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.
curl -O https://raw.githubusercontent.com/railwayapp/railway-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/railwayapp/railway-skillsWrote 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/railwayapp/railway-skills/agents-md)<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.
<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>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 | $0.01756 | $0.01756 |
| Opus 5 | $0.00878 | $0.00878 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
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.
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/railwayas the plugin by using a remote source subpath (source.path: "plugins/railway"). The shared payload therefore exposesplugins/railway/.grok-plugin/plugin.json,plugins/railway/.grok-plugin/mcp.json,plugins/railway/skills, andplugins/railway/hooksdirectly. - 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
- Read
plugins/railway/skills/use-railway/SKILL.md. - Choose the minimum reference set needed for the request.
- 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 |
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 · +2 lines · +206 tokens per session 61d7eb6380b2
- 10d ago First seen · 115 lines · 1,550 tokens per session scan A e62e5771934e
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.
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.
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.
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).
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).
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.
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.