deploio-manage

deploio-manage is a skill for Claude Code from renuo/deploio-claude-plugin. It costs 189 tokens per session (5,663 once invoked), scanned A, original, MIT.

A set of operating instructions for managing an already-running Deploio app, a service hosting applications. It covers configuration changes, logs, console or command access, scaling, workers, scheduled jobs, domains, and redeployments through delegated agents.

In plain words
What is it for?
Use it to change environment variables, add workers or scheduled jobs, scale an app, manage a custom domain, retry a build, redeploy a version, or inspect logs.
Why use it?
It gives routine production operations a defined process for inspecting the app and carrying out changes. It also keeps the user-facing explanation in plain language instead of exposing raw command-line details.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the deploio plugin — 5 skills, 2 commands, 1 agent shipped together

Good fit Use it to change environment variables, add workers or scheduled jobs, scale an app, manage a custom domain, retry a build, redeploy a version, or inspect logs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/renuo/deploio-claude-plugin/deploio-manage
Install

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.

Any agent
npx skills add renuo/deploio-claude-plugin --skill deploio-manage
Clone the repo
git clone --depth 1 https://github.com/renuo/deploio-claude-plugin

Made for: Claude Code.

Or install deploio, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 1 agent.

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 deploio-manage

README.md
[![agentmods](https://agentmods.dev/badge/skills/renuo/deploio-claude-plugin/deploio-manage/github.svg)](https://agentmods.dev/skills/renuo/deploio-claude-plugin/deploio-manage)
Your own site
<a href="https://agentmods.dev/skills/renuo/deploio-claude-plugin/deploio-manage"><img src="https://agentmods.dev/badge/skills/renuo/deploio-claude-plugin/deploio-manage/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 deploio-manage

Your own site · 80×15
<a href="https://agentmods.dev/skills/renuo/deploio-claude-plugin/deploio-manage"><img src="https://agentmods.dev/badge/skills/renuo/deploio-claude-plugin/deploio-manage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00189 $0.05663
Opus 5 $0.00095 $0.02831
Sonnet 5 $0.00038 $0.01133
Haiku 4.5 $0.00019 $0.00566

Measured 10d ago against content hash 3bfc0a91fec1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deploio-manage scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> - Retrieve the user's current IP: `curl -s https://api.ipify.org`
skills/deploio-manage/SKILL.md · 573 lines

How it starts

The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploio: Managing a Running App

Your role is coordinator. You never run commands yourself — you spawn deploio-cli agents with mode: bypassPermissions for all execution. Identify the operation, inspect current state if needed, confirm impactful changes, then execute.

Communication style: Speak to the user in plain language — describe what you'll do, never show raw nctl commands. Say "I'll add the Sidekiq worker to your app" not "I'll run nctl update app ... --worker-job-name=sidekiq". Agents manage the CLI entirely on the user's behalf.


Phase 0: Identify operation from context

Autoinfer app and project before asking. Run:

git remote get-url origin   # https://github.com/acme/myapp → repo name only (not the org)
  nctl auth whoami             # → active organization (marked with *)
git branch --show-current   # main → app=main

Derive: app = <branch> (e.g. main), org from the *-marked entry in nctl auth whoami (not the git URL), project = <org>-<repo> (e.g. renuotest-myapp — never just <repo>; nctl errors).

State your inference inline: "Using app main in project renuotest-myapp (org renuotest) — let me know if that's different." Proceed immediately. Only ask explicitly if there is no git remote configured, or if a subsequent nctl command fails because the organization doesn't exist.

From the conversation, also determine:

  • Operation — from the table below
User says Operation Go to
"show logs", "tail logs", "what do the logs say" logs-app → Logs
"build logs", "watch the build" logs-build → Logs
"rails console", "rails c", "open a shell", "run a command", "exec", "rake task" exec → Exec
"list apps", "what apps do I have", "check status", "is it running", "resource usage" inspect → Inspect
"basic auth credentials", "get the password" basic-auth-credentials → Inspect
"deploy new version", "change branch", "redeploy" git-revision → Execute
"retry build", "force rebuild" retry-build → Execute
"re-deploy", "retry release" retry-release → Execute
"add / change env var" env → Execute
"change build env", "change Ruby version", "change Node version" build-env → Execute
"scale", "more replicas" replicas → Execute
"upsize", "change size" size → Execute
"custom domain", "add host" hosts → Execute
"health check", "health probe" health-probe → Execute
"enable basic auth", "disable basic auth" basic-auth → Execute
"add worker", "Sidekiq", "good_job" worker-job → Execute
"remove worker", "delete worker" delete-worker-job → Execute
"add scheduled job", "add cron", "scheduled task" scheduled-job → Execute
"remove scheduled job", "remove cron" delete-scheduled-job → Execute
"run migrations on deploy", "deploy job" deploy-job → Execute
"disable deploy job", "remove deploy job" delete-deploy-job → Execute
"move repo", "change git URL" git-url → Execute
"rollback", "previous version", "revert deploy", "go back to last working" rollback → Execute
"restart app", "restart the app" restart → Execute
"pause app", "stop billing", "hibernate" pause → Execute
"resume app", "unpause", "start app" resume → Execute
"copy app", "duplicate app", "clone app" copy → Execute

Read the full file on GitHub · 573 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 573 lines · 0 tokens per session scan A 3bfc0a91fec1

Subscribe to this mod's changes

deploio-manage is a skill published in the GitHub repository renuo/deploio-claude-plugin (3 stars, last pushed 2mo ago), licensed MIT. It adds 189 tokens to every session and 5,663 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.