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/.github/copilot-instructions.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/copilot-instructions)<a href="https://agentmods.dev/instructions/crmne/ruby_llm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/crmne/ruby_llm/copilot-instructions/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/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/crmne/ruby_llm/copilot-instructions.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 | $0.01811 | $0.01811 |
| Opus 5.5 | $0.00724 | $0.00724 |
| Sonnet 5.5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
ruby_llm copilot-instructions.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 8d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for RubyLLM
Use AGENTS.md and CONTRIBUTING.md as the source of truth for every change,
review, and triage. AGENTS.md describes how the code is built and the
boundaries Archspec.rb enforces; CONTRIBUTING.md describes what the project
accepts. When they and this file disagree, they win.
The four things every change is judged on, in order: the public API reads like Ruby a Rails developer already knows; persisted Rails records behave exactly like the plain-Ruby objects; providers and protocols stay in their layers with no wire vocabulary in the domain; and the work is small, tested, documented, and free of implementation comments.
Framework structure
RubyLLM is an AI framework with two main parts: its public Ruby API and its
providers and protocols. The API covers conversations (Chat, Message,
Tool, Agent, structured output, streaming, and loop control) and individual
operations (paint, animate, speak, transcribe, ocr, moderate, embed,
and rerank). Use the relevant operation instead of routing every AI feature
through a chat.
Providers supply endpoints, credentials, catalogs, and protocol selection. Protocols implement request and response formats, including dialect quirks. Model resolution, configuration, accounting, instrumentation, batches, and provider resources support both API families.
Rails integration brings the same API to application records, with Active
Record persistence, Active Storage attachments, Hotwire streaming, jobs, and
generators. Preserve that native Rails experience without introducing Rails
dependencies into the plain-Ruby library. See AGENTS.md for the boundaries.
Provider documentation
Apply the provider acceptance policy to documentation-only requests too. Flag provider listings, promotional links, and dedicated setup sections for third-party services that only change an existing provider's API base URL or API key as out of scope. Point contributors to documenting RubyLLM integration in their service's own documentation. Keep generic endpoint configuration in the shared guide; provider-specific additions must support an approved core integration or explain a distinct RubyLLM requirement.
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.
- 8d ago Changed · +4 lines · +71 tokens per session e681a3d1f008
- 27d ago Changed · +8 lines · +116 tokens per session 72bbb6a7f45c
- 1mo ago Changed · +10 lines · +95 tokens per session e1ca8ab5e879
- 1mo ago Changed · +19 lines · +202 tokens per session 8ddc858b4fbe
- 1mo ago First seen · 105 lines · 1,327 tokens per session scan A f1d65b2c93ca
ruby_llm copilot-instructions.md is an instructions file published in the GitHub repository crmne/ruby_llm (4,488 stars, last pushed yesterday), licensed MIT. It adds 1,811 tokens to every session, about $0.0072 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 2026-09-05.
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.