A skill that sends suitable tasks to a language model running locally through LM Studio, instead of using the main model. It separates autonomous work from simple text transformations.

Use it to delegate file reading, project exploration, tool use, and mechanical text changes to local models. It also helps choose the appropriate local model tier.

It helps reduce use of the main model's quota for routine or lower-risk work. It also makes clear which tasks may be unsuitable for a smaller local model.

How fvanlookeren-bit/llm-Intern configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fvanlookeren-bit/llm-Intern. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fvanlookeren-bit/llm-Intern/main/.claude/skills/intern/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/fvanlookeren-bit/llm-Intern

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fvanlookeren-bit/llm-intern/intern/github.svg)](https://agentmods.dev/skills/fvanlookeren-bit/llm-intern/intern)

Your own site

<a href="https://agentmods.dev/skills/fvanlookeren-bit/llm-intern/intern"><img src="https://agentmods.dev/badge/skills/fvanlookeren-bit/llm-intern/intern/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fvanlookeren-bit/llm-intern/intern"><img src="https://agentmods.dev/badge/skills/fvanlookeren-bit/llm-intern/intern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,588 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.

Model	Per session	Once invoked
Fable 5.1	$0.00149	$0.01588
Opus 5.5	$0.00060	$0.00635
Sonnet 5.5	$0.00030	$0.00318
Haiku 4.5	$0.00015	$0.00159

Measured 2mo ago against content hash b9884747784d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

intern 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 2mo 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.

.claude/skills/intern/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intern (LM Studio local)

Delegar la tarea al modelo local de LM Studio vía el servidor MCP lm-studio, en vez de hacerla directo. LM Studio corre 100% local y no consume cuota del modelo grande ("ilimitado y gratis"), pero rinde peor en razonamiento complejo — este skill existe para decidir bien CUÁNDO delegar y CON QUÉ modelo, no solo cómo llamar la tool.

"El intern" no es sinónimo de subagentes (el tool Agent/Explore/ general-purpose, etc.): esos corren en el modelo grande y consumen su cuota igual que hacerlo directo. El intern es el MCP lm-studio — un modelo distinto, gratis, local.

1. Dos tiers, y las tools de cada uno

lm_studio_list_models muestra el tier= de cada modelo:

subagent (junior) — contexto largo y tool-calling confiable. Se le delega con autonomía: que lea los archivos él mismo, en vez de masticarle el contexto.
intern — el resto. Delegación mecánica, todo el contexto en el prompt.

El roster se configura con LM_STUDIO_SUBAGENT_MODELS="id-a,id-b". Es curado a propósito: el host reporta tool_use para todos los modelos no-embedding, hasta los de 1-2B, así que esa capability no sirve para decidir a quién confiarle un loop.

Tools:

lm_studio_generate — solo texto/código, POST directo al modelo, sin tools. Tier intern. Dale todo el contexto necesario en el prompt (datos, texto fuente, resultados de tus propias tool calls) — no puede ir a buscar nada él mismo.
lm_studio_agent — con tools MCP reales. Tier subagent. Le pasás mcp_servers (nombres de ~/.lmstudio/mcp.json, listalos con lm_studio_list_mcp_servers antes) y corre un loop de agente real: llama tools, lee resultados, repite hasta terminar (tope max_iterations, default 8). Usá el mínimo de MCPs necesario — cada uno agrega tools al contexto del modelo. Verificá cada dato contra el tool_trace que devuelve, no contra su prosa.
lm_studio_capacity — techo de memoria, modelos residentes y margen libre. Llamala antes de cargar un segundo modelo.
lm_studio_list_models — qué modelos hay, cuál está cargado y en qué tier.
lm_studio_list_mcp_servers — qué MCPs puede usar lm_studio_agent.

Read the full file on GitHub · 100 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.

2mo ago First seen · 100 lines · 149 tokens per session scan A b9884747784d

Subscribe to this mod's changes

intern is a skill published in the GitHub repository fvanlookeren-bit/llm-Intern (6 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 1,588 once invoked, about $0.0006 per session on Opus 5.5. 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.

Building agents

intern next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
internfvanlookeren-bit/llm-Intern	Skill	6	2mo ago	MIT	A	149	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

llm-Intern: Skill for Claude Code