in WordPress projects (plugins/themes/sites): phpstan.neon setup, baselines, WordPress-specific typing, and handling third-party plugin classes.

WordPress/agent-skills · 47 tokens

bug-root-cause-finder

Root cause analysis methods for PHP bugs. Provides 5 Whys technique, fault tree analysis, git bisect guidance, and stack trace parsing.

dykyi-roman/awesome-claude-code · 36 tokens

wp-phpstan-static-analysis

Run PHPStan static analysis on a WordPress plugin or theme using szepeviktor/phpstan-wordpress. Covers the composer dev-dependencies and what is pulled transitively (phpstan/phpstan ^2.0, php-stubs/wordpress-stubs), the optional phpstan/extension-installer that auto-registers the extension, the phpstan.neon.dist…

Lonsdale201/wp-agent-skills · 227 tokens

check-cascading-failures

Detects cascading failure risks in PHP systems. Identifies shared resources, unbounded queues, missing backpressure, thread pool exhaustion, and failure propagation paths.

dykyi-roman/awesome-claude-code · 39 tokens