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 fthsrbst/mnema --skill media-gengit clone --depth 1 https://github.com/fthsrbst/mnemaWrote 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/fthsrbst/mnema/media-gen)<a href="https://agentmods.dev/skills/fthsrbst/mnema/media-gen"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/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/fthsrbst/mnema/media-gen"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/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 | $0.00075 | $0.00713 |
| Opus 5 | $0.00037 | $0.00357 |
| Sonnet 5 | $0.00015 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
media-gen 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 9d 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.
What it actually says
Medya Üretimi (ComfyUI via Hub)
Bir görsel/video gerektiğinde kullanıcıdan isteme — hub'daki media_generate ile kendin üret.
Akış
machine_status→ ComfyUI açık mı? Kapalıysa kullanıcıya "ComfyUI'ı açar mısın" de.workflow_list→ mevcut workflowlar.media_generate(workflow, inputs)çağır.- Dönen
fileshub'daki yerel yol,urlsHTTP erişimi. Dosyayı işinde doğrudan kullan.
Workflow envanteri (doğrulanmış)
| Workflow | İş | Süre | Notlar |
|---|---|---|---|
z-image-t2i |
Hızlı görsel taslak/iterasyon | ~15-30sn | width/height/steps/cfg ayarlanabilir |
flux2-t2i |
Kaliteli final görsel | ~1-2dk | turbo=false → 20 adım en iyi kalite |
qwen-image-t2i |
Görsel; metin/tipografi içerenlerde en iyi | ~30sn (turbo) | turbo=false → 50 adım |
qwen-image-edit |
Var olan görseli talimatla düzenleme | ~30-60sn | image_path: yerel dosya (otomatik yüklenir), prompt: düzenleme talimatı |
wan22-t2v |
Text-to-video | dk'lar | length: kare sayısı (16fps; 81≈5sn), test için 33 kullan |
Prompt kuralları
- İngilizce yaz — görsel modeller İngilizce prompt'ta belirgin daha iyi.
- Zenginleştir: özne + stil + kompozisyon + ışık ("a minimal flat illustration of ..., soft colors, centered composition").
- İterasyon stratejisi: önce
z-image-t2iile 2-3 varyant (farklı seed), beğenilen kompozisyonuflux2-t2i/qwen-image-t2iile finalize et. - Aynı seed + aynı prompt = aynı sonuç; varyant için seed'i verme (otomatik rastgele).
Hatalar
- "workflow yok" →
workflow_list; yeni workflow ekleme: kullanıcı ComfyUI'da kurar,scripts/comfy-convert.tsAPI formatına çevirir. - "doldurulmamış girdi bekliyor: X" →
inputs.Xver. - Zaman aşımı → ilk çağrıda model VRAM'e yüklenir (yavaş);
timeoutSec: 600+ile tekrarla. Video için 900+. - Üretim kalitesi kötüyse önce prompt'u zenginleştir, sonra turbo=false dene.
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.
- 9d ago First seen · 35 lines · 75 tokens per session scan A 56c7775fc14b
media-gen is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 713 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
atet
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
spoken-response-desktop
Read and embed an assistant response aloud in Codex Desktop, Antigravity App, or OpenCode Desktop.
create-speech-recording-controls
Turn text into speech with Agent Voice and clickable playback controls. Use when the user explicitly requests controlled playback on a compatible desktop renderer.
create-speech-recording-desktop
Create and embed a speech recording in Codex Desktop, Antigravity App, or OpenCode Desktop.
create-speech-recording
Turn text into speech with Agent Voice. Use for creating audio recordings and speaking text aloud.
spoken-response
Read an assistant response aloud with Agent Voice. Use when the user requests a spoken response, the previous response as audio, or spoken responses for a thread.