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.
git clone --depth 1 https://github.com/jgt87/local-llm-mcpWrote 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/commands/jgt87/local-llm-mcp/local_ask)<a href="https://agentmods.dev/commands/jgt87/local-llm-mcp/local_ask"><img src="https://agentmods.dev/badge/commands/jgt87/local-llm-mcp/local_ask/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/commands/jgt87/local-llm-mcp/local_ask"><img src="https://agentmods.dev/badge/commands/jgt87/local-llm-mcp/local_ask.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 | $0.00014 | $0.00292 |
| Opus 5.5 | $0.00006 | $0.00117 |
| Sonnet 5.5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
local_ask 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 5d 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
Request: $ARGUMENTS
If the request is empty, ask the user what to send.
Answer the request with local_ask. If it refers to a file or command output, read it yourself and include the relevant part in the prompt. Pick maxTokens to fit the expected answer length (160 is about 10 seconds). Present the answer with the model name and time taken.
Ground rules:
- Use the local-llm tools for the generation step; do the reading, trimming and checking yourself. The local model has no file access, no repo context and no memory between calls, so every call must carry all the text it needs.
- Keep maxTokens tight: locally it runs at roughly 16 tokens per second.
- Stay on the default provider unless the user asked for OpenRouter. Never send secrets, keys or private data to provider="openrouter".
- If a call fails because Ollama is unreachable, say so and stop; do not silently do the work yourself instead.
- Treat the reply as a draft. Check it against the source before presenting it, fix what is wrong, and say briefly what you changed.
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.
- 5d ago First seen · 21 lines · 14 tokens per session scan A 32b4e418e831
local_ask is a command published in the GitHub repository jgt87/local-llm-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 292 once invoked, about $0.0001 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 2026-10-27.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
prompt-show
Display full details of a saved prompt by ID.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.