Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jerry0022/dotclaude/plugin install local-llmWrote 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/jerry0022/dotclaude/local-llm-setup)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/local-llm-setup"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/local-llm-setup.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 | $0.00096 | $0.00915 |
| Opus 5 | $0.00048 | $0.00458 |
| Sonnet 5 | $0.00019 | $0.00183 |
| Haiku 4.5 | $0.00010 | $0.00092 |
Grade A, and why
local-llm-setup 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-llm-setup
Guided flow to connect this plugin to a running AnythingLLM Desktop instance.
What this skill does
- Confirms the user has installed AnythingLLM Desktop and generated an API key.
- Asks the user to paste the API key.
- Saves the key to
~/.claude/local-llm/config.json(user-global, outside any git repo). - Verifies the key against
GET /api/v1/auth. - Auto-creates the
claude-codeworkspace if missing. - Reports the resulting phase.
Step 1 — Precondition check
Before asking for the key, tell the user what they need:
AnythingLLM Desktop must be installed and running. If not yet installed: https://anythingllm.com/download After install:
- Open AnythingLLM.
- Settings → Developer API → Generate API Key.
- Copy the key.
- (Recommended) Configure the LLM provider to Ollama with Gemma 4 E4B:
- HuggingFace page: https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF
- Ollama pull tag:
hf.co/bartowski/google_gemma-4-e4b-it-gguf:bf16(HuggingFace GGUF — supported by Ollama ≥ v0.3.13; pull via the AnythingLLM UI orollama pull). If Ollama is not installed, AnythingLLM can download it during the provider setup. Any other model configured in AnythingLLM will also work — the plugin uses whatever the workspace is set to.
Step 2 — Ask for the key
Ask the user in chat (not via AskUserQuestion — the key is free-form text, not a multiple choice):
Paste your AnythingLLM API key here (or type
cancelto abort).
Wait for the user's next message. If the response is cancel, stop and report that no changes were made.
Otherwise, treat the user's message as the API key. Do not echo the key back in chat.
Step 3 — Save and verify
Run the save-and-verify script, passing the key via argv:
node "${CLAUDE_PLUGIN_ROOT}/scripts/save-api-key.js" "<paste-the-key-here>"
The script writes to ~/.claude/local-llm/config.json and probes AnythingLLM. It prints a single-line JSON result to stdout with these shapes:
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.
- 6d ago First seen · 74 lines · 96 tokens per session scan A c8827852623c
local-llm-setup is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 915 once invoked, about $0.0005 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
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.