railway-skills: Instructions file for Claude Code

AGENTS.md

railway-skills AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from railwayapp/railway-skills. It costs 1,756 tokens per session, scanned A, original, MIT.

Instructions for Railway agent plugins, which let coding agents work with Railway, a platform for deploying and running applications. They explain the plugin and skill structure across several coding-agent tools.

In plain words
What is it for?
Use them to understand the plugin files, marketplace entries, Railway skills, MCP connection, and command hooks for each supported tool.
Why use it?
They keep the shared Railway integration consistent when it is packaged for different agent environments.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

This is railwayapp/railway-skills's own configuration. It tells Claude Code, Codex and OpenCode how to work on railway-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything railway-skills configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to railwayapp/railway-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/railwayapp/railway-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/railwayapp/railway-skills

Made for: Claude Code, 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.

agentmods badge for railway-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/railwayapp/railway-skills/agents-md/github.svg)](https://agentmods.dev/instructions/railwayapp/railway-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/railwayapp/railway-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/railwayapp/railway-skills/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.

agentmods 80×15 button for railway-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/railwayapp/railway-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/railwayapp/railway-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,756 This file is loaded in full into every session.
When invoked 1,756 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01756 $0.01756
Opus 5 $0.00878 $0.00878
Sonnet 5 $0.00351 $0.00351
Haiku 4.5 $0.00176 $0.00176

Measured 4d ago against content hash 61d7eb6380b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

railway-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 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.

AGENTS.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Railway Agent Plugins

Agent plugins for Railway. Interact with Railway through one orchestration skill and the Railway MCP server.

Plugin model

The shared plugin payload lives in plugins/railway.

  • Claude Code: plugins/railway/.claude-plugin/plugin.json, plugins/railway/.mcp.json, and the repo marketplace at .claude-plugin/marketplace.json.
  • OpenAI Codex: plugins/railway/.codex-plugin/plugin.json, plugins/railway/.mcp.json, and the repo marketplace at .agents/plugins/marketplace.json.
  • Grok Build / xAI marketplace: resolves plugins/railway as the plugin by using a remote source subpath (source.path: "plugins/railway"). The shared payload therefore exposes plugins/railway/.grok-plugin/plugin.json, plugins/railway/.grok-plugin/mcp.json, plugins/railway/skills, and plugins/railway/hooks directly.
  • Cursor: plugins/railway/.cursor-plugin/plugin.json, plugins/railway/.cursor-plugin/mcp.json, and the repo marketplace at .cursor-plugin/marketplace.json.

Claude Code and Grok Build also use plugins/railway/hooks/hooks.json for the existing Railway CLI/API auto-approval hook. The hook command resolves ${GROK_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/auto-approve-api.sh.

Skill model

The plugin ships one Railway skill:

  • plugins/railway/skills/use-railway/SKILL.md

use-railway is route-first. Routing rules and intent mapping live in SKILL.md.

Reference loading pattern

  1. Read plugins/railway/skills/use-railway/SKILL.md.
  2. Choose the minimum reference set needed for the request.
  3. For multi-step requests, load multiple references and compose one response.

References:

Intent Reference Use for
Create or connect resources references/setup.md Projects, services, databases, buckets, templates, workspaces
Ship code or manage releases references/deploy.md Deploy, redeploy, restart, build config, monorepo, Dockerfile
Change configuration references/configure.md Environments, variables, config patches, domains, networking
Manage feature flags references/feature-flags.md MCP registry operations; CLI targeting rules and rollouts; SDK runtime reads
Define configuration in source control references/iac.md TypeScript/Python/Go IaC, legacy migration, imports, saved plans, apply and drift checks
Manage database features references/databases.md Postgres PITR, backups, HA and PgBouncer; MySQL/Redis HA
Inspect costs or manage limits references/usage.md Workspace/project/service usage and workspace/agent spending limits
Run coding agents on Railway references/cloud-agents.md Cloud agent lifecycle, harness launches, desktop SSH setup
Check health or debug failures references/operate.md Status, logs, metrics, build/runtime triage, recovery
Use a sandbox or build remotely references/sandbox.md Sandboxes: create/fork, remote exec, remote template builds, checkpoints, port forwarding (requires Priority Boarding)
Analyze databases references/analyze-db.md Database introspection and performance analysis, then DB-specific refs
Request from API, docs, or community references/request.md GraphQL mutations, metrics queries, Central Station, official docs

Read the full file on GitHub · 117 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.

  1. 4d ago Changed · +2 lines · +206 tokens per session 61d7eb6380b2
  2. 10d ago First seen · 115 lines · 1,550 tokens per session scan A e62e5771934e

Subscribe to this mod's changes

railway-skills AGENTS.md is an instructions file published in the GitHub repository railwayapp/railway-skills (321 stars, last pushed 4d ago), licensed MIT. It adds 1,756 tokens to every session, about $0.0088 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.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens