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/igmarin/rails-ai-bridgeWrote 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/igmarin/rails-ai-bridge/copilot-instructions)<a href="https://agentmods.dev/instructions/igmarin/rails-ai-bridge/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/igmarin/rails-ai-bridge/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/igmarin/rails-ai-bridge/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/igmarin/rails-ai-bridge/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 | $0.01820 | $0.01820 |
| Opus 5 | $0.00910 | $0.00910 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
rails-ai-bridge 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 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DemoApp — Copilot Context
Auto-generated by rails-ai-bridge v5.2.0 Generated: 2026-09-15T03:10:26Z Rails 8.1.3.1 | Ruby 4.0.7
This file provides a high-level overview of this Rails application's structure, patterns, and conventions. As an AI assistant, use this context to quickly understand the project and generate idiomatic code that adheres to its design decisions. For deeper dives, use the live MCP tools referenced throughout this document.
Anti-hallucination rules
- Verify before you write (column, association, route, helper, gem).
- Mark assumptions with
[ASSUMPTION]. Silent guesses are forbidden. - This app is not average Rails. Query conventions and gems before scaffolding.
- Check the inheritance chain (filters, concerns, STI) before editing a controller or model.
- Empty tool output is information, not permission to invent.
- Re-query after writes. Stale tool output lies.
Engineering rules (read first)
Defaults for this codebase unless existing files clearly show a different pattern.
Controllers & strong parameters
- Permit attributes explicitly; never pass raw
paramsintoModel.new,update, orassign_attributes. - Extend
permitlists deliberately when adding fields; mirror neighboring actions in the same controller.
Authentication & authorization
- Guard mutating and sensitive reads with the app's existing auth (e.g.
before_actionfilters, policies). A public route does not imply public data. - Use
rails_get_controllersfor filters andrails_get_conventionsfor architecture hints when unsure.
Data access & performance
- Avoid N+1: use
includes/preload/eager_loadfor associations used in views or serializers. - Do not load unbounded collections: paginate list endpoints, use
find_eachin jobs, stream large exports. - Large or hot tables: check indexes before new
WHERE/ORDER BY; userails_get_schemabefore heavy queries.
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 First seen · 137 lines · 1,820 tokens per session scan A e1364ddd7b7d
rails-ai-bridge copilot-instructions.md is an instructions file published in the GitHub repository igmarin/rails-ai-bridge (14 stars, last pushed today), licensed MIT. It adds 1,820 tokens to every session, about $0.0091 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 2026-09-15.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.