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 sandraschi/civitai-mcp --skill civitai-depotgit clone --depth 1 https://github.com/sandraschi/civitai-mcpWrote 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/sandraschi/civitai-mcp/civitai-depot)<a href="https://agentmods.dev/skills/sandraschi/civitai-mcp/civitai-depot"><img src="https://agentmods.dev/badge/skills/sandraschi/civitai-mcp/civitai-depot/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/sandraschi/civitai-mcp/civitai-depot"><img src="https://agentmods.dev/badge/skills/sandraschi/civitai-mcp/civitai-depot.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 | $0.00021 | $0.00129 |
| Opus 5 | $0.00010 | $0.00064 |
| Sonnet 5 | $0.00004 | $0.00026 |
| Haiku 4.5 | $0.00002 | $0.00013 |
Grade A, and why
civitai-depot 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.
What it actually says
Civitai → comfyops depot
civitai_models_tool(operation=search, query=..., types=LORA|Checkpoint)get/version_getfor file sizes and hashesoutbox_enqueuewithversion_id+model_type- Human approve →
outbox_publish(download) - Generate in comfyops-mcp using the depot path
Dry-run by default. Token required for real downloads.
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 · 15 lines · 21 tokens per session scan A 89b09084f34c
civitai-depot is a skill published in the GitHub repository sandraschi/civitai-mcp (2 stars, last pushed 12d ago), licensed MIT. It adds 21 tokens to every session and 129 once invoked, about $0.0001 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
civitai-mcp-ultimate
Ultimate MCP server for Civitai — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze trends. Use when user asks about AI models, LoRAs, checkpoints, Stable Diffusion, Flux, image generation prompts, or Civitai.
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
adversarial-ml-evasion
Craft adversarial examples that cause trained ML classifiers to misclassify at inference time — image recognition, malware detectors, IDS, spam filters.