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 ci-maintenancegit 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/ci-maintenance)<a href="https://agentmods.dev/skills/sybil-solutions/local-studio/ci-maintenance"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/ci-maintenance/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/sybil-solutions/local-studio/ci-maintenance"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/ci-maintenance.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 | $0.00036 | $0.00514 |
| Opus 5.5 | $0.00014 | $0.00206 |
| Sonnet 5.5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
ci-maintenance 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 3d 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.
This is a copy
100% identical to ci-maintenance — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Audit the trust boundary before editing. This skill owns Actions event semantics, workflow security, permissions, action pinning, setup reuse, untrusted inputs, timeouts, concurrency, and artifact trust boundaries.
Workflow
- Decide whether this is a review or an implementation. Reviews produce evidence-backed findings without editing; implementations continue through the smallest boundary-preserving change.
- Inspect every affected workflow, composite action, and caller. List all affected jobs and actions before proceeding.
- For each job, record the trigger, actor/fork status, workflow revision, checked-out revision, permissions, credentials, and every external input and consumer. Include artifacts, caches, outputs, PR fields, refs, dispatch inputs, generated files, and called actions.
- Consult current GitHub documentation for every platform-sensitive decision. Repository examples establish local convention, not platform semantics.
- Apply every applicable rule:
- Default workflow permissions to empty and grant minimal job permissions.
- Reuse the repository's shared setup action unless the environment must differ.
- Give executable jobs intentional matrices and realistic timeouts.
- Pin external actions and reusable workflows to full commit SHAs with readable release comments; verify each SHA belongs to that upstream release.
- Analyze event choice, checkout revision, and credential persistence together.
- Pass untrusted expressions through environment variables; validate and quote them before use.
- Derive concurrency from interruption safety.
- For forks, privileged credentials, publication, or cross-run data, read privileged-workflows.md.
- Run the narrowest syntax and repository checks, inspect the complete diff, and identify behavior testable only on GitHub-hosted runners.
For local patterns, inspect the current shared setup action and the nearest workflow with the same trust boundary. Use ordinary check workflows for routine precedent and privileged publication workflows only for equivalent trust boundaries.
The task is complete when every affected job and caller has a recorded trust boundary, every applicable rule has evidence or a compensating control, local checks pass, and GitHub-only verification is identified. Reviews report every failure with evidence; implementations resolve every failure and contain only intended behavior.
What ships with it
1 file 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.
- 3d ago First seen · 49 lines · 36 tokens per session scan A d71bcff16658
ci-maintenance is a skill published in the GitHub repository sybil-solutions/local-studio (1,828 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 514 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ci-maintenance, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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.
translator
Translates text between languages. Use this when the user wants to translate a word, phrase, or passage into another language.
kitchen-adventure
Act as a dungeon master for a text-based adventure set in a world where everyone is a sentient kitchen appliance. Trigger when user says "start kitchen adventure".
mood-music
A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
budget-tracker
Track daily expenses and income. Use when the user wants to log spending, record a purchase, add income, or see a budget summary.
query-wikipedia
Query summary from Wikipedia for a given topic.