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 afaraha8403/balakit --skill media-gengit clone --depth 1 https://github.com/afaraha8403/balakitWrote 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/afaraha8403/balakit/media-gen)<a href="https://agentmods.dev/skills/afaraha8403/balakit/media-gen"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/media-gen/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/afaraha8403/balakit/media-gen"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/media-gen.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 | $0.00139 | $0.04170 |
| Opus 5.5 | $0.00056 | $0.01668 |
| Sonnet 5.5 | $0.00028 | $0.00834 |
| Haiku 4.5 | $0.00014 | $0.00417 |
Grade A, and why
media-gen scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**⚠️ Wix / JS-heavy site fallback:** If the browser tool errors out (blank page, WinError), the site is likely a Wix SPA. Do NOT retry the browser — switch to `curl + grep` to extract `wixstatic.com` image URLs from the How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Generation (Fal.ai) — v3.1
Leading words: pick the model, run the script, dual-model ads, one image per message, native filesystem path.
Decision model (read this first):
- Pick the job: still / edit / upscale / video / Instagram ad pair.
- Run
scripts/generate.py(or the documented fal_client call). Do not paste a rotated key; useFAL_KEY="$FAL_KEY". - Image-to-image when a reference exists. Dual-model for ad concepts (Nano Banana Pro Edit + Ideogram v4).
- One image per chat message (Telegram).
- Depth: references/endpoint-models.md, references/model-input-formats.md, references/high-conversion-prompting.md, references/fal-key-troubleshooting.md, references/wix-product-image-extraction.md.
Black Forest Labs FLUX Prompting Guide Reference: The official FLUX prompting guide is at https://docs.bfl.ml/guides/prompting_summary.md All photography terminology lives in references/photography-lexicon.md, sourced from BFL's official Prompt Reference (https://docs.bfl.ml/guides/prompting_unified_reference.md).
Key principle from BFL: "Prompt the model as if describing a real photograph: specify lens, lighting, framing, and texture details for maximum realism."
How FLUX reads prompts: Write in prose, not keyword lists — describe scenes like a novelist. Lighting descriptions have the highest single impact on output quality.
Setup
# Prerequisites
export FAL_KEY="your-key-here" # On Windows: setx FAL_KEY "key" (restart terminal)
pip install fal-client
# CRITICAL: fal-client >= 1.0.0 required for CDN upload (image-to-image)
# Old v0.13.1 broke CDN auth. Upgrade: pip install --upgrade fal-client
CRITICAL: FAL_KEY must use shell expansion, not the literal string.
Hardcoding the key string (FAL_KEY="07138a1e-...") returns 401 even when the shell-expanded version (FAL_KEY="$FAL_KEY") works. The env var may contain escape characters or may have been rotated since you read it.
✅ FAL_KEY="$FAL_KEY" python scripts/generate.py ...
❌ FAL_KEY="07138a1e-..." python scripts/generate.py ...
What ships with it
10 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.
- config.json 148 B
- references/ad-psychology-guide.md 57 KB
- references/cost-reference.md 4.2 KB
- references/endpoint-models.md 4.1 KB
- references/fal-key-troubleshooting.md 2.6 KB
- references/high-conversion-prompting.md 16 KB
- references/model-input-formats.md 2.3 KB
- references/photography-lexicon.md 448 B
- references/wix-product-image-extraction.md 2.2 KB
- scripts/generate.py 16 KB runs code
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.
- 1mo ago Changed · -290 lines 4e659beaf84c
- 2mo ago First seen · 581 lines · 139 tokens per session scan A c2df675bd421
media-gen is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 4,170 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
fal
Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another…
atlas-cloud-media
Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.
atlas-cloud-media
Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.
ai-image-generation-studio
Install and use the official AI Image Generator package, pinned by digest, for paid hosted work on the Beatra service.
ai-storyboard-generator
Install and use the official AI Storyboard Generator package, pinned by digest, for paid hosted work on the Beatra service.
ai-studio-image
Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.