crmne/ruby_llm is a Ruby framework that provides one interface for building AI chats, agents, tools, retrieval-augmented generation, and multimodal workflows across multiple model providers. Ruby and Rails developers use it to add AI features without rewriting application code for each provider. The catalogue contains instructions and a skill for working with the framework.
Borrowing it
Nothing to install: this file belongs to crmne/ruby_llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crmne/ruby_llm/main/AGENTS.mdgit clone --depth 1 https://github.com/crmne/ruby_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/instructions/crmne/ruby_llm/agents-md)<a href="https://agentmods.dev/instructions/crmne/ruby_llm/agents-md"><img src="https://agentmods.dev/badge/instructions/crmne/ruby_llm/agents-md/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/instructions/crmne/ruby_llm/agents-md"><img src="https://agentmods.dev/badge/instructions/crmne/ruby_llm/agents-md.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 | $0.06277 | $0.06277 |
| Opus 5.5 | $0.02511 | $0.02511 |
| Sonnet 5.5 | $0.01255 | $0.01255 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
ruby_llm AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
How RubyLLM is built. For coding agents first, humans welcome. Read CONTRIBUTING.md for what gets accepted; this file is how to write it.
What this is
RubyLLM is a Ruby AI framework: chat, tools, agents, structured output, embeddings, reranking, images, video, audio, OCR, moderation, and Rails integration behind one API, with twenty-three providers in the box. Plain Ruby (>= 3.2), a handful of small dependencies, no heavyweight abstractions.
Framework structure
There are two main parts: the public Ruby API and the providers and protocols that connect it to AI services.
- The public API has two families. Text generation and conversations use
Chat,Message,Tool, andAgent, with structured output, streaming, and loop control. Individual AI operations usepaint,animate,speak,transcribe,ocr,moderate,embed, andrerank, each with a typed result. These operations do not require a conversation; some have streaming or asynchronous lifecycles. - Providers and protocols connect both families to services. Providers supply endpoints, authentication, catalogs, protocol selection, and service-specific settings. Protocols implement request formats, response parsing, streaming, and error normalization. Format quirks belong in protocol dialects selected by providers.
- Shared services support the API. Model and provider resolution, configuration, usage and cost tracking, instrumentation, batches, file storage, and prompt caching belong to the framework as a whole. Do not force an independent operation through
Chatto reuse them. - Rails adds a native application integration. The same conversation API works on application-owned records, with Active Record persistence, Active Storage attachments, Hotwire streaming, Active Job workflows, and generators. Individual operations remain available in Rails services and jobs. Rails integration builds on the Ruby API; the plain-Ruby library has no Rails dependency.
- Conversation history belongs to the application. Build requests from the local transcript. Do not introduce provider-stored conversation cursors or continue a remote history that can diverge from local messages. Defer provider features that require that lifecycle. Preserving native response content for replay is different from storing a conversation remotely.
- Realtime conversations are outside 2.0's scope. Keep speech generation and transcription, including streamed results. A WebSocket transport for one operation does not justify a separate live conversation API. Hosted asynchronous research jobs remain individual operations, not persisted chat sessions.
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 Changed · +8 tokens per session f532e3e8bfb4
- 9d ago Changed · +94 tokens per session 7e49c67f5921
- 12d ago Changed · +42 tokens per session 1394f13c8e4b
- 14d ago Changed · +28 lines · +326 tokens per session 680c8de08138
- 15d ago Changed · +1 lines · +112 tokens per session 0d20f24012d5
- 23d ago Changed · +10 tokens per session 5c3345783015
- 25d ago Changed 4ebdcd132730
- 26d ago Changed · +1 lines · +127 tokens per session 5942a1e7d1f0
- 27d ago Changed · -2 tokens per session 99ba6f997d0d
- 28d ago First seen · 209 lines · 5,560 tokens per session scan A 308edc766515
ruby_llm AGENTS.md is an instructions file published in the GitHub repository crmne/ruby_llm (4,489 stars, last pushed yesterday), licensed MIT. It adds 6,277 tokens to every session, about $0.0251 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.