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.
npx agentmods add skills/alecs5am/ralphy/audio-explainernpx skills add alecs5am/ralphy --skill audio-explainergit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/skills/alecs5am/ralphy/audio-explainer)<a href="https://agentmods.dev/skills/alecs5am/ralphy/audio-explainer"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/audio-explainer.svg" alt="Measured on agentmods" 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 | $0.00353 | $0.03727 |
| Opus 5 | $0.00177 | $0.01863 |
| Sonnet 5 | $0.00071 | $0.00745 |
| Haiku 4.5 | $0.00035 | $0.00373 |
Grade A, and why
audio-explainer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **`ralphy` is the only entry-point.** No direct `ffmpeg`, `yt-dlp`, `curl`, or `bunx tsx` against provider SDKs. Every step in the workflow below is either a `ralphy` verb (already shipped) or an LLM call routed throu How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio-explainer
Trigger refinements
ALSO FIRE when the user drops a YouTube / podcast URL whose duration is > 4 minutes AND asks for "a video" (not "a clip" / "a short" / "a cut") — that is the audio-to-longform path, not the short-form cut path. Long-form on a URL: pull --audio-only, then run this skill on the audio.
DO NOT FIRE for:
- Short-form cuts (< 4 min) from a long-form source — route to
podcast-cliptemplate. - Talking-head essays where the user wants their face on screen — route to
yap-talking-headorgreen-screen-explainer. - Multi-speaker debates / interviews — route to
interview-dialog(split-screen) orpodcast-clip(cut viral moments). - Music videos / non-speech audio — route to
music-videotemplate. - Once the project has
index.htmlcomposed and the user wants render / preview tweaks — handback to the editor playbook.
Hard invariants
ralphyis the only entry-point. No directffmpeg,yt-dlp,curl, orbunx tsxagainst provider SDKs. Every step in the workflow below is either aralphyverb (already shipped) or an LLM call routed throughcli/lib/providers/llm.ts → callLLM(). AGENTS invariant #2.- Append-only on the project dir. Per AGENTS invariant #14, every regeneration writes
.v2/.v3files. Never overwriteoverlay-plan.json,captions.json, or any asset inartifacts/. The skill writes a new version; the user picks which to promote. - English-only on disk. Every file the skill writes lands in English. If the source audio is Russian / Spanish / etc., the on-disk
overlay-plan.jsonkeepsvo_textin the source language (it's transcript content) but every comment, log line, file name, and skill-generated annotation is English. Chat with the user matches their language. - No raw API code. Browser screenshots run through a Playwright helper script the skill calls via
bunx playwright, not via rawpuppeteer.launch()in inline code. Image generation goes throughralphy generate image. Music + SFX throughralphy generate music+ralphy generate sfx. No direct ElevenLabs HTTP calls. - Composition must be deterministic. The HyperFrames
index.htmlthe skill emits has noDate.now()/ unseededMath.random()/fetch()at render time. Per.agents/skills/hyperframes/references/playbook.mdhard invariants.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 258 lines · 353 tokens per session scan A 8a7a70894669
audio-explainer is a skill published in the GitHub repository alecs5am/ralphy (128 stars, last pushed 8d ago), licensed Apache-2.0. It adds 353 tokens to every session and 3,727 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
clinical-imaging
Clinical and physiological imaging analysis. Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow. For DICOM file handling use pydicom; for biosignals use neurokit2.
curated-bio-datasets
Guide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database…
deeptools
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.