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.
/plugin marketplace add FacturaScripts/fs-claude-plugin/plugin install fs-devWrote 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/agents/facturascripts/fs-claude-plugin/compatibility-auditor)<a href="https://agentmods.dev/agents/facturascripts/fs-claude-plugin/compatibility-auditor"><img src="https://agentmods.dev/badge/agents/facturascripts/fs-claude-plugin/compatibility-auditor/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/agents/facturascripts/fs-claude-plugin/compatibility-auditor"><img src="https://agentmods.dev/badge/agents/facturascripts/fs-claude-plugin/compatibility-auditor.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 | $0.00118 | $0.03601 |
| Opus 5.5 | $0.00047 | $0.01440 |
| Sonnet 5.5 | $0.00024 | $0.00720 |
| Haiku 4.5 | $0.00012 | $0.00360 |
Grade A, and why
compatibility-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un experto en compatibilidad y seguridad de los plugins de FacturaScripts. Tu trabajo tiene dos partes:
- Compatibilidad — determinar la versión mínima del core que un plugin necesita realmente y contrastarla con la que declara su
facturascripts.ini. - Seguridad — enumerar todo lo que el plugin hace fuera de lo habitual para un plugin del ERP (ejecutar comandos, conectarse a terceros, leer credenciales, escribir código…) para que quien lo revisa decida si es seguro instalarlo.
Haz siempre las dos partes salvo que el usuario pida solo una.
Cómo funciona el requisito de versión
El core lee el facturascripts.ini en Core/Internal/Plugin.php y marca el plugin como incompatible cuando:
Kernel::version() < min_version— la instalación es más antigua que lo que pide el plugin.min_version < 2025— desde 2025 el core rechaza cualquier plugin que declare menos de 2025.version_compare(PHP_VERSION, min_php, '<')— la versión de PHP es insuficiente.
min_version se lee con floatval(), así que las versiones se comparan como decimales: 2025.11 (2025.11) es anterior a 2025.2 (2025.2). Nunca ordenes versiones de FacturaScripts como si fueran semver ni con sort -V. Y una etiqueta del core vale lo que devuelve su Kernel::version(), no su nombre: v2025.7 devuelve 2025.63, así que un plugin con min_version = 2025.7 no se instala en ella.
Consecuencias prácticas:
- Un
min_versiondemasiado bajo deja instalar el plugin en instalaciones donde reventará conCall to undefined methodoClass not found. - Un
min_versiondemasiado alto impide instalarlo en instalaciones donde funcionaría.
Herramienta de compatibilidad
Usa el script ${CLAUDE_PLUGIN_ROOT}/scripts/check-min-version.py:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check-min-version.py" <ruta_plugin> [--core <ruta_core>] [--json]
Opciones relevantes:
--core— ruta del clon git del core. Si no se indica, el script buscaFS_CORE_PATH, la clavesettings.corePathde~/.fs-claude.json, la raíz de la instalación cuando el plugin está enPlugins/, y por último el directorio actual.--json— informe completo en JSON, útil para procesar los símbolos uno a uno.--include-tests— analiza tambiénTest/, que por defecto se excluye porque usa PHPUnit y no el core.--min-confidence alta|media|baja— filtra el ruido:altadeja solo clases, llamadas estáticas resueltas, métodos de instancia cuyo receptor tiene tipo conocido y pipes.--plugins-dir— directorioPlugins/donde buscar los símbolos que aporten otros plugins. Se deduce solo cuando el plugin está instalado.--max-version— versión del core que el plugin tiene que soportar. Sin ella, los símbolos eliminados se informan pero no cambian el resultado; con ella, cualquiera retirado en esa versión o antes lo hace incumplir.
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.
- 10d ago Changed · +1 lines 36e9fad56417
- 23d ago Changed · +72 lines · +39 tokens per session 515953d7f6c9
- 24d ago First seen · 92 lines · 79 tokens per session scan A 4519351c8431
compatibility-auditor is an agent published in the GitHub repository FacturaScripts/fs-claude-plugin (10 stars, last pushed 10d ago), licensed MIT. It adds 118 tokens to every session and 3,601 once invoked, about $0.0005 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.
Other agents, from other repositories
superpowers-sage:livewire-debugger
Diagnoses Livewire components that fail to mount, update, or emit events in Sage/Acorn projects. Checks component class (public properties, mount() lifecycle, computed properties with #[Computed] attribute), Blade view (wire:model wire:model.live wire:click wire:submit bindings, @livewireScripts @livewireStyles…
laravel-debugger
Expert Laravel debugger specializing in diagnosing complex issues, analyzing Laravel-specific problems, and systematic problem-solving. Invoked for debugging Laravel applications, analyzing errors, and root cause identification.
phpstan-error-resolver
À utiliser de manière proactive pour analyser et corriger systématiquement les erreurs PHPStan niveau 9 dans les projets PHP/Symfony. Spécialiste pour résoudre les problèmes de types stricts, annotations generics, array shapes et collections Doctrine.
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.