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.
git clone --depth 1 https://github.com/xberg-io/liter-llmWrote 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/plugins/xberg-io/liter-llm/plugin)<a href="https://agentmods.dev/plugins/xberg-io/liter-llm/plugin"><img src="https://agentmods.dev/badge/plugins/xberg-io/liter-llm/plugin/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/plugins/xberg-io/liter-llm/plugin"><img src="https://agentmods.dev/badge/plugins/xberg-io/liter-llm/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
liter-llm 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 today.
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.
What it actually says
{
"name": "liter-llm",
"description": "Universal LLM API client for 174 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.",
"version": "2.3.0",
"author": {
"name": "Kreuzberg, Inc.",
"email": "[email protected]",
"url": "https://xberg.io"
},
"homepage": "https://xberg.io",
"repository": "https://github.com/xberg-io/liter-llm",
"license": "MIT",
"keywords": [
"llm",
"openai",
"proxy",
"embeddings",
"mcp"
],
"mcpServers": {
"liter-llm": {
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/mcp-launch.sh",
"args": [
"mcp",
"--transport",
"stdio"
]
}
}
}
What it installs
The manifest is a name and a version. 7 skills, 3 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 374 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill liter-llm A 112 tokens
- Skill liter-llm-using-the-mcp-server A 44 tokens
- Skill liter-llm-calling-llms A 44 tokens
- Skill liter-llm-embeddings-and-search A 43 tokens
- Skill liter-llm-tool-calling A 35 tokens
- Skill liter-llm-running-the-proxy A 45 tokens
- Skill liter-llm-streaming-responses A 34 tokens
- Command liter-llm-stream A 7 tokens
- Command liter-llm-chat A 10 tokens
- Command index A 0 tokens
- MCP server liter-llm A not measured
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.
- today Changed 3c0229e660bb
- 3d ago Changed 3cf6efa71c23
- 4d ago Changed adb23f546ae6
- 5d ago Changed · -1 lines bcf89cfaf868
- 9d ago Changed 1805529d71bd
- 10d ago Changed cd3e6b4d4a09
- 11d ago Changed 29773737cd89
- 13d ago Changed 3fe6a8a616c6
- 19d ago Changed 50ab39e2d065
- 24d ago First seen · 32 lines scan A 2f1a70cfc5aa
liter-llm is a plugin published in the GitHub repository xberg-io/liter-llm (261 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
wiki
AI-generated documentation backend for code repositories.
scg
Source Capability Graph — map connector reachability + route/traverse it for Agentic Search.
mewbo-apps-builder
app-builder + app-repair agents and the submitapp / appdata session tools for the Mewbo Apps sub-product.
widget-builder
st-widget-builder sub-agent for stlite console widgets.
harness
mewbo-harness skill — how this harness itself behaves (result caps, timeouts, paths, deferred tools, delegation).
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.