npcpy is a Python library for building applications with multimodal language models, agent-based AI, and knowledge graphs. Researchers and developers use it with local or cloud model providers to create agents, multi-agent teams, and AI workflows.
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 NPC-Worldwide/npcpy --skill naturalgit clone --depth 1 https://github.com/NPC-Worldwide/npcpyWrote 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/npc-worldwide/npcpy/natural)<a href="https://agentmods.dev/skills/npc-worldwide/npcpy/natural"><img src="https://agentmods.dev/badge/skills/npc-worldwide/npcpy/natural/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/npc-worldwide/npcpy/natural"><img src="https://agentmods.dev/badge/skills/npc-worldwide/npcpy/natural.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 | $0.00041 | $0.00163 |
| Opus 5.5 | $0.00016 | $0.00065 |
| Sonnet 5.5 | $0.00008 | $0.00033 |
| Haiku 4.5 | $0.00004 | $0.00016 |
Grade A, and why
natural 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 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.
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
natural
Render the provided prompt template with Jinja context and send it to the active NPC's LLM. The rendered text becomes the user prompt; the LLM response is placed in context['output'].
Inputs
promptsystem(default:'')
Steps
render_and_send→render_and_send.py
Usage
/run_jinx jinx_ref=natural input_values={"prompt": "<value>", "system": ""}
What ships with it
1 file 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.
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 First seen · 26 lines · 41 tokens per session scan A e9b11212f516
natural is a skill published in the GitHub repository NPC-Worldwide/npcpy (1,517 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 163 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model.
llm-prompting-guide
Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…
octave-ultra-mythic
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. REQUIRES octave-mastery and octave-compression.
metodo-3w1h
Dê a habilidade para agentes de IA de estruturar e otimizar prompts de imagens utilizando rigorosamente o método 3W1H (Who, What, Where, How) criado pelo Mário Lúcio. Utilize esta skill sempre que o usuário mencionar termos como 'gerar imagem', 'criar prompt de imagem', 'engenharia de prompt de imagem', 'fotorrealismo…
prompt-estruturado
Gera prompts a partir de uma estrutura modularizada com persona, contexto, tarefa, formato e regras.