A command-line interface for sending text and multimedia files to language models from OpenAI, Anthropic, Google Gemini, or Ollama.

Run one-off or interactive chats, analyze files, summarize content, and select models through saved aliases or provider settings.

It gives developers one terminal workflow for choosing models and processing files across several providers.

llm-cli — Skill for Claude Code by glebis

Install

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.

Any agent

npx skills add glebis/claude-skills --skill llm-cli

Clone the repo

git clone --depth 1 https://github.com/glebis/claude-skills

Made for: Claude Code.

Or install llm-cli, the plugin that ships this one along with the rest of its 1 skill.

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/glebis/claude-skills/llm-cli.svg)](https://agentmods.dev/skills/glebis/claude-skills/llm-cli)

Your own site

<a href="https://agentmods.dev/skills/glebis/claude-skills/llm-cli"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/llm-cli.svg" alt="Measured on agentmods" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,636 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Excessive Agency · line 123
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
high Excessive Agency · line 132
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
high Excessive Agency · line 206
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
medium Rogue Agent · line 85
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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	$0.00040	$0.01636
Opus 5	$0.00020	$0.00818
Sonnet 5	$0.00008	$0.00327
Haiku 4.5	$0.00004	$0.00164

Measured 4d ago against content hash 2253fa49d51e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

llm-cli 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.

The scan reads SKILL.md. This mod also ships 5 executable files (executor.py, input_handler.py, llm_skill.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

llm-cli/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM CLI Skill

Purpose

This skill enables seamless interaction with multiple LLM providers (OpenAI, Anthropic, Google Gemini, Ollama) through the llm CLI tool. It processes textual and multimedia information with support for both one-off executions and interactive conversation modes.

When to Use This Skill

Trigger this skill when:

User wants to process text/files with an LLM
User needs to choose between multiple available LLMs
User wants interactive conversation with an LLM
User needs to pipe content through an LLM for processing
User wants to use specific model aliases (e.g., "claude-opus", "gpt-4o")

Example user requests:

"Process this file with Claude"
"Analyze this text with the fastest available model"
"Start an interactive chat with OpenAI"
"Use Gemini to summarize this document"
"Chat mode with my local Ollama instance"

Supported Providers & Models

OpenAI

Latest Models (2025):
- gpt-5 - Most advanced model
- gpt-4-1 / gpt-4.1 - Latest high-performance
- gpt-4-1-mini / gpt-4.1-mini - Smaller, faster version
- gpt-4o - Multimodal omni model
- gpt-4o-mini - Lightweight multimodal
- o3 - Advanced reasoning
- o3-mini / o3-mini-high - Reasoning variants

Aliases: openai, gpt

Anthropic

Latest Models (2025):
- claude-sonnet-4.5 - Latest flagship model
- claude-opus-4.1 - Complex task specialist
- claude-opus-4 - Coding specialist
- claude-sonnet-4 - Balanced performance
- claude-3.5-sonnet - Previous generation
- claude-3.5-haiku - Fast & efficient

Aliases: anthropic, claude

Google Gemini

Latest Models (2025):
- gemini-2.5-pro - Most advanced
- gemini-2.5-flash - Default fast model
- gemini-2.5-flash-lite - Speed optimized
- gemini-2.0-flash - Previous generation
- gemini-2.5-computer-use - UI interaction

Aliases: google, gemini

Ollama (Local)

Popular Models:
- llama3.1 - Meta's latest (8b, 70b, 405b)
- llama3.2 - Compact versions (1b, 3b)
- mistral-large-2 - Mistral flagship
- deepseek-coder - Code specialist
- starcode2 - Code models

Read the full file on GitHub · 208 lines

Files

What ships with it

16 files 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.

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.

4d ago First seen · 208 lines · 40 tokens per session scan A 2253fa49d51e

Subscribe to this mod's changes

llm-cli is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,636 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 2026-09-03.

Data and AI Prompting

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens