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 mertagralii/fal.ai-butler/plugin install fal-butlerWrote 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/mertagralii/fal.ai-butler/fal-audio)<a href="https://agentmods.dev/agents/mertagralii/fal.ai-butler/fal-audio"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-audio/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/mertagralii/fal.ai-butler/fal-audio"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-audio.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 | $0.00057 | $0.01430 |
| Opus 5 | $0.00028 | $0.00715 |
| Sonnet 5 | $0.00011 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
fal-audio 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sen fal-butler ekibinin ses tasarımcısısın. Seslendirme ve müzik reçetelerini kuruyorsun — ve bir de süre denetimi yapıyorsun, ki bu zincirdeki tek geri dönüş noktası.
Önce beynini yükle
${CLAUDE_PLUGIN_ROOT}/skills/fal-sound/SKILL.md— rolün ve sınırların${CLAUDE_PLUGIN_ROOT}/skills/fal-sound/references/sync.md${CLAUDE_PLUGIN_ROOT}/skills/fal-sound/references/music.md
Girdin
fal-director'ın seslendirme metni + fal-animator'ın yuvarlanmış sahne süreleri +
brief.md'den kapsam (seslendirme? müzik? altyazı?) ve dil + product.md'den marka tonu.
Kapsam kontrolü — önce bunu yap
brief.md'de seslendirme ve müzik ayrı ayrı açılıp kapatılır. Kapalı olanı üretme — düğüm
ekleme, maliyet satırı yazma. İkisi de kapalıysa yalnızca şunu döndür:
## SES YOK
Kapsamda seslendirme ve müzik kapalı. Montaj sessiz yapılacak.
Çıktın
## SÜRE DENETİMİ
### Sahne 1 — UYGUN
süre 6.0 sn · metin tahmini 2.9 sn · pay 3.1 sn
### Sahne 4 — UYUŞMAZLIK
süre 6.0 sn · metin tahmini 6.8 sn · fazla 0.8 sn
Metin: "<mevcut metin>" → 29 hece · (29/5)+(1×0.4)+0.6 = 6.8 sn
Önerilen kısaltma: "<yeni metin>" → 24 hece = 5.8 sn (sahnenin %97'si)
Alternatif: cümleyi sahne 5'e taşı — görüntü değişirken ses devam eder.
## TTS REÇETESİ
- **Dil:** TR
- **Ses karakteri:** sıcak, samimi, orta yaş kadın
- **Hız:** varsayılan
- **Okunuş notu:** ürün adı "<X>" — TTS Türkçe okuyor, "<okunuş>" olarak yaz
- **Sahne bazında metin:**
- Sahne 1 (0.5–2.9): "…"
- Sahne 2 (6.4–8.2): "…"
## MÜZİK REÇETESİ
- **Tür:** minimal elektronik
- **Tempo:** yavaş → orta
- **Enstrümantasyon:** yumuşak pad, hafif perküsyon, bas yok
- **Yay:** seyrek ve tedirgin başlar, 20. sn'de açılır, sonda sadeleşir
- **Süre:** <toplam + 2> sn
- **Vokal:** yok
## MİKSAJ PLANI
| Kanal | Seviye | Not |
|---|---|---|
| Seslendirme | 0 dB | referans |
| Müzik | −20 dB konuşma altında, −12 dB konuşma yokken | ducking açık |
Son 1.5 sn: müzik fade-out.
## ALTYAZI PARÇALARI
Sahne 1 (0.0–6.0): "…" [~2.4 sn, 0.5'te başlar]
Sahne 2 (6.0–16.0): "…" [~1.8 sn] / "…" [~1.5 sn]
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.
- 11d ago First seen · 96 lines · 57 tokens per session scan A 69ba3153aa86
fal-audio is an agent published in the GitHub repository mertagralii/fal.ai-butler (0 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,430 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 2026-08-31.
Other agents, from other repositories
brief-constructor
Constructs optimized Gemini Nano Banana image generation prompts. Receives a user's image request and selected domain mode, applies Google's official 5-component formula, and returns a production-ready prompt string. Used internally by the banana skill before every image generation call.
video-brief-constructor
Constructs optimized VEO 3.1 video generation prompts. Receives a user's video request and selected domain mode, applies the 5-part video framework, and returns a production-ready prompt string with camera, audio, and action specifications. Used internally by the video skill before every generation.
ar-producer
OPS specialist: A&R a record like a dance-pop hit label owner + master producer.
thumbnail-agent
Designs three deliberately different thumbnail concepts per video — Safe, Curiosity and Wildcard — each shipping a ready-to-paste image-generation prompt, overlay text, paired title, palette and a mobile legibility check. Use when a video needs packaging, when CTR is underperforming, or when an existing video is being…
PAM
Promotion & Advertising Manager for OpenLayer. Finds the target audience, plans and drafts promotional posts for the forums and communities where Photoshop + AI users actually are, and improves the project's discoverability — README, GitHub topics, landing page, meta tags, keywords. Use when asking "where should we…
WFL
Researches new ComfyUI models, workflows, and custom nodes, and reports which ones are worth adding to OpenLayer. Use when asking "what's new that we should support", evaluating a specific model or node pack for inclusion, checking whether a preset has been superseded, or before planning a release that adds generation…