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 glebis/claude-skills --skill local-modelsgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/local-models)<a href="https://agentmods.dev/skills/glebis/claude-skills/local-models"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/local-models/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/glebis/claude-skills/local-models"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/local-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00116 | $0.01488 |
| Opus 5 | $0.00058 | $0.00744 |
| Sonnet 5 | $0.00023 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
local-models 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 8d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-models
Quick access to local LLMs through llama.cpp, reusing the GGUF models already pulled by Ollama (no re-download for text and embeddings). Everything runs on the machine — no API key, no network, no per-token cost.
When to use this skill
Reach for local models instead of a cloud API when the task is:
- Privacy-sensitive — redacting PII, processing personal notes, health data, secrets-adjacent text. The data never leaves the machine.
- Offline — no network available, or the user explicitly wants local-only.
- High-volume / low-stakes — classifying or tagging hundreds of items, where a small model is good enough and cloud cost/latency would add up.
- A fast throwaway — a quick summary, translation, or "what is this" where round-tripping to a frontier model is overkill.
Prefer a frontier (Claude) model when the task needs strong reasoning, long context, careful code, or high accuracy — these local models are small (0.6–4B).
The core trick: reuse Ollama's models
Ollama stores model weights as extension-less GGUF blobs under
~/.ollama/models/blobs/. These are ordinary GGUF files — llama.cpp loads
them directly. scripts/ollama_blob.py reads Ollama's manifests and resolves a
friendly name (e.g. qwen2.5:3b) to its weights blob path. No conversion, no
duplicate downloads.
Usage
The entry point is scripts/lm. Run scripts/lm help for the full list. Invoke
it with an absolute path, e.g. ~/ai_projects/claude-skills/local-models/scripts/lm.
lm models # list local models (text / vision / embed)
lm ask [MODEL] "PROMPT" # one-shot prompt (default qwen2.5:3b)
lm chat [MODEL] # interactive REPL
# Text presets — accept a file path, inline text, OR stdin:
lm summarize report.md
cat notes.txt | lm tldr
lm keywords article.txt
lm anonymize transcript.txt # → [NAME] [EMAIL] [PHONE] [ADDRESS] ...
lm proofread draft.md
lm translate German "Good morning"
lm classify "praise,complaint,question" feedback.txt # → one label
lm extract "invoice_number, total, due_date" invoice.txt # → JSON
# Vision (downloads model+projector once via HuggingFace — see note below):
lm describe-image photo.jpg
lm tag-image screenshot.png
lm vision photo.jpg "What brand is the shoe?"
# Embeddings & serving:
lm embed "text to embed" # → OpenAI-style JSON vector
lm serve qwen2.5:3b 8080 # OpenAI-compatible server on :8080
What ships with it
3 files 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.
- 8d ago First seen · 108 lines · 116 tokens per session scan A 560e903ce7ff
local-models is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 116 tokens to every session and 1,488 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 2026-09-03.
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.