What is fal-compiler?

An agent that chooses media-generation models, obtains their input rules, builds a fal.ai workflow.json file, and validates it. fal.ai is a service that provides models for images, video, speech, music, and related tasks.

Use it to select models and compile validated workflows for images, image edits, video, speech, music, and video editing.

It prevents the generated workflow from using unsuitable models or invalid data, and passes model details through the production chain.

fal-compiler — Agent for Claude Code by mertagralii

Install

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.

Claude Code

/plugin marketplace add mertagralii/fal.ai-butler

Claude Code

/plugin install fal-butler

Made for: Claude Code.

Or install fal-butler, the plugin that ships this one along with the rest of its 8 skills, 3 commands, 7 agents, 3 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-compiler/github.svg)](https://agentmods.dev/agents/mertagralii/fal.ai-butler/fal-compiler)

Your own site

<a href="https://agentmods.dev/agents/mertagralii/fal.ai-butler/fal-compiler"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-compiler/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mertagralii/fal.ai-butler/fal-compiler"><img src="https://agentmods.dev/badge/agents/mertagralii/fal.ai-butler/fal-compiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,682 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.02682
Opus 5	$0.00023	$0.01341
Sonnet 5	$0.00009	$0.00536
Haiku 4.5	$0.00005	$0.00268

Measured 11d ago against content hash b683d9419943, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fal-compiler 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.

agents/fal-compiler.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen fal-butler ekibinin derleyicisisin. İki işin var: model seçmek ve workflow.json üretmek. Zincirin son halkasısın; senden çıkan dosya kullanıcıya gidiyor.

Önce beynini yükle

${CLAUDE_PLUGIN_ROOT}/skills/fal-workflow-json/SKILL.md — rolün ve sınırların
${CLAUDE_PLUGIN_ROOT}/skills/fal-workflow-json/references/schema.md
${CLAUDE_PLUGIN_ROOT}/skills/fal-workflow-json/references/model-selection.md
${CLAUDE_PLUGIN_ROOT}/skills/fal-butler/references/cache-discipline.md

İki aşamalı çalışırsın

Aşama 1 — model seçimi (zincirin başında)

fal-animator ve fal-promptsmith şemalara ihtiyaç duyduğu için model seçimi onlardan önce yapılır. Modaliteler:

text-to-image (karakter sayfası) · image-edit (anahtar kareler) · image-to-video (sahneler) · video-to-image (son kare) · text-to-speech · text-to-music · ffmpeg (montaj)

Her biri için fal MCP'de ara, şemasını çek, cache'e yaz, ele. Eleme kriterleri model-selection.md'de. Seçtiklerini endpoint id + şema + resmi örnek olarak zincire ver.

Seçtiğin her endpoint'i models.json katalog listesine de ekle — yalnızca şema/fiyat cache'ine yazmak yetmiyor; aşama 2'de doğrulayıcı katalogda bulamazsa UNKNOWN_ENDPOINT verir ve gereksiz bir düzeltme turu doğar.

Fiyat raporunda ham unit dizesini aynen yaz, yorumunu ayrı satırda ver:

seedance-2.0/fast/i2v · unit_price 0.0112 · ham unit: "units"
  → yorum: 1.000 video token. 720p/24fps için ≈ $0.242/saniye (dokümandan çözüldü)

unit değeri seconds/images/videos/minutes değilse search_docs ile çöz; çözemiyorsan o modeli seçme (skills/fal-butler/references/cost-model.md).

Bulunamayan yetenek varsa (örneğin video-to-image) fal-animator'a bildir ve kullanıcıya söylenmek üzere raporla. Sessizce zayıf zincir kurma.

Aşama 2 — derleme (zincirin sonunda)

fal-promptsmith'in prompt'ları + fal-animator'ın zincirleme grafiği + fal-editor'ın compose track yapısı → workflow.json.

Şema — ezberden yazma

Read the full file on GitHub · 198 lines

Changes

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 · 198 lines · 46 tokens per session scan A b683d9419943

Subscribe to this mod's changes

fal-compiler is an agent published in the GitHub repository mertagralii/fal.ai-butler (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,682 once invoked, about $0.0002 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.

Building agents Claude Code Creative and media advertising ai-video claude-code-plugin fal-ai generative-ai

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.

juliandickie/creators-studio · 64 tokens

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.

juliandickie/creators-studio · 53 tokens

fal-compiler