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 danielrosehill/Claude-AI-Video-Producer-Plugin --skill recommend-modelgit clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-PluginWrote 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/danielrosehill/claude-ai-video-producer-plugin/recommend-model)<a href="https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/recommend-model"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/recommend-model/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/danielrosehill/claude-ai-video-producer-plugin/recommend-model"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/recommend-model.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 | $0.00128 | $0.01302 |
| Opus 5 | $0.00064 | $0.00651 |
| Sonnet 5 | $0.00026 | $0.00260 |
| Haiku 4.5 | $0.00013 | $0.00130 |
Grade A, and why
recommend-model 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommend model
Conversational model picker. Use this when the user asks "what should I use for X" or "find me a cheap/good/fast model for X". For deep written research, use model-researcher instead.
Step 1 — Capture preferences
Ask only the questions you don't already know from brief/creative-brief.md:
- Workload: text-to-image, text-to-video, image-to-video, lip-sync, voice/TTS, upscale, interpolate, other.
- Priority: quality / speed / cost (pick one as primary, one as secondary).
- Budget ceiling: per-output cap (e.g. "$0.20 per clip"), or "no cap, just tell me".
- Output specs: resolution, aspect ratio, duration (for video).
- Hard requirements: e.g. needs audio, needs >10s, needs lip-sync, needs photoreal faces, needs commercial license.
- Provider preference: fal / Replicate / WaveSpeed / MiniMax / any (default: any). Only suggest providers whose key is present in
~/.config/ai-video-producer/.env.
Keep this short — one batched message, not five round trips. Infer from the brief where possible.
Step 2 — Query providers
Replicate (use the bundled MCP):
mcp__plugin_ai-video-producer_replicate__search_modelswith a query like the workload ("image-to-video","lipsync","upscaler").- For top hits, call
mcp__plugin_ai-video-producer_replicate__get_modelsfor pricing/hardware metadata, andlist_models_versionsif a specific version is needed. - Pricing on Replicate is usually per-second of GPU time × hardware tier — convert to per-output by multiplying by typical run time stated on the model page.
fal.ai (hosted MCP exists for catalogue, but is thin — prefer web fetch):
- Use
WebFetchagainsthttps://fal.ai/models?categories=<category>and individual model pages (e.g.https://fal.ai/models/fal-ai/<slug>). - fal usually quotes per-second-of-output or per-megapixel — use what the page states.
- Execution path is
runners/fal_run.mjs— confirm the model id matches thefal-ai/<slug>form the runner expects.
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.
- 12d ago First seen · 75 lines · 0 tokens per session scan A 34400acaed2f
recommend-model is a skill published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 128 tokens to every session and 1,302 once invoked, about $0.0006 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.