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 Desko77/claude-code-skills-1c --skill lmstudio-apigit clone --depth 1 https://github.com/Desko77/claude-code-skills-1cWrote 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/desko77/claude-code-skills-1c/lmstudio-api)<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/lmstudio-api"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/lmstudio-api.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 | $0.00199 | $0.04643 |
| Opus 5 | $0.00100 | $0.02322 |
| Sonnet 5 | $0.00040 | $0.00929 |
| Haiku 4.5 | $0.00020 | $0.00464 |
Grade A, and why
lmstudio-api 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 4d 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 lmstudio-api — 54 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LM Studio API
Проверено вживую на LM Studio 0.4.x, 2026-08-07, локальный сервер на порту 1234
(AMD Strix Halo, 128 ГБ единой памяти). Замеры в конце - на qwen3-vl-30b-a3b-instruct.
Три поверхности API
| Поверхность | Путь | Назначение |
|---|---|---|
| OpenAI-совместимая | /v1/* |
инференс: chat/completions; models отдает только КАТАЛОГ скачанных |
| Нативная v0 (устаревшая) | /api/v0/* |
models с полем state; управления моделями нет |
| Нативная v1 | /api/v1/* |
с LM Studio 0.4.0, рекомендуемая: инференс + управление моделями |
Anthropic-совместимые эндпоинты тоже заявлены в доках, не проверялись.
Эндпоинты v1
POST /api/v1/chat (НЕ /api/v1/chat/completions)
GET /api/v1/models
POST /api/v1/models/load
POST /api/v1/models/unload
POST /api/v1/models/download
GET /api/v1/models/download/status
load: обязателен model - точный ключ модели. Опционально context_length,
eval_batch_size, flash_attention, num_experts, offload_kv_cache_to_gpu,
echo_load_config. Всегда ставить echo_load_config: true - ответ вернет фактически
примененный конфиг, и сразу видно, что сервер проигнорировал.
Ответ: {"type", "instance_id", "load_time_seconds", "status": "loaded", "load_config": {...}}.
Вызов БЛОКИРУЮЩИЙ - возвращается по факту загрузки, отдельно опрашивать готовность не нужно.
unload: обязателен instance_id, НЕ имя модели. Берется из loaded_instances[].id
ответа GET /api/v1/models.
GET /api/v1/models отдает {"models":[...]} с полями key, type, publisher,
architecture, quantization, size_bytes, max_context_length, capabilities,
loaded_instances[]. У инстанса - id и config с фактическими context_length,
parallel, flash_attention, eval_batch_size, num_experts и прочим.
Пустой loaded_instances = модель не загружена.
Инференс: два эндпоинта, и они НЕ равнозначны
/v1/chat/completions (OpenAI) |
/api/v1/chat (родной) |
|
|---|---|---|
| поле ввода | messages |
input |
| схема | лишние ключи проглатывает | строгая, лишний ключ -> 400 unrecognized_keys |
| управление reasoning | НЕТ (см. ниже) | reasoning первым классом |
| ответ | choices[].message.content |
output[].content |
| статистика | usage |
stats c reasoning_output_tokens |
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.
- 4d ago First seen · 285 lines · 199 tokens per session scan A e8905e184e29
lmstudio-api is a skill published in the GitHub repository Desko77/claude-code-skills-1c (56 stars, last pushed 5d ago), licensed MIT. It adds 199 tokens to every session and 4,643 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lmstudio-api, differing in 54 lines, and is treated as a copy.
Other skills, from other repositories
lmstudio-api
A reference for controlling LM Studio through its HTTP API. LM Studio is a local server for running AI models, and the guide covers checking, loading, unloading, and configuring models.
humanize-ai-text
A rewriting guide for turning text produced by language-model agents into more natural reports, documentation, letters, or posts. It keeps the original meaning, figures, and technical terms.
transcribe
A tool for turning video and audio recordings into written transcripts, with optional speaker separation and screen analysis. Speaker separation identifies which parts of the recording belong to different people.
composing-1c-queries
A guide to writing queries in the 1C:Enterprise query language, which reads and combines data from a 1C configuration. It requires checking the configuration's actual metadata before writing a query.
1c-naparnik
A set of tools for analyzing and editing BSL, the programming language used by 1C, plus searching 1C platform documentation and the ITS knowledge base. ITS is 1C's technical information system.
1c-web-test
A browser-testing tool for the 1C:Enterprise web client. It uses Playwright to navigate screens, fill forms, read tables and reports, and apply filters.