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.
npx skills add osouthgate/agent-plus-skills --skill railway-opsgit clone --depth 1 https://github.com/osouthgate/agent-plus-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/skills/osouthgate/agent-plus-skills/railway-ops)<a href="https://agentmods.dev/skills/osouthgate/agent-plus-skills/railway-ops"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus-skills/railway-ops/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/skills/osouthgate/agent-plus-skills/railway-ops"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus-skills/railway-ops.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 | $0.00098 | $0.04754 |
| Opus 5 | $0.00049 | $0.02377 |
| Sonnet 5 | $0.00020 | $0.00951 |
| Haiku 4.5 | $0.00010 | $0.00475 |
Grade A, and why
railway-ops 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 10d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
railway-ops
Project-scoped CLI that wraps the Railway CLI into a read-first, JSON-output overview tool. Stdlib-only Python 3. Designed for incident triage — one call returns the full project/services/errors/envs picture so you don't burn context chaining per-service railway invocations.
Lives at ${CLAUDE_SKILL_DIR}/../../bin/railway-ops; the plugin auto-adds bin/ to PATH, so just run railway-ops ....
Prerequisites
railwayCLI installed and on PATH (railway --versionmust succeed).- Authenticated —
railway loginmust have run (railway whoamimust return a user). - Project linked —
railway linkmust have been run in this repo (or pass--env <name>explicitly). - Optional:
RAILWAY_API_TOKEN(orRAILWAY_TOKEN) env var — unlocks deploy history via Railway's GraphQL API, giving youactiveDeploy(currently serving) separately fromlatestDeploy(most recent attempt), plus commit SHA, PR number, branch, and timestamps on each. Without a token the skill still works — it just falls back to a single CLI-sourced deploy with onlyid/status.
The skill bails with a clear message if any of these preconditions are missing.
When to reach for this
- User asks "what's happening in prod" — run
overview --env production --prettyand you get services, deploy status, recent errors, and env var names in one shot. - User asks "why is broken" — run
errors <service> --env production --prettyfor focused error/warning triage. - User asks "what env vars does have" — run
envs <service>to get NAMES only. Values never touch stdout. - User says "show me Railway" / "Railway status" — run
statusto get the project/env/whoami context.
When NOT to use this — fall back to railway directly
This wrapper is read-only by design. Write actions are deliberately unwrapped and rejected (up, deploy, redeploy, restart, down, delete, init, link, unlink, add, scale). If the user wants to DO something (change state), you should skip railway-ops entirely and use the raw railway CLI — it's already authed on their machine.
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.
- 10d ago First seen · 269 lines · 98 tokens per session scan A 979addb0c6e0
railway-ops is a skill published in the GitHub repository osouthgate/agent-plus-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 4,754 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
coolify
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…
cloud-administration
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get…
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
virtualization-operations
Runs the hypervisor layer beneath the servers — host capacity and consolidation ratios, VM sprawl, snapshot discipline, resilience and live migration, and licensing that counts cores rather than instances. Use this to size or expand a cluster, work out why VMs are slow when the hosts look idle, clean up sprawl, set…
network-administration
Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the network's trust assumptions still hold.
business-continuity-and-resilience
Plans for operating through disruption — impact analysis, recovery objectives, continuity plans, and the exercises that prove they work. Use this to run a business impact analysis, set RTO and RPO, write or test a continuity plan, prepare for a supplier or site failure, or answer a customer's resilience questionnaire.