What is rails-agent-skills AGENTS.md?

A set of instructions for coding agents working on Ruby on Rails applications. It requires test-driven development, or writing and running a failing test before implementing the missing feature, and describes a daily workflow from understanding the app to opening a pull request.

Loading relevant Rails context, planning tests, confirming a failing test, implementing features, running the full test suite, updating documentation, reviewing changes, and preparing pull requests.

It prevents code from being written before the expected behaviour is tested. The required sequence helps catch mistakes through tests, linters, documentation, and review.

How igmarin/rails-agent-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to igmarin/rails-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/igmarin/rails-agent-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/igmarin/rails-agent-skills

Made for: Codex, OpenCode.

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/instructions/igmarin/rails-agent-skills/agents-md.svg)](https://agentmods.dev/instructions/igmarin/rails-agent-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/igmarin/rails-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/igmarin/rails-agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,330 This file is loaded in full into every session.

When invoked 1,330 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.01330	$0.01330
Opus 5	$0.00665	$0.00665
Sonnet 5	$0.00266	$0.00266
Haiku 4.5	$0.00133	$0.00133

Measured 8d ago against content hash daf95ee45210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rails-agent-skills 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 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.

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rails Agent Skills

This file is the host-context source of truth. CLAUDE.md and GEMINI.md point here.

Install igmarin/ruby-core-skills next to this pack. Skills marked (from core) live there.

Tests gate implementation

Implementation waits until a test exists, has been run, and fails because the feature is missing — not because of a typo or setup error. Wrote code first? Delete it and start over.

plan-tests → write failing test → confirm RED
  → propose implementation → implement → confirm GREEN
  → linters + full suite → write-yard-docs *(from core)* → code-review → PR

Daily loop

flowchart LR
  A[Task] --> B[load-context]
  B --> C[plan-tests]
  C --> D[write-tests RED]
  D --> E[implement GREEN]
  E --> F[docs + review]
  F --> G[PR]

flowchart TB
  subgraph thisRepo[rails-agent-skills]
    atomics[28 atomics]
    personas[9 personas]
  end
  core[ruby-core-skills]
  thisRepo --> core

When to load a skill

Read the matching SKILL.md before acting. Descriptions are triggers only — the body is the procedure.

Rails skills

Skill	Use when
`load-context`	Existing app. Load schema, routes, one neighbor.
`setup-environment`	First-time setup. Do not echo secrets.
`plan-tests`	Choosing the first failing spec.
`write-tests`	Writing or cleaning RSpec.
`test-service`	Service specs under `spec/services/`.
`code-review`	Reviewing a Rails PR or diff.
`security-check`	XSS, CSRF, SQLi, secrets, auth bypass.
`review-architecture`	Fat models/controllers, boundaries.
`review-migration`	Production-safe migrations.
`apply-stack-conventions`	PostgreSQL + Hotwire + Tailwind.
`apply-code-conventions`	DRY/YAGNI/PORO by path. Linter is style SoT.
`implement-authorization`	Pundit, CanCanCan, policies.
`implement-background-job`	Active Job, Sidekiq, Solid Queue.
`implement-graphql`	graphql-ruby schema, resolver, mutation.
`implement-hotwire`	Frames, streams, Stimulus.
`optimize-performance`	N+1, slow queries, caching.
`version-api`	REST v1/v2, deprecation.
`seed-database`	Seeds vs fixtures vs factories.
`refactor-code`	Structure change, same behavior.
`generate-api-collection`	REST collections. Not GraphQL.
`create-engine`	Scaffold a Rails engine.
`test-engine`	Dummy app and engine specs.
`document-engine`	Engine README and install docs.
`create-engine-installer`	Install generators.
`review-engine`	Engine isolation and host contract.
`release-engine`	SemVer release.
`extract-engine`	Host feature → engine.
`upgrade-engine`	Cross-version compatibility.

Read the full file on GitHub · 121 lines

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.

8d ago First seen · 121 lines · 1,330 tokens per session scan A daf95ee45210

Subscribe to this mod's changes

rails-agent-skills AGENTS.md is an instructions file published in the GitHub repository igmarin/rails-agent-skills (24 stars, last pushed 17d ago), licensed MIT. It adds 1,330 tokens to every session, about $0.0066 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 2026-08-30.

Languages Ruby TDD Testing agent-skills ruby-on-rails-skills

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

rails-agent-skills: Instructions file for Codex