Local Studio is a local-first control panel for running, managing, and using self-hosted large language model backends such as vLLM, SGLang, llama.cpp, and ExLlama. It lets users launch models, monitor GPU and runtime state, chat through OpenAI-compatible endpoints, and run agent sessions from a desktop or connected mobile device. The catalogue skills and instruction support agent workflows with Local Studio and its controllers.
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 sybil-solutions/local-studio --skill automationsgit clone --depth 1 https://github.com/sybil-solutions/local-studioWrote 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/sybil-solutions/local-studio/automations)<a href="https://agentmods.dev/skills/sybil-solutions/local-studio/automations"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/automations.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 | $0.00049 | $0.00976 |
| Opus 5 | $0.00024 | $0.00488 |
| Sonnet 5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
automations 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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automations
An automation is a saved prompt Local Studio re-runs on a schedule. By default each run happens in its own fresh session that cannot see this conversation, in a project directory, on a model; an automation can instead be attached to an existing session, and then every run continues that thread. Automations are the same records the user sees in the Automations tab — the tools below read and write that one store, so anything you change shows up there immediately, and anything the user changes there is what you will read back.
Use these tools whenever the user wants work to keep happening without them asking again ("every morning…", "check on this hourly", "remind me weekly"), and whenever they ask about a job that is already scheduled.
Tools
list_automations— every automation: id, schedule, active/paused, next run, how the last run ended.read_automation— one automation in full: its exact prompt, model, directory, and its run history (last 20 runs, with what each run reported).schedule_automation— create one.update_automation— change name, prompt, schedule, model, directory or session in place.set_automation_status— pause or resume.run_automation_now— run it immediately and report the outcome; waits for the run to finish.delete_automation— remove it and its history, permanently.
Where a run happens
Runs are fresh by default: no memory of earlier runs, so the prompt has to carry everything the run needs. Pass sessionId to schedule_automation or update_automation to attach the automation to an existing chat instead — the run resumes that session, reads what is already in it, and appends its work to that thread. Pass sessionId: "" to detach and go back to fresh runs.
Attach when the recurring work only makes sense as a continuation ("keep updating the migration notes in this thread"). Leave it fresh when each run should stand alone. A session that has been deleted does not break the automation: that run falls back to a fresh session and records why in its summary, which read_automation shows.
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.
- 7d ago First seen · 47 lines · 49 tokens per session scan A 8719b61695c6
automations is a skill published in the GitHub repository sybil-solutions/local-studio (1,753 stars, last pushed 4d ago), licensed Apache-2.0. It adds 49 tokens to every session and 976 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
send-email
Call the runintent tool with the following exact parameters.
rag-code-review
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review"…
olares-knowledge
Olares Knowledge via olares-cli knowledge — manage download-server URL, yt-dlp, aria2, torrent, HuggingFace, and Wise download tasks: create/list/inspect/pause/resume/cancel/remove, prefs, sync, and file probes. Requires Olares 1.12.7+. Not for installer download or copying a Drive file with files download.
olares-search
Olares search via olares-cli search — the Desktop global search over Drive files, Sync (Seafile) libraries, Google Drive, Dropbox, Wise/Knowledge, and installed applications, with paging and JSON output. On Olares 1.12.7+ one search drive (alias search files) covers all four file sources. Use for Olares search…
session-librarian
Organize sessions by prompt: find, rename, archive, prune.
mood-tracker
A simple mood tracking skill that stores your daily mood and comments. Use this when the user wants to log their mood, track how they feel, or see their mood history.