manage-llm-server

manage-llm-server is a skill for Claude Code, Codex from airiclenz/llama-launcher. It costs 66 tokens per session (1,738 once invoked), scanned A, original, MIT.

A tool for inspecting and controlling local language-model servers, including servers run by llama.cpp, Ollama, or LM Studio. It shows which model is loaded, what is running, and recent logs.

In plain words
What is it for?
Use it to list available model profiles, see the active server, switch models, and start, stop, restart, or troubleshoot a local language-model server.
Why use it?
It removes the need to remember separate commands for checking server state, changing models, or investigating a stuck model load. It also requires checking the current state before actions that could interrupt work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list available model profiles, see the active server, switch models, and start, stop, restart, or troubleshoot a local language-model server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/airiclenz/llama-launcher/manage-llm-server
Install

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.

Any agent
npx skills add airiclenz/llama-launcher --skill manage-llm-server
Clone the repo
git clone --depth 1 https://github.com/airiclenz/llama-launcher

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for manage-llm-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/airiclenz/llama-launcher/manage-llm-server/github.svg)](https://agentmods.dev/skills/airiclenz/llama-launcher/manage-llm-server)
Your own site
<a href="https://agentmods.dev/skills/airiclenz/llama-launcher/manage-llm-server"><img src="https://agentmods.dev/badge/skills/airiclenz/llama-launcher/manage-llm-server/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.

agentmods 80×15 button for manage-llm-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/airiclenz/llama-launcher/manage-llm-server"><img src="https://agentmods.dev/badge/skills/airiclenz/llama-launcher/manage-llm-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.01738
Opus 5 $0.00033 $0.00869
Sonnet 5 $0.00013 $0.00348
Haiku 4.5 $0.00007 $0.00174

Measured 11d ago against content hash 009c45535ed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

manage-llm-server 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 11d 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.

skills/manage-llm-server/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

manage-llm-server

llama-launcher is a CLI for running and switching local LLM servers (llama.cpp, Ollama, LM Studio). Models are defined as profiles; loading a profile starts the right server and loads its model. Use this skill to inspect state, switch profiles, and tail logs.

Safety rules (do these first)

  1. Always start with a passive inspectionllama-launcher status --json and llama-launcher list --json. Do not call load, unload, start, or stop until you've shown the user what's currently running and have explicit confirmation to change it.
  2. Check for in-flight work before mutating. Switching, unloading, or stopping a model interrupts any request or job currently using it. If a high uptime_seconds coincides with the user actively working, assume the model may be in use and confirm before changing it.
  3. load <profile> is idempotent — it's a no-op if the requested profile is already active. Only reach for --restart if the user explicitly asks to force a restart, or if the server is in a bad state confirmed via logs.
  4. unload and stop end the session — any in-flight requests will fail. Confirm before calling.

Command reference

Passive (safe to run any time):

Command Purpose
llama-launcher list / --json Enumerate available profiles (name, title, description, backend, model file, gpu_layers, context_size). title is the human-readable label; description is omitted when unset.
llama-launcher status / --json Per-backend: running, address, active_profile, active_model, pid, uptime_seconds.
llama-launcher logs <backend> Tail the last chunk of an instance's log. Add -f to follow.
llama-launcher logs clean --days N / --all Prune old logs.
llama-launcher config validate Check the config file for errors.
llama-launcher version Print version.

Mutating (confirm with user first):

Command Purpose
llama-launcher load <profile> Activate a profile. No-op if already active.
llama-launcher load <profile> --restart Force a restart even if active.
llama-launcher unload [profile] Stop the server / unload the model.
llama-launcher start [--profile p] Start a server, optionally with a profile.
llama-launcher stop [target] Stop a server by host:port or backend name.

Read the full file on GitHub · 96 lines

Changes

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.

  1. 11d ago First seen · 96 lines · 66 tokens per session scan A 009c45535ed9

Subscribe to this mod's changes

manage-llm-server is a skill published in the GitHub repository airiclenz/llama-launcher (2 stars, last pushed 28d ago), licensed MIT. It adds 66 tokens to every session and 1,738 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 2026-08-31.