Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bobmatnyc/claude-mpm-skillsnpx agentmods add skills/bobmatnyc/claude-mpm-skills/local-llm-opsWrote 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/bobmatnyc/claude-mpm-skills/local-llm-ops)<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/local-llm-ops"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/local-llm-ops/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/bobmatnyc/claude-mpm-skills/local-llm-ops"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/local-llm-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 60 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00033 | $0.00661 |
| Opus 5 | $0.00016 | $0.00331 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
local-llm-ops scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. Verify service: `curl http://localhost:11434/api/version` What it actually says
Local LLM Ops (Ollama)
Overview
Your localLLM repo provides a full local LLM toolchain on Apple Silicon: setup scripts, a rich CLI chat launcher, benchmarks, and diagnostics. The operational path is: install Ollama, ensure the service is running, initialize the venv, pull models, then launch chat or benchmarks.
Quick Start
./setup_chatbot.sh
./chatllm
If no models are present:
ollama pull mistral
Setup Checklist
- Install Ollama:
brew install ollama - Start the service:
brew services start ollama - Run setup:
./setup_chatbot.sh - Verify service:
curl http://localhost:11434/api/version
Chat Launchers
./chatllm(primary launcher)./chator./chat.py(alternate launchers)- Aliases:
./install_aliases.shthenllm,llm-code,llm-fast
Task modes:
./chat -t coding -m codellama:70b
./chat -t creative -m llama3.1:70b
./chat -t analytical
Benchmark Workflow
Benchmarks are scripted in scripts/run_benchmarks.sh:
./scripts/run_benchmarks.sh
This runs bench_ollama.py with:
benchmarks/prompts.yamlbenchmarks/models.yaml- Multiple runs and max token limits
Diagnostics
Run the built-in diagnostic script when setup fails:
./diagnose.sh
Common fixes:
- Re-run
./setup_chatbot.sh - Ensure
ollamais in PATH - Pull at least one model:
ollama pull mistral
Operational Notes
- Virtualenv lives in
.venv - Chat configs and sessions live under
~/.localllm/ - Ollama API runs at
http://localhost:11434
Related Skills
toolchains/universal/infrastructure/docker
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.
- 12d ago First seen · 101 lines · 33 tokens per session scan A 11a7d45aba3f
local-llm-ops is a skill published in the GitHub repository bobmatnyc/claude-mpm-skills (74 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 661 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
weknora-rag-search
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.
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.
qdrant
Manage Qdrant vector database via REST API. Use when the user asks to create or delete collections, upsert or search vectors, inspect points, filter by payload fields, manage snapshots, check cluster status, or debug semantic search issues. Covers collection CRUD, point upsert/search/scroll/count, payload indexes…
rag-answerer
RAG answerer that only answers from supplied context.