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 vendored-assetsgit 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/vendored-assets)<a href="https://agentmods.dev/skills/sybil-solutions/local-studio/vendored-assets"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/vendored-assets/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/vendored-assets"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/vendored-assets.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 | $0.00041 | $0.00586 |
| Opus 5.5 | $0.00016 | $0.00234 |
| Sonnet 5.5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
vendored-assets 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 vendored-assets — 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
Treat upstream artifacts as supply-chain inputs. Change their generator or documented import source, then regenerate; generated output is review evidence, not an editing surface.
Workflow
- Trace ownership. Identify the artifact, generator or exact import procedure, upstream source/version, license, consumers, tests, and shipped package or bundle. Search by asset and upstream project name to find current packaging scripts, generated artifacts, consumers, and history. Continue when every input and consumer is accounted for.
- Pin provenance. Resolve moving URLs, tags, branches, and omitted versions to an immutable release or artifact. Record project, version, path or URL, and digest in the generator or maintenance header. Omit a digest only when another enforced immutable source is recorded. Continue when a future run cannot silently select different bytes.
- Clear the license gate. Verify release metadata, license files, bundled notices, and the license trail retained in the distributed form. Continue when every distributed artifact has a verified retained license trail.
- Regenerate. Improve the generator or import reference first. Recover an exact procedure for generatorless assets; add a deterministic script only for recurring updates. Record a one-off procedure beside the artifact. A clean rerun must produce no diff.
- Audit the complete diff. Account for behavior, URLs and runtime fetches, source maps, notices, encoding, format changes, and additions or removals. For browser assets, also read browser-assets.md. Continue when every change is attributable and suspicious content is resolved or reported.
- Clear test and size gates. Record byte sizes before and after, use focused consumer tests, and compare bundle size or composition when shipped JavaScript, CSS, or registry output changes materially. Compare that output against the pre-update revision rather than measuring only current size. Continue when focused checks pass and every non-trivial size delta is explained.
- Close release impact. Apply root changeset routing for consumer-visible behavior, browser support, wire data, or meaningful shipped-size changes. Generated sections owned by barrels, AI docs, or migration tooling remain with the owners named in root instructions.
The task is complete when every input and consumer is accounted for, provenance and licenses are immutable and retained, regeneration is deterministic, every output change and non-trivial size delta is explained, focused checks pass or are reported as not runnable, and release impact is recorded.
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 · 48 lines · 41 tokens per session scan A b45cfc17cce2
vendored-assets is a skill published in the GitHub repository sybil-solutions/local-studio (1,828 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 586 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to vendored-assets, 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.