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 xuiltul/animaworks --skill local-llm-toolgit clone --depth 1 https://github.com/xuiltul/animaworksWrote 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/xuiltul/animaworks/local-llm-tool)<a href="https://agentmods.dev/skills/xuiltul/animaworks/local-llm-tool"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/local-llm-tool.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00403 |
| Opus 5 | $0.00025 | $0.00201 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
local-llm-tool 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 7d 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
Local LLM Tool
External tool for text generation and chat via local LLM (Ollama/vLLM).
Invocation via Bash
Use Bash with animaworks-tool local_llm <subcommand> [args]. See Actions below for syntax.
Actions
generate — Text generation
{"tool_name": "local_llm", "action": "generate", "args": {"prompt": "prompt text", "system": "system prompt (optional)", "temperature": 0.7, "max_tokens": 2048}}
chat — Multi-turn chat
{"tool_name": "local_llm", "action": "chat", "args": {"messages": [{"role": "user", "content": "question"}], "system": "system prompt (optional)"}}
models — List available models
{"tool_name": "local_llm", "action": "models", "args": {}}
status — Server status
{"tool_name": "local_llm", "action": "status", "args": {}}
CLI Usage (S/C/D/G-mode)
animaworks-tool local_llm generate "prompt" [-S "system prompt"]
animaworks-tool local_llm list
animaworks-tool local_llm status
Notes
- Ollama or vLLM server must be running
- Use -s/--server to specify server URL
- Use -m/--model to specify model
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.
- 7d ago First seen · 52 lines · 50 tokens per session scan A b4f7ce2fe5bf
local-llm-tool is a skill published in the GitHub repository xuiltul/animaworks (254 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 403 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
local-llm-ops
Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.
llm-finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization.
ml-engineer
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
prompt-engineer
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization.
analyze_current
Read and understand the current baseline implementation. Extract all relevant information about the existing approach without modifying anything, and record the analysis as a structured JSON entry.