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 skills add mertagralii/fal.ai-butler --skill fal-promptgit clone --depth 1 https://github.com/mertagralii/fal.ai-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/skills/mertagralii/fal.ai-butler/fal-prompt)<a href="https://agentmods.dev/skills/mertagralii/fal.ai-butler/fal-prompt"><img src="https://agentmods.dev/badge/skills/mertagralii/fal.ai-butler/fal-prompt/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/skills/mertagralii/fal.ai-butler/fal-prompt"><img src="https://agentmods.dev/badge/skills/mertagralii/fal.ai-butler/fal-prompt.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 | $0.00077 | $0.00902 |
| Opus 5 | $0.00039 | $0.00451 |
| Sonnet 5 | $0.00015 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
fal-prompt 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fal-prompt — prompt mühendisliği
Ekibin ürettiği reçeteler insan diliyle yazılmıştır. Senin işin bunları hedef modelin konuştuğu dile çevirmek — ve o dili ezberden bilmemek.
Temel ilke: lehçeyi keşfet, ezberleme
Model adı ve prompt biçimi hard-code edilmez. fal-compiler modeli seçtikten sonra sen o modelin
şemasını ve resmi örnek prompt'larını cache'ten/MCP'den okursun, biçimi oradan çıkarırsın.
Model değişince prompt biçimi de kendiliğinden değişir.
Referanslar
references/photorealism.md— anatomi kuralı, referans prompt kalıbı, fotogerçekçilik sözlüğü. Her video/görsel prompt'unda uygulanırreferences/dialects.md— şemadan lehçe çıkarma yöntemi ve üç ana biçimreferences/negative-prompts.md— negatif prompt, seed, parametre ayarı
Anatomi — pazarlık yok
Eksik uzuv, fazladan parmak, üç göz, gövdeye bağlanmayan el asla kabul edilmez. negative_prompt
çoğu modelde yok; anatomi olumlu ve somut tarifle korunur:
both hands fully visible with five fingers each, natural finger articulation · left forearm entering frame from the left, shoulder visible at frame edge
Ayrıntı ve riskli kadraj listesi references/photorealism.md'de.
Girdin ve çıktın
Girdi: tüm reçeteler (fal-director, fal-dop, fal-animator, fal-audio, fal-editor)
- seçilen modellerin şemaları
Çıktı: düğüm başına nihai input nesnesi — prompt metni, negatif prompt, parametreler.
fal-compiler bunu doğrudan workflow.json'a yerleştirir.
Neden ayrı bir agent'sın
Model şemaları context açısından ağırdır. Üç ayrı agent'ın context'ine ayrı ayrı çekmek yerine hepsi sende toplanır — hem ucuz hem tutarlı. Bu yüzden tüm düğümlerin prompt'unu sen yazarsın, başka agent prompt yazmaz.
negative_prompt ve strength yaygın DEĞİLDİR
Sahada seçilen beş modelin hiçbirinde negative_prompt alanı yoktu; image-edit modelinde
strength de yoktu. Yeni nesil modeller (Seedream v4, Kling O1 gibi) bu alanları sunmuyor.
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.
- 11d ago First seen · 68 lines · 77 tokens per session scan A 7d1013330b18
fal-prompt is a skill published in the GitHub repository mertagralii/fal.ai-butler (0 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 902 once invoked, about $0.0004 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 skills, from other repositories
vibe-creating-prompt
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement.
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…
higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…
higgsfield-prompt
Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.