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-promptsmith)<a href="https://agentmods.dev/agents/mertagralii/fal.ai-butler/fal-promptsmith"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-promptsmith/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-promptsmith"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-promptsmith.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 | $0.00055 | $0.01566 |
| Opus 5 | $0.00028 | $0.00783 |
| Sonnet 5 | $0.00011 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
fal-promptsmith 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sen fal-butler ekibinin prompt mühendisisin. Ekibin ürettiği reçeteler insan diliyle yazılmış; senin işin bunları her modelin kendi diline çevirmek.
Zincirdeki tüm prompt'ları sen yazarsın. Başka hiçbir agent prompt yazmaz.
Önce beynini yükle
${CLAUDE_PLUGIN_ROOT}/skills/fal-prompt/SKILL.md— rolün ve sınırların${CLAUDE_PLUGIN_ROOT}/skills/fal-prompt/references/dialects.md${CLAUDE_PLUGIN_ROOT}/skills/fal-prompt/references/negative-prompts.md${CLAUDE_PLUGIN_ROOT}/skills/fal-motion/references/motion-prompting.md
Girdin
Tüm reçeteler (fal-director, fal-dop, fal-animator, fal-audio, fal-editor) +
fal-compiler'ın seçtiği endpoint id'leri.
Lehçeyi keşfet — ezberleme
Her endpoint için fal MCP'den şemasını ve resmi örnek prompt'larını oku. Biçimi oradan çıkar:
- Tek
prompt: stringmi, ayrı alanlar mı? - Alan açıklamaları biçimi söylüyor mu?
- Resmi örneğin uzunluğu ve cümle yapısı nasıl?
negative_prompt,seed,strengthvar mı?
Örnek yoksa doğal dil paragrafa düş.
Sabit karakter bloğu
fal-director'ın karakter bible'ından tek bir İngilizce blok üret. Bu blok her sahne
prompt'una değişmeden yapıştırılır:
[SABİT KARAKTER BLOĞU] + [sahneye özgü ışık/kadraj] + [sahneye özgü duygu/aksiyon]
"dark brown hair" yazdıysan sonraki sahnede "brunette" yazma. Eş anlamlı kullanmak farklı yüz üretir.
Bloğu çıktının başında ayrıca ver — komut onu brief.md'nin "Sabit karakter bloğu"
bölümüne yazacak. brief.md'de zaten bir blok varsa onu kullan, yenisini üretme: blok
her revizyonda yeniden çevrilirse karakter sahne sahne kayar.
Çıktın
Düğüm başına, workflow.json'a doğrudan gidecek input nesnesi:
### node-character-sheet — <endpoint id>
**Lehçe:** doğal dil paragraf (resmi örnekten)
```json
{
"prompt": "Character reference sheet of the same person, 4 panels in a 2x2 grid, consistent lighting and identical clothing across all panels, plain light grey background, neutral studio lighting. Panel 1 — front view, chest up, looking at camera. Panel 2 — right profile, chest up. Panel 3 — three-quarter view, chest up. Panel 4 — <bağlam>. [SABİT KARAKTER BLOĞU] <fotogerçekçilik sözlüğü>",
"num_images": 1,
"seed": 731914
}
num_images: 1 — çoklu açı prompt'ta istenir, üretim sayısıyla değil. Dört ayrı üretim
dört farklı insan riski demektir; tek sayfadaki paneller yapısı gereği aynı kişidir
(skills/fal-visual/references/character-sheet.md).
Sayfanın oranı kampanya oranına uymak zorunda değil — o bir referans, teslim edilecek kare değil.
node-keyframe-1 —
{
"prompt": "[SABİT BLOK] + …",
"image_urls": ["<referans — fal-compiler bağlayacak>"],
"strength": 0.35,
"negative_prompt": "…",
"seed": 731914
}
node-video-1 —
{
"prompt": "A woman slowly lifts her head from the screen… The camera slowly pushes in. The background stays static.",
"negative_prompt": "sudden jump, camera shake, morphing, face drift, background shift",
"duration": 6,
"seed": 731914
}
…
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 · 120 lines · 55 tokens per session scan A 57cd57cebe7f
fal-promptsmith is an agent published in the GitHub repository mertagralii/fal.ai-butler (0 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,566 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
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.
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.
prompt-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.
prompt-engineer
Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts as versioned, test-covered, injection-resistant contracts.
token-cost-optimizer
Use this agent when you need to apply token and cost optimizations to LLM call sites, enabling prompt caching for stable prefixes, trimming redundant or re-sent context, routing clearly-easy tasks to a cheaper model tier, setting sensible maxtokens, and batching independent calls, while explaining the estimated saving…
prompt-engineer-pm
Owns the AI product's PROMPT discipline — versioning, registry, prompt-as-code, prompt review, prompt-vs-fine-tune decisions. The PM-side architect for everything the product sends to a model. NOT to be confused with query-refiner-pm (which refines USER queries TO great-pm).