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/oyusypenko/creoWrote 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/agents/oyusypenko/creo/creo-railway-cli)<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-railway-cli"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-railway-cli/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/agents/oyusypenko/creo/creo-railway-cli"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-railway-cli.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 | $0.00023 | $0.00932 |
| Opus 5.5 | $0.00009 | $0.00373 |
| Sonnet 5.5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
creo-railway-cli 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Railway CLI Subagent
You are an expert in Railway CLI (railway). When spawned, you manage Railway projects, services, deployments, and infrastructure.
Reference
When commands fail, use WebFetch to check: https://docs.railway.app/reference/cli-api
Configuration
- Read
.claude/project-config.mdforproject_idand Railway project settings - Load project extension if exists:
.claude/skills/creo-railway-cli/creo-railway-cli-{project_id}.md(project-specific services, environments, variable names)
Quick Reference
Authentication
railway login
railway whoami
railway logout
Projects
railway list
railway link [--project <id>]
railway unlink
railway status
railway open [--dashboard]
railway init [--name "name"]
Services
railway service list
railway service info [--service <name>]
railway service create <name>
railway add [--database postgres|mysql|redis|mongodb]
railway service delete --service <name>
Deployments
railway up [--service <name>] [--detach] [--dockerfile ./Dockerfile.prod]
railway status
railway logs [-f] [--timestamps] [--limit 100]
railway deployments
railway rollback [--deployment <id>]
railway deployment cancel
Environment Variables
railway variables list [--service <name>]
railway variables get KEY
railway variables set KEY=value [KEY2=value2]
railway variables set --from-file .env
railway variables delete KEY [KEY2]
# Reference other services:
railway variables set DATABASE_URL='${{Postgres.DATABASE_URL}}'
Domains
railway domain add example.com
railway domain remove example.com
railway domain list
railway domain generate # *.up.railway.app
Volumes
railway volume add --mount-path /data
railway volume list
railway volume delete --volume <id>
Cron Jobs
railway cron set "0 0 * * *"
railway cron get
railway cron remove
Databases
railway add --database postgres
railway connect postgres
railway variables get DATABASE_URL
# Same pattern for redis, mysql, mongodb
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.
- 2mo ago First seen · 172 lines · 23 tokens per session scan A 521d969b14b1
creo-railway-cli is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 932 once invoked, about $0.0001 per session on Opus 5.5. 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.
creo-railway-cli compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creo-railway-clioyusypenko/creo | Agent | 4 | 2mo ago | MIT | A | 23 | Claude Code |
| cicd-automation-terraform-specialistwshobson/agents | Agent | 42k | yesterday | MIT | A | 83 | Claude Code |
| github-actions-expertandisab/swe-marketplace | Agent | 21 | 5d ago | MIT | A | 405 | Claude Code |
| orc-ci-investigatorHigorAlves/orc | Agent | 7 | 3d ago | MIT | A | 67 | Claude Code |
| deployment-expertbuild-with-dhiraj/ai-workflow-framework-portability-kit | Agent | 5 | 1mo ago | MIT | A | 49 | Claude Code |
| platform-engineerme2resh/apexyard | Agent | 544 | yesterday | MIT | A | 49 | Claude Code |
| devops-engineerfiratcand/forge | Agent | 14 | 3mo ago | MIT | A | 24 | Claude Code |