EXTENSIONS

Plex Media Server control-API wrapper — trigger library refreshes on demand and capture per-section outcomes.

Generate timestamped publishing assets from owned or user-supplied YouTube video metadata and transcripts.

Generate platform-shaped social media post drafts for Facebook, X, LinkedIn, TikTok, and Instagram. Supports persona-driven text, short posts, text plus image/card plans, provided media, and orchestration-friendly media requests for @alvagante/content-image and @alvagante/content-card.

Generate publication-ready blog posts on any topic using Claude or any OpenAI-compatible endpoint, or save agent-written posts keylessly. Configurable skill level (novice/intermediate/senior/guru), output length, writing persona presets, and model selection.

Generate dense, visually structured cheatsheets on any technical topic. Outputs print-to-PDF-ready HTML (Cmd-P → Save as PDF) or GitHub-flavoured Markdown. Configurable skill level (novice→guru), verbosity, and completeness. Uses Claude or any OpenAI-compatible endpoint, or stores agent-written content keylessly.

Generate Ixen pages — self-narrated, mixed-media web pages in the tradition of 'I, Xen' (2005), where the technology itself speaks in first person while teaching real technical content. Self-contained HTML output with pop-up command windows, zoomable images, embedded video/audio/PDF, and inline cheatsheet/infographic embeds. Uses Claude or any OpenAI-compatible endpoint, or saves agent-written pages keylessly.

Generate playing-card shaped content images using OpenAI image generation. Adds card sequence, skill-level corner numbering, topic icons, optional logo hints, and expanded card-specific style presets.

Generate browser-ready infographic pages using OpenAI image generation. Produces an image, reliable HTML text shell, and relative output suitable for embedding in @alvagante/content-ixen.

Generate images using the OpenAI Images API (gpt-image-1.5 by default). Supports transparent PNG output and 9 style presets: ixen-dark, ixen-light, pencil-bw, pencil-color-accents, blueprint, technical-diagram, cyberpunk-photo, educational, none. Optional outputDir for composing multi-media mini-sites alongside content-ixen pages.

Generate songs from topics using Claude for lyrics and 1min.ai (Suno or Lyria) for audio. Part of the @alvagante content-media suite.

Monitor disk usage and backup snapshot inventory on any SSH-accessible host or the local machine. Produces typed, versioned artifacts for each mount point and backup directory, with configurable warning and critical thresholds.

A generic data-table report for any swamp model — render materialised resource data as markdown tables, dataview-style, instead of hand-writing a bespoke report per model. Declare a `tableViews` tag (JSON: a list of {spec, columns, where, sort, limit}) for curated views — the config lives in the model's free-form `tags`, so it works on ANY model type with no schema change — or get an auto-table per resource spec with zero config. Column paths are content-relative (e.g. `facets.pricing.perTBMonth`); filters are scalar- equality. Point it at any model, get tables, no TypeScript.

A domain-neutral, sourced, versioned knowledge base — the provenance-aware core generalised out of @stateless/llm-catalog. One uniform `entry` record (open `kind` + open `facets` + `claims` + `relations`, like @stateless/inventory), but with a provenance envelope (asOf, source, versionPins, supersededBy) on every volatile assertion, so it can hold external, decaying, contested knowledge honestly — a value without a date + source is not trustworthy here. Declarative lifecycle: `apply` materialises the declared entries (re-run = versioned trend), `update` folds in a public catalog without clobbering local truth, `prune` soft-retires undeclared entries, `contribute` sanitises selected entries into PR-ready public fragments. It knows no domain (no typed facets, no compute methods); a consuming catalog — LLM-ops, cloud-storage pricing — is an instance whose entries carry that domain's kinds and facets.

A sourced, versioned knowledge base of LLM-ops knowledge — NOT a control plane for running models, but the structured, CEL-queryable record that running extensions read to decide which model to run where, with what settings, at what cost. Six subject kinds (model, runtime, provider, hardware, technique, endpoint), all the same uniform `entry` shape (open kind + open facets, like @stateless/inventory); a model's run-options embed on the model in runsOn[] keyed by endpoint, and capacity/plan answer "what to run where" over them. The twist: it records external, decaying knowledge, so every volatile assertion carries a provenance envelope (asOf, source, versionPins, supersededBy) — "best vLLM version" is derived as the latest un-superseded claim, never a bare rotting field. Declarative: `apply` materialises one `entry` resource per id (re-run = versioned trend); `prune` soft-retires undeclared entries.

Tailscale tailnet device inventory via the API — sync all devices, delete stale entries

Fleet audit for AWS Security Hub control EC2.2 ("VPC default security groups

Fleet-wide VPC inventory across `profiles × regions`. A single read-only

Lists RDS DB clusters in the configured AWS region and emits two

Lists every running RDS DB instance (Aurora cluster members AND standalone

Write-side retirement operations for a CloudFormation StackSet, run from the

Read-only operational audit of a CloudFormation StackSet and all of its stack

Coalesces a CloudFormation StackSet lens (@jentz/aws-stackset-audit) and an

Generic AWS workflow-safety primitive. Fails closed before any AWS work

Trigger CloudFormation StackSet drift detection and record its outcome — the